Guido de Croon

Sabrina M. Neuman, Brian Plancher, Bardienus P. Duisterhof et al.

Machine learning (ML) has become a pervasive tool across computing systems. An emerging application that stress-tests the challenges of ML system design is tiny robot learning, the deployment of ML on resource-constrained low-cost autonomous robots. Tiny robot learning lies at the intersection of embedded systems, robotics, and ML, compounding the challenges of these domains. Tiny robot learning is subject to challenges from size, weight, area, and power (SWAP) constraints; sensor, actuator, and compute hardware limitations; end-to-end system tradeoffs; and a large diversity of possible deployment scenarios. Tiny robot learning requires ML models to be designed with these challenges in mind, providing a crucible that reveals the necessity of holistic ML system design and automated end-to-end design tools for agile development. This paper gives a brief survey of the tiny robot learning space, elaborates on key challenges, and proposes promising opportunities for future work in ML system design.

Jason Yik, Korneel Van den Berghe, Douwe den Blanken et al. · eth-zurich

Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. Prior neuromorphic computing benchmark efforts have not seen widespread adoption due to a lack of inclusive, actionable, and iterative benchmark design and guidelines. To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems. NeuroBench is a collaboratively-designed effort from an open community of researchers across industry and academia, aiming to provide a representative structure for standardizing the evaluation of neuromorphic approaches. The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings. In this article, we outline tasks and guidelines for benchmarks across multiple application domains, and present initial performance baselines across neuromorphic and conventional approaches for both benchmark tracks. NeuroBench is intended to continually expand its benchmarks and features to foster and track the progress made by the research community.

Cheng Liu, Erik-Jan van Kampen, Guido C. H. E. de Croon

Enabling the capability of assessing risk and making risk-aware decisions is essential to applying reinforcement learning to safety-critical robots like drones. In this paper, we investigate a specific case where a nano quadcopter robot learns to navigate an apriori-unknown cluttered environment under partial observability. We present a distributional reinforcement learning framework to generate adaptive risk-tendency policies. Specifically, we propose to use lower tail conditional variance of the learnt return distribution as intrinsic uncertainty estimation, and use exponentially weighted average forecasting (EWAF) to adapt the risk-tendency in accordance with the estimated uncertainty. In simulation and real-world empirical results, we show that (1) the most effective risk-tendency vary across states, (2) the agent with adaptive risk-tendency achieves superior performance compared to risk-neutral policy or risk-averse policy baselines.

Federico Paredes-Vallés, Kirk Y. W. Scheper, Christophe De Wagter et al.

Event cameras have recently gained significant traction since they open up new avenues for low-latency and low-power solutions to complex computer vision problems. To unlock these solutions, it is necessary to develop algorithms that can leverage the unique nature of event data. However, the current state-of-the-art is still highly influenced by the frame-based literature, and usually fails to deliver on these promises. In this work, we take this into consideration and propose a novel self-supervised learning pipeline for the sequential estimation of event-based optical flow that allows for the scaling of the models to high inference frequencies. At its core, we have a continuously-running stateful neural model that is trained using a novel formulation of contrast maximization that makes it robust to nonlinearities and varying statistics in the input events. Results across multiple datasets confirm the effectiveness of our method, which establishes a new state of the art in terms of accuracy for approaches trained or optimized without ground truth.

Federico Paredes-Vallés, Jesse Hagenaars, Julien Dupeyroux et al.

Biological sensing and processing is asynchronous and sparse, leading to low-latency and energy-efficient perception and action. In robotics, neuromorphic hardware for event-based vision and spiking neural networks promises to exhibit similar characteristics. However, robotic implementations have been limited to basic tasks with low-dimensional sensory inputs and motor actions due to the restricted network size in current embedded neuromorphic processors and the difficulties of training spiking neural networks. Here, we present the first fully neuromorphic vision-to-control pipeline for controlling a freely flying drone. Specifically, we train a spiking neural network that accepts high-dimensional raw event-based camera data and outputs low-level control actions for performing autonomous vision-based flight. The vision part of the network, consisting of five layers and 28.8k neurons, maps incoming raw events to ego-motion estimates and is trained with self-supervised learning on real event data. The control part consists of a single decoding layer and is learned with an evolutionary algorithm in a drone simulator. Robotic experiments show a successful sim-to-real transfer of the fully learned neuromorphic pipeline. The drone can accurately follow different ego-motion setpoints, allowing for hovering, landing, and maneuvering sideways$\unicode{x2014}$even while yawing at the same time. The neuromorphic pipeline runs on board on Intel's Loihi neuromorphic processor with an execution frequency of 200 Hz, spending only 27 $\unicode{x00b5}$J per inference. These results illustrate the potential of neuromorphic sensing and processing for enabling smaller, more intelligent robots.

Levi Burner, Guido de Croon, Yiannis Aloimonos

Animals with foveated vision, including humans, experience microsaccades, small, rapid eye movements that they are not aware of. Inspired by this phenomenon, we develop a method for "Artificial Microsaccade Compensation". It can stabilize video captured by a tailless ornithopter that has resisted attempts to use camera-based sensing because it shakes at 12-20 Hz. Our approach minimizes changes in image intensity by optimizing over 3D rotation represented in SO(3). This results in a stabilized video, computed in real time, suitable for human viewing, and free from distortion. When adapted to hold a fixed viewing orientation, up to occasional saccades, it can dramatically reduce inter-frame motion while also benefiting from an efficient recursive update. When compared to Adobe Premier Pro's warp stabilizer, which is widely regarded as the best commercial video stabilization software available, our method achieves higher quality results while also running in real time.

Yingfu Xu, Guangzhi Tang, Amirreza Yousefzadeh et al.

Spiking neural networks (SNNs) for event-based optical flow are claimed to be computationally more efficient than their artificial neural networks (ANNs) counterparts, but a fair comparison is missing in the literature. In this work, we propose an event-based optical flow solution based on activation sparsification and a neuromorphic processor, SENECA. SENECA has an event-driven processing mechanism that can exploit the sparsity in ANN activations and SNN spikes to accelerate the inference of both types of neural networks. The ANN and the SNN for comparison have similar low activation/spike density (~5%) thanks to our novel sparsification-aware training. In the hardware-in-loop experiments designed to deduce the average time and energy consumption, the SNN consumes 44.9ms and 927.0 microjoules, which are 62.5% and 75.2% of the ANN's consumption, respectively. We find that SNN's higher efficiency attributes to its lower pixel-wise spike density (43.5% vs. 66.5%) that requires fewer memory access operations for neuron states.

Yilun Wu, Federico Paredes-Vallés, Guido C. H. E. de Croon

Inspired by frame-based methods, state-of-the-art event-based optical flow networks rely on the explicit construction of correlation volumes, which are expensive to compute and store, rendering them unsuitable for robotic applications with limited compute and energy budget. Moreover, correlation volumes scale poorly with resolution, prohibiting them from estimating high-resolution flow. We observe that the spatiotemporally continuous traces of events provide a natural search direction for seeking pixel correspondences, obviating the need to rely on gradients of explicit correlation volumes as such search directions. We introduce IDNet (Iterative Deblurring Network), a lightweight yet high-performing event-based optical flow network directly estimating flow from event traces without using correlation volumes. We further propose two iterative update schemes: "ID" which iterates over the same batch of events, and "TID" which iterates over time with streaming events in an online fashion. Our top-performing ID model sets a new state of the art on DSEC benchmark. Meanwhile, the base ID model is competitive with prior arts while using 80% fewer parameters, consuming 20x less memory footprint and running 40% faster on the NVidia Jetson Xavier NX. Furthermore, the TID model is even more efficient offering an additional 5x faster inference speed and 8 ms ultra-low latency at the cost of only a 9% performance drop, making it the only model among current literature capable of real-time operation while maintaining decent performance.

Rik J. Bouwmeester, Federico Paredes-Vallés, Guido C. H. E. de Croon

Nano quadcopters are small, agile, and cheap platforms that are well suited for deployment in narrow, cluttered environments. Due to their limited payload, these vehicles are highly constrained in processing power, rendering conventional vision-based methods for safe and autonomous navigation incompatible. Recent machine learning developments promise high-performance perception at low latency, while dedicated edge computing hardware has the potential to augment the processing capabilities of these limited devices. In this work, we present NanoFlowNet, a lightweight convolutional neural network for real-time dense optical flow estimation on edge computing hardware. We draw inspiration from recent advances in semantic segmentation for the design of this network. Additionally, we guide the learning of optical flow using motion boundary ground truth data, which improves performance with no impact on latency. Validation results on the MPI-Sintel dataset show the high performance of the proposed network given its constrained architecture. Additionally, we successfully demonstrate the capabilities of NanoFlowNet by deploying it on the ultra-low power GAP8 microprocessor and by applying it to vision-based obstacle avoidance on board a Bitcraze Crazyflie, a 34 g nano quadcopter.

Yingfu Xu, Guido C. H. E. de Croon

Learning-based visual ego-motion estimation is promising yet not ready for navigating agile mobile robots in the real world. In this article, we propose CUAHN-VIO, a robust and efficient monocular visual-inertial odometry (VIO) designed for micro aerial vehicles (MAVs) equipped with a downward-facing camera. The vision frontend is a content-and-uncertainty-aware homography network (CUAHN) that is robust to non-homography image content and failure cases of network prediction. It not only predicts the homography transformation but also estimates its uncertainty. The training is self-supervised, so that it does not require ground truth that is often difficult to obtain. The network has good generalization that enables "plug-and-play" deployment in new environments without fine-tuning. A lightweight extended Kalman filter (EKF) serves as the VIO backend and utilizes the mean prediction and variance estimation from the network for visual measurement updates. CUAHN-VIO is evaluated on a high-speed public dataset and shows rivaling accuracy to state-of-the-art (SOTA) VIO approaches. Thanks to the robustness to motion blur, low network inference time (~23ms), and stable processing latency (~26ms), CUAHN-VIO successfully runs onboard an Nvidia Jetson TX2 embedded processor to navigate a fast autonomous MAV.

Diana A. Olejnik, Sunyi Wang, Julien Dupeyroux et al.

This paper discusses a low-cost, open-source and open-hardware design and performance evaluation of a low-speed, multi-fan wind system dedicated to micro air vehicle (MAV) testing. In addition, a set of experiments with a flapping wing MAV and rotorcraft is presented, demonstrating the capabilities of the system and the properties of these different types of drones in response to various types of wind. We performed two sets of experiments where a MAV is flying into the wake of the fan system, gathering data about states, battery voltage and current. Firstly, we focus on steady wind conditions with wind speeds ranging from 0.5 m/s to 3.4 m/s. During the second set of experiments, we introduce wind gusts, by periodically modulating the wind speed from 1.3 m/s to 3.4 m/s with wind gust oscillations of 0.5 Hz, 0.25 Hz and 0.125 Hz. The "Flapper" flapping wing MAV requires much larger pitch angles to counter wind than the "CrazyFlie" quadrotor. This is due to the Flapper's larger wing surface. In forward flight, its wings do provide extra lift, considerably reducing the power consumption. In contrast, the CrazyFlie's power consumption stays more constant for different wind speeds. The experiments with the varying wind show a quicker gust response by the CrazyFlie compared with the Flapper drone, but both their responses could be further improved. We expect that the proposed wind gust system will provide a useful tool to the community to achieve such improvements.

Marina González-Álvarez, Julien Dupeyroux, Federico Corradi et al.

Robotic airships offer significant advantages in terms of safety, mobility, and extended flight times. However, their highly restrictive weight constraints pose a major challenge regarding the available computational resources to perform the required control tasks. Neuromorphic computing stands for a promising research direction for addressing such problem. By mimicking the biological process for transferring information between neurons using spikes or impulses, spiking neural networks (SNNs) allow for low power consumption and asynchronous event-driven processing. In this paper, we propose an evolved altitude controller based on an SNN for a robotic airship which relies solely on the sensory feedback provided by an airborne radar. Starting from the design of a lightweight, low-cost, open-source airship, we also present an SNN-based controller architecture, an evolutionary framework for training the network in a simulated environment, and a control strategy for ameliorating the gap with reality. The system's performance is evaluated through real-world experiments, demonstrating the advantages of our approach by comparing it with an artificial neural network and a linear controller. The results show an accurate tracking of the altitude command with an efficient control effort.

Bardienus P. Duisterhof, Shushuai Li, Javier Burgués et al.

Nano quadcopters are ideal for gas source localization (GSL) as they are safe, agile and inexpensive. However, their extremely restricted sensors and computational resources make GSL a daunting challenge. In this work, we propose a novel bug algorithm named `Sniffy Bug', which allows a fully autonomous swarm of gas-seeking nano quadcopters to localize a gas source in an unknown, cluttered and GPS-denied environments. The computationally efficient, mapless algorithm foresees in the avoidance of obstacles and other swarm members, while pursuing desired waypoints. The waypoints are first set for exploration, and, when a single swarm member has sensed the gas, by a particle swarm optimization-based procedure. We evolve all the parameters of the bug (and PSO) algorithm, using our novel simulation pipeline, `AutoGDM'. It builds on and expands open source tools in order to enable fully automated end-to-end environment generation and gas dispersion modeling, allowing for learning in simulation. Flight tests show that Sniffy Bug with evolved parameters outperforms manually selected parameters in cluttered, real-world environments.

Shushuai Li, Christophe De Wagter, Guido C. H. E. de Croon

Relative localization is an important ability for multiple robots to perform cooperative tasks in GPS-denied environment. This paper presents a novel autonomous positioning framework for monocular relative localization of multiple tiny flying robots. This approach does not require any groundtruth data from external systems or manual labelling. Instead, the proposed framework is able to label real-world images with 3D relative positions between robots based on another onboard relative estimation technology, using ultra-wide band (UWB). After training in this self-supervised manner, the proposed deep neural network (DNN) can predict relative positions of peer robots by purely using a monocular camera. This deep learning-based visual relative localization is scalable, distributed and autonomous. We also built an open-source and light-weight simulation pipeline by using Blender for 3D rendering, which allows synthetic image generation of other robots, and generalized training of the neural network. The proposed localization framework is tested on two real-world Crazyflie2 quadrotors by running the DNN on the onboard AIdeck (a tiny AI chip and monocular camera). All results demonstrate the effectiveness of the self-supervised multi-robot localization method.

Yingfu Xu, Guido C. H. E. de Croon

In the field of visual ego-motion estimation for Micro Air Vehicles (MAVs), fast maneuvers stay challenging mainly because of the big visual disparity and motion blur. In the pursuit of higher robustness, we study convolutional neural networks (CNNs) that predict the relative pose between subsequent images from a fast-moving monocular camera facing a planar scene. Aided by the Inertial Measurement Unit (IMU), we mainly focus on translational motion. The networks we study have similar small model sizes (around 1.35MB) and high inference speeds (around 10 milliseconds on a mobile GPU). Images for training and testing have realistic motion blur. Departing from a network framework that iteratively warps the first image to match the second with cascaded network blocks, we study different network architectures and training strategies. Simulated datasets and a self-collected MAV flight dataset are used for evaluation. The proposed setup shows better accuracy over existing networks and traditional feature-point-based methods during fast maneuvers. Moreover, self-supervised learning outperforms supervised learning. Videos and open-sourced code are available at https://github.com/tudelft/PoseNet_Planar

Shushuai Li, Feng Shan, Jiangpeng Liu et al.

Lightweight aerial swarms have potential applications in scenarios where larger drones fail to operate efficiently. The primary foundation for lightweight aerial swarms is efficient relative localization, which enables cooperation and collision avoidance. Computing the real-time position is challenging due to extreme resource constraints. This paper presents an autonomous relative localization technique for lightweight aerial swarms without infrastructure by fusing ultra-wideband wireless distance measurements and the shared state information (e.g., velocity, yaw rate, height) from neighbors. This is the first fully autonomous, tiny, fast, and accurate relative localization scheme implemented on a team of 13 lightweight (33 grams) and resource-constrained (168MHz MCU with 192 KB memory) aerial vehicles. The proposed resource-constrained swarm ranging protocol is scalable, and a surprising theoretical result is discovered: the unobservability poses no issues because the state drift leads to control actions that make the state observable again. By experiment, less than 0.2m position error is achieved at the frequency of 16Hz for as many as 13 drones. The code is open-sourced, and the proposed technique is relevant not only for tiny drones but can be readily applied to many other resource-restricted robots. Video and code can be found at \textnormal{\url{https://shushuai3.github.io/autonomous-swarm/}}.

Federico Paredes-Vallés, Kirk Y. W. Scheper, Guido C. H. E. de Croon

The combination of spiking neural networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from the raw stimuli generated with an event-based camera. A novel adaptive neuron model and stable spike-timing-dependent plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. After convergence, the neural architecture exhibits the main properties of biological visual motion systems, namely feature extraction and local and global motion perception. Convolutional layers with input synapses characterized by single and multiple transmission delays are employed for feature and local motion perception, respectively; while global motion selectivity emerges in a final fully-connected layer. The proposed solution is validated using synthetic and real event sequences. Along with this paper, we provide the cuSNN library, a framework that enables GPU-accelerated simulations of large-scale spiking neural networks. Source code and samples are available at https://github.com/tudelft/cuSNN.

Stein Stroobants, Christophe de Wagter, Guido C. H. E. De Croon

The real-world application of small drones is mostly hampered by energy limitations. Neuromorphic computing promises extremely energy-efficient AI for autonomous flight but is still challenging to train and deploy on real robots. To reap the maximal benefits from neuromorphic computing, it is necessary to perform all autonomy functions end-to-end on a single neuromorphic chip, from low-level attitude control to high-level navigation. This research presents the first neuromorphic control system using a spiking neural network (SNN) to effectively map a drone's raw sensory input directly to motor commands. We apply this method to low-level attitude estimation and control for a quadrotor, deploying the SNN on a tiny Crazyflie. We propose a modular SNN, separately training and then merging estimation and control sub-networks. The SNN is trained with imitation learning, using a flight dataset of sensory-motor pairs. Post-training, the network is deployed on the Crazyflie, issuing control commands from sensor inputs at 500Hz. Furthermore, for the training procedure we augmented training data by flying a controller with additional excitation and time-shifting the target data to enhance the predictive capabilities of the SNN. On the real drone, the perception-to-control SNN tracks attitude commands with an average error of 3.0 degrees, compared to 2.7 degrees for the regular flight stack. We also show the benefits of the proposed learning modifications for reducing the average tracking error and reducing oscillations. Our work shows the feasibility of performing neuromorphic end-to-end control, laying the basis for highly energy-efficient and low-latency neuromorphic autopilots.

Jesse Hagenaars, Yilun Wu, Federico Paredes-Vallés et al.

Event cameras provide low-latency perception for only milliwatts of power. This makes them highly suitable for resource-restricted, agile robots such as small flying drones. Self-supervised learning based on contrast maximization holds great potential for event-based robot vision, as it foregoes the need for high-frequency ground truth and allows for online learning in the robot's operational environment. However, online, on-board learning raises the major challenge of achieving sufficient computational efficiency for real-time learning, while maintaining competitive visual perception performance. In this work, we improve the time and memory efficiency of the contrast maximization pipeline, making on-device learning of low-latency monocular depth possible. We demonstrate that online learning on board a small drone yields more accurate depth estimates and more successful obstacle avoidance behavior compared to only pre-training. Benchmarking experiments show that the proposed pipeline is not only efficient, but also achieves state-of-the-art depth estimation performance among self-supervised approaches. Our work taps into the unused potential of online, on-device robot learning, promising smaller reality gaps and better performance.

Jesse J. Hagenaars, Stein Stroobants, Sander M. Bohte et al.

Vision is an essential part of attitude control for many flying animals, some of which have no dedicated sense of gravity. Flying robots, on the other hand, typically depend heavily on accelerometers and gyroscopes for attitude stabilization. In this work, we present the first vision-only approach to flight control for use in generic environments. We show that a quadrotor drone equipped with a downward-facing event camera can estimate its attitude and rotation rate from just the event stream, enabling flight control without inertial sensors. Our approach uses a small recurrent convolutional neural network trained through supervised learning. Real-world flight tests demonstrate that our combination of event camera and low-latency neural network is capable of replacing the inertial measurement unit in a traditional flight control loop. Furthermore, we investigate the network's generalization across different environments, and the impact of memory and different fields of view. While networks with memory and access to horizon-like visual cues achieve best performance, variants with a narrower field of view achieve better relative generalization. Our work showcases vision-only flight control as a promising candidate for enabling autonomous, insect-scale flying robots.

Michiel Firlefyn, Jesse Hagenaars, Guido de Croon

Insects have long been recognized for their ability to navigate and return home using visual cues from their nest's environment. However, the precise mechanism underlying this remarkable homing skill remains a subject of ongoing investigation. Drawing inspiration from the learning flights of honey bees and wasps, we propose a robot navigation method that directly learns the home vector direction from visual percepts during a learning flight in the vicinity of the nest. After learning, the robot will travel away from the nest, come back by means of odometry, and eliminate the resultant drift by inferring the home vector orientation from the currently experienced view. Using a compact convolutional neural network, we demonstrate successful learning in both simulated and real forest environments, as well as successful homing control of a simulated quadrotor. The average errors of the inferred home vectors in general stay well below the 90° required for successful homing, and below 24° if all images contain sufficient texture and illumination. Moreover, we show that the trajectory followed during the initial learning flight has a pronounced impact on the network's performance. A higher density of sample points in proximity to the nest results in a more consistent return. Code and data are available at https://mavlab.tudelft.nl/learning_to_home .

Dario Izzo, Emmanuel Blazquez, Robin Ferede et al.

Spacecraft and drones aimed at exploring our solar system are designed to operate in conditions where the smart use of onboard resources is vital to the success or failure of the mission. Sensorimotor actions are thus often derived from high-level, quantifiable, optimality principles assigned to each task, utilizing consolidated tools in optimal control theory. The planned actions are derived on the ground and transferred onboard where controllers have the task of tracking the uploaded guidance profile. Here we argue that end-to-end neural guidance and control architectures (here called G&CNets) allow transferring onboard the burden of acting upon these optimality principles. In this way, the sensor information is transformed in real time into optimal plans thus increasing the mission autonomy and robustness. We discuss the main results obtained in training such neural architectures in simulation for interplanetary transfers, landings and close proximity operations, highlighting the successful learning of optimality principles by the neural model. We then suggest drone racing as an ideal gym environment to test these architectures on real robotic platforms, thus increasing confidence in their utilization on future space exploration missions. Drone racing shares with spacecraft missions both limited onboard computational capabilities and similar control structures induced from the optimality principle sought, but it also entails different levels of uncertainties and unmodelled effects. Furthermore, the success of G&CNets on extremely resource-restricted drones illustrates their potential to bring real-time optimal control within reach of a wider variety of robotic systems, both in space and on Earth.

J. Lu, J. J. Hagenaars, G. C. H. E. de Croon

Inspired by the natural nervous system, synaptic plasticity rules are applied to train spiking neural networks with local information, making them suitable for online learning on neuromorphic hardware. However, when such rules are implemented to learn different new tasks, they usually require a significant amount of work on task-dependent fine-tuning. This paper aims to make this process easier by employing an evolutionary algorithm that evolves suitable synaptic plasticity rules for the task at hand. More specifically, we provide a set of various local signals, a set of mathematical operators, and a global reward signal, after which a Cartesian genetic programming process finds an optimal learning rule from these components. Using this approach, we find learning rules that successfully solve an XOR and cart-pole task, and discover new learning rules that outperform the baseline rules from literature.

Christophe De Wagter, Federico Paredes-Vallés, Nilay Sheth et al.

Robotics is the next frontier in the progress of Artificial Intelligence (AI), as the real world in which robots operate represents an enormous, complex, continuous state space with inherent real-time requirements. One extreme challenge in robotics is currently formed by autonomous drone racing. Human drone racers can fly through complex tracks at speeds of up to 190 km/h. Achieving similar speeds with autonomous drones signifies tackling fundamental problems in AI under extreme restrictions in terms of resources. In this article, we present the winning solution of the first AI Robotic Racing (AIRR) Circuit, a competition consisting of four races in which all participating teams used the same drone, to which they had limited access. The core of our approach is inspired by how human pilots combine noisy observations of the race gates with their mental model of the drone's dynamics to achieve fast control. Our approach has a large focus on gate detection with an efficient deep neural segmentation network and active vision. Further, we make contributions to robust state estimation and risk-based control. This allowed us to reach speeds of ~9.2m/s in the last race, unrivaled by previous autonomous drone race competitions. Although our solution was the fastest and most robust, it still lost against one of the best human pilots, Gab707. The presented approach indicates a promising direction to close the gap with human drone pilots, forming an important step in bringing AI to the real world.

Stein Stroobants, Julien Dupeyroux, Guido de Croon

The great promises of neuromorphic sensing and processing for robotics have led researchers and engineers to investigate novel models for robust and reliable control of autonomous robots (navigation, obstacle detection and avoidance, etc.), especially for quadrotors in challenging contexts such as drone racing and aggressive maneuvers. Using spiking neural networks, these models can be run on neuromorphic hardware to benefit from outstanding update rates and high energy efficiency. Yet, low-level controllers are often neglected and remain outside of the neuromorphic loop. Designing low-level neuromorphic controllers is crucial to remove the standard PID, and therefore benefit from all the advantages of closing the neuromorphic loop. In this paper, we propose a parsimonious and adjustable neuromorphic PID controller, endowed with a minimal number of 93 neurons sparsely connected to achieve autonomous, onboard altitude control of a quadrotor equipped with Intel's Loihi neuromorphic chip. We successfully demonstrate the robustness of our proposed network in a set of experiments where the quadrotor is requested to reach a target altitude from take-off. Our results confirm the suitability of such low-level neuromorphic controllers, ultimately with a very high update frequency.

Nitin J. Sanket, Chahat Deep Singh, Chethan M. Parameshwara et al.

The rapid rise of accessibility of unmanned aerial vehicles or drones pose a threat to general security and confidentiality. Most of the commercially available or custom-built drones are multi-rotors and are comprised of multiple propellers. Since these propellers rotate at a high-speed, they are generally the fastest moving parts of an image and cannot be directly "seen" by a classical camera without severe motion blur. We utilize a class of sensors that are particularly suitable for such scenarios called event cameras, which have a high temporal resolution, low-latency, and high dynamic range. In this paper, we model the geometry of a propeller and use it to generate simulated events which are used to train a deep neural network called EVPropNet to detect propellers from the data of an event camera. EVPropNet directly transfers to the real world without any fine-tuning or retraining. We present two applications of our network: (a) tracking and following an unmarked drone and (b) landing on a near-hover drone. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with different propeller shapes and sizes. Our network can detect propellers at a rate of 85.1% even when 60% of the propeller is occluded and can run at upto 35Hz on a 2W power budget. To our knowledge, this is the first deep learning-based solution for detecting propellers (to detect drones). Finally, our applications also show an impressive success rate of 92% and 90% for the tracking and landing tasks respectively.

Benjamin Keltjens, Tom van Dijk, Guido de Croon

Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on indoor environments with camera rotation. Indoor, rotated scenes are common for less constrained applications and pose problems for two reasons: abundance of low texture regions and increased complexity of depth cues for images under rotation. In an effort to extend self-supervised learning to more generalised environments we propose two additions. First, we propose a novel Filled Disparity Loss term that corrects for ambiguity of image reconstruction error loss in textureless regions. Specifically, we interpolate disparity in untextured regions, using the estimated disparity from surrounding textured areas, and use L1 loss to correct the original estimation. Our experiments show that depth estimation is substantially improved on low-texture scenes, without any loss on textured scenes, when compared to Monodepth by Godard et al. Secondly, we show that training with an application's representative rotations, in both pitch and roll, is sufficient to significantly improve performance over the entire range of expected rotation. We demonstrate that depth estimation is successfully generalised as performance is not lost when evaluated on test sets with no camera rotation. Together these developments enable a broader use of self-supervised learning of monocular depth estimation for complex environments.

Jesse Hagenaars, Federico Paredes-Vallés, Guido de Croon

The field of neuromorphic computing promises extremely low-power and low-latency sensing and processing. Challenges in transferring learning algorithms from traditional artificial neural networks (ANNs) to spiking neural networks (SNNs) have so far prevented their application to large-scale, complex regression tasks. Furthermore, realizing a truly asynchronous and fully neuromorphic pipeline that maximally attains the abovementioned benefits involves rethinking the way in which this pipeline takes in and accumulates information. In the case of perception, spikes would be passed as-is and one-by-one between an event camera and an SNN, meaning all temporal integration of information must happen inside the network. In this article, we tackle these two problems. We focus on the complex task of learning to estimate optical flow from event-based camera inputs in a self-supervised manner, and modify the state-of-the-art ANN training pipeline to encode minimal temporal information in its inputs. Moreover, we reformulate the self-supervised loss function for event-based optical flow to improve its convexity. We perform experiments with various types of recurrent ANNs and SNNs using the proposed pipeline. Concerning SNNs, we investigate the effects of elements such as parameter initialization and optimization, surrogate gradient shape, and adaptive neuronal mechanisms. We find that initialization and surrogate gradient width play a crucial part in enabling learning with sparse inputs, while the inclusion of adaptivity and learnable neuronal parameters can improve performance. We show that the performance of the proposed ANNs and SNNs are on par with that of the current state-of-the-art ANNs trained in a self-supervised manner.

Mario Coppola, Jian Guo, Eberhard Gill et al.

This paper proposes a model-based framework to automatically and efficiently design understandable and verifiable behaviors for swarms of robots. The framework is based on the automatic extraction of two distinct models: 1) a neural network model trained to estimate the relationship between the robots' sensor readings and the global performance of the swarm, and 2) a probabilistic state transition model that explicitly models the local state transitions (i.e., transitions in observations from the perspective of a single robot in the swarm) given a policy. The models can be trained from a data set of simulated runs featuring random policies. The first model is used to automatically extract a set of local states that are expected to maximize the global performance. These local states are referred to as desired local states. The second model is used to optimize a stochastic policy so as to increase the probability that the robots in the swarm observe one of the desired local states. Following these steps, the framework proposed in this paper can efficiently lead to effective controllers. This is tested on four case studies, featuring aggregation and foraging tasks. Importantly, thanks to the models, the framework allows us to understand and inspect a swarm's behavior. To this end, we propose verification checks to identify some potential issues that may prevent the swarm from achieving the desired global objective. In addition, we explore how the framework can be used in combination with a "standard" evolutionary robotics strategy (i.e., where performance is measured via simulation), or with online learning.

Daniël Willemsen, Mario Coppola, Guido C. H. E. de Croon

Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials, a property known as sample efficiency. This research thus investigates the use of learned world models to improve sample efficiency. We present a novel multi-agent model-based RL algorithm: Multi-Agent Model-Based Policy Optimization (MAMBPO), utilizing the Centralized Learning for Decentralized Execution (CLDE) framework. CLDE algorithms allow a group of agents to act in a fully decentralized manner after training. This is a desirable property for many systems comprising of multiple robots. MAMBPO uses a learned world model to improve sample efficiency compared to model-free Multi-Agent Soft Actor-Critic (MASAC). We demonstrate this on two simulated multi-robot tasks, where MAMBPO achieves a similar performance to MASAC, but requires far fewer samples to do so. Through this, we take an important step towards making real-life learning for multi-robot systems possible.

Raoul Dinaux, Nikhil Wessendorp, Julien Dupeyroux et al.

Course estimation is a key component for the development of autonomous navigation systems for robots. While state-of-the-art methods widely use visual-based algorithms, it is worth noting that they all fail to deal with the complexity of the real world by being computationally greedy and sometimes too slow. They often require obstacles to be highly textured to improve the overall performance, particularly when the obstacle is located within the focus of expansion (FOE) where the optic flow (OF) is almost null. This study proposes the FAst ITerative Half-plane (FAITH) method to determine the course of a micro air vehicle (MAV). This is achieved by means of an event-based camera, along with a fast RANSAC-based algorithm that uses event-based OF to determine the FOE. The performance is validated by means of a benchmark on a simulated environment and then tested on a dataset collected for indoor obstacle avoidance. Our results show that the computational efficiency of our solution outperforms state-of-the-art methods while keeping a high level of accuracy. This has been further demonstrated onboard an MAV equipped with an event-based camera, showing that our event-based FOE estimation can be achieved online onboard tiny drones, thus opening the path towards fully neuromorphic solutions for autonomous obstacle avoidance and navigation onboard MAVs.

Julien Dupeyroux, Jesse Hagenaars, Federico Paredes-Vallés et al.

Neuromorphic processors like Loihi offer a promising alternative to conventional computing modules for endowing constrained systems like micro air vehicles (MAVs) with robust, efficient and autonomous skills such as take-off and landing, obstacle avoidance, and pursuit. However, a major challenge for using such processors on robotic platforms is the reality gap between simulation and the real world. In this study, we present for the very first time a fully embedded application of the Loihi neuromorphic chip prototype in a flying robot. A spiking neural network (SNN) was evolved to compute the thrust command based on the divergence of the ventral optic flow field to perform autonomous landing. Evolution was performed in a Python-based simulator using the PySNN library. The resulting network architecture consists of only 35 neurons distributed among 3 layers. Quantitative analysis between simulation and Loihi reveals a root-mean-square error of the thrust setpoint as low as 0.005 g, along with a 99.8% matching of the spike sequences in the hidden layer, and 99.7% in the output layer. The proposed approach successfully bridges the reality gap, offering important insights for future neuromorphic applications in robotics. Supplementary material is available at https://mavlab.tudelft.nl/loihi/.

F. Paredes-Vallés, G. C. H. E. de Croon

Event cameras are novel vision sensors that sample, in an asynchronous fashion, brightness increments with low latency and high temporal resolution. The resulting streams of events are of high value by themselves, especially for high speed motion estimation. However, a growing body of work has also focused on the reconstruction of intensity frames from the events, as this allows bridging the gap with the existing literature on appearance- and frame-based computer vision. Recent work has mostly approached this problem using neural networks trained with synthetic, ground-truth data. In this work we approach, for the first time, the intensity reconstruction problem from a self-supervised learning perspective. Our method, which leverages the knowledge of the inner workings of event cameras, combines estimated optical flow and the event-based photometric constancy to train neural networks without the need for any ground-truth or synthetic data. Results across multiple datasets show that the performance of the proposed self-supervised approach is in line with the state-of-the-art. Additionally, we propose a novel, lightweight neural network for optical flow estimation that achieves high speed inference with only a minor drop in performance.

D. B. de Jong, F. Paredes-Vallés, G. C. H. E. de Croon

End-to-end trained convolutional neural networks have led to a breakthrough in optical flow estimation. The most recent advances focus on improving the optical flow estimation by improving the architecture and setting a new benchmark on the publicly available MPI-Sintel dataset. Instead, in this article, we investigate how deep neural networks estimate optical flow. A better understanding of how these networks function is important for (i) assessing their generalization capabilities to unseen inputs, and (ii) suggesting changes to improve their performance. For our investigation, we focus on FlowNetS, as it is the prototype of an encoder-decoder neural network for optical flow estimation. Furthermore, we use a filter identification method that has played a major role in uncovering the motion filters present in animal brains in neuropsychological research. The method shows that the filters in the deepest layer of FlowNetS are sensitive to a variety of motion patterns. Not only do we find translation filters, as demonstrated in animal brains, but thanks to the easier measurements in artificial neural networks, we even unveil dilation, rotation, and occlusion filters. Furthermore, we find similarities in the refinement part of the network and the perceptual filling-in process which occurs in the mammal primary visual cortex.

Kirk Y. W. Scheper, Guido C. H. E. de Croon

Automatic optimization of robotic behavior has been the long-standing goal of Evolutionary Robotics. Allowing the problem at hand to be solved by automation often leads to novel approaches and new insights. A common problem encountered with this approach is that when this optimization occurs in a simulated environment, the optimized policies are subject to the reality gap when implemented in the real world. This often results in sub-optimal behavior, if it works at all. This paper investigates the automatic optimization of neurocontrollers to perform quick but safe landing maneuvers for a quadrotor micro air vehicle using the divergence of the optical flow field of a downward looking camera. The optimized policies showed that a piece-wise linear control scheme is more effective than the simple linear scheme commonly used, something not yet considered by human designers. Additionally, we show the utility in using abstraction on the input and output of the controller as a tool to improve the robustness of the optimized policies to the reality gap by testing our policies optimized in simulation on real world vehicles. We tested the neurocontrollers using two different methods to generate and process the visual input, one using a conventional CMOS camera and one a dynamic vision sensor, both of which perform significantly differently than the simulated sensor. The use of the abstracted input resulted in near seamless transfer to the real world with the controllers showing high robustness to a clear reality gap.

Bardienus P. Duisterhof, Srivatsan Krishnan, Jonathan J. Cruz et al.

We present fully autonomous source seeking onboard a highly constrained nano quadcopter, by contributing application-specific system and observation feature design to enable inference of a deep-RL policy onboard a nano quadcopter. Our deep-RL algorithm finds a high-performance solution to a challenging problem, even in presence of high noise levels and generalizes across real and simulation environments with different obstacle configurations. We verify our approach with simulation and in-field testing on a Bitcraze CrazyFlie using only the cheap and ubiquitous Cortex-M4 microcontroller unit. The results show that by end-to-end application-specific system design, our contribution consumes almost three times less additional power, as compared to competing learning-based navigation approach onboard a nano quadcopter. Thanks to our observation space, which we carefully design within the resource constraints, our solution achieves a 94% success rate in cluttered and randomized test environments, as compared to the previously achieved 80%. We also compare our strategy to a simple finite state machine (FSM), geared towards efficient exploration, and demonstrate that our policy is more robust and resilient at obstacle avoidance as well as up to 70% more efficient in source seeking. To this end, we contribute a cheap and lightweight end-to-end tiny robot learning (tinyRL) solution, running onboard a nano quadcopter, that proves to be robust and efficient in a challenging task using limited sensory input.

Shuo Li, Erik van der Horst, Philipp Duernay et al.

Drone racing is becoming a popular e-sport all over the world, and beating the best human drone race pilots has quickly become a new major challenge for artificial intelligence and robotics. In this paper, we propose a strategy for autonomous drone racing which is computationally more efficient than navigation methods like visual inertial odometry and simultaneous localization and mapping. This fast light-weight vision-based navigation algorithm estimates the position of the drone by fusing race gate detections with model dynamics predictions. Theoretical analysis and simulation results show the clear advantage compared to Kalman filtering when dealing with the relatively low frequency visual updates and occasional large outliers that occur in fast drone racing. Flight tests are performed on a tiny racing quadrotor named "Trashcan", which was equipped with a Jevois smart-camera for a total of 72g. The test track consists of 3 laps around a 4-gate racing track. The gates spaced 4 meters apart and can be displaced from their supposed position. An average speed of 2m/s is achieved while the maximum speed is 2.6m/s. To the best of our knowledge, this flying platform is the smallest autonomous racing drone in the world and is 6 times lighter than the existing lightest autonomous racing drone setup (420g), while still being one of the fastest autonomous racing drones in the world.

Tom van Dijk, Guido C. H. E. de Croon

Deep neural networks have lead to a breakthrough in depth estimation from single images. Recent work often focuses on the accuracy of the depth map, where an evaluation on a publicly available test set such as the KITTI vision benchmark is often the main result of the article. While such an evaluation shows how well neural networks can estimate depth, it does not show how they do this. To the best of our knowledge, no work currently exists that analyzes what these networks have learned. In this work we take the MonoDepth network by Godard et al. and investigate what visual cues it exploits for depth estimation. We find that the network ignores the apparent size of known obstacles in favor of their vertical position in the image. Using the vertical position requires the camera pose to be known; however we find that MonoDepth only partially corrects for changes in camera pitch and roll and that these influence the estimated depth towards obstacles. We further show that MonoDepth's use of the vertical image position allows it to estimate the distance towards arbitrary obstacles, even those not appearing in the training set, but that it requires a strong edge at the ground contact point of the object to do so. In future work we will investigate whether these observations also apply to other neural networks for monocular depth estimation.

S. Li, M. M. O. I. Ozo, C. De Wagter et al.

Drone racing is becoming a popular sport where human pilots have to control their drones to fly at high speed through complex environments and pass a number of gates in a pre-defined sequence. In this paper, we develop an autonomous system for drones to race fully autonomously using only onboard resources. Instead of commonly used visual navigation methods, such as simultaneous localization and mapping and visual inertial odometry, which are computationally expensive for micro aerial vehicles (MAVs), we developed the highly efficient snake gate detection algorithm for visual navigation, which can detect the gate at 20HZ on a Parrot Bebop drone. Then, with the gate detection result, we developed a robust pose estimation algorithm which has better tolerance to detection noise than a state-of-the-art perspective-n-point method. During the race, sometimes the gates are not in the drone's field of view. For this case, a state prediction-based feed-forward control strategy is developed to steer the drone to fly to the next gate. Experiments show that the drone can fly a half-circle with 1.5m radius within 2 seconds with only 30cm error at the end of the circle without any position feedback. Finally, the whole system is tested in a complex environment (a showroom in the faculty of Aerospace Engineering, TU Delft). The result shows that the drone can complete the track of 15 gates with a speed of 1.5m/s which is faster than the speeds exhibited at the 2016 and 2017 IROS autonomous drone races.

Kimberly McGuire, Guido de Croon, Karl Tuyls

This paper presents a literature survey and a comparative study of Bug Algorithms, with the goal of investigating their potential for robotic navigation. At first sight, these methods seem to provide an efficient navigation paradigm, ideal for implementations on tiny robots with limited resources. Closer inspection, however, shows that many of these Bug Algorithms assume perfect global position estimate of the robot which in GPS-denied environments implies considerable expenses of computation and memory -- relying on accurate Simultaneous Localization And Mapping (SLAM) or Visual Odometry (VO) methods. We compare a selection of Bug Algorithms in a simulated robot and environment where they endure different types noise and failure-cases of their on-board sensors. From the simulation results, we conclude that the implemented Bug Algorithms' performances are sensitive to many types of sensor-noise, which was most noticeable for odometry-drift. This raises the question if Bug Algorithms are suitable for real-world, on-board, robotic navigation as is. Variations that use multiple sensors to keep track of their progress towards the goal, were more adept in completing their task in the presence of sensor-failures. This shows that Bug Algorithms must spread their risk, by relying on the readings of multiple sensors, to be suitable for real-world deployment.

Guido de Croon, Christophe De Wagter

A novel approach is proposed for monocular obstacle detection, which relies on self-supervised learning to discriminate everything above the horizon line from everything below. Obstacles on the path of a robot that keeps moving at the same height, will appear both above and under the horizon line. This implies that classifying obstacle pixels will be inherently uncertain. Hence, in the proposed approach the classifier's uncertainty is used for obstacle detection. The (preliminary) results show that this approach can indeed work in different environments. On the well-known KITTI data set, the self-supervised learning scheme clearly segments the road and sky, while application to a flying data set leads to the segmentation of the flight arena's floor.

Steven van der Helm, Kimberly N. McGuire, Mario Coppola et al.

We present a range-based solution for indoor relative localization by Micro Air Vehicles (MAVs), achieving sufficient accuracy for leader-follower flight. Moving forward from previous work, we removed the dependency on a common heading measurement by the MAVs, making the relative localization accuracy independent of magnetometer readings. We found that this restricts the relative maneuvers that guarantee observability, and also that higher accuracy range measurements are required to rectify the missing heading information, yet both disadvantages can be tackled. Our implementation uses Ultra Wide Band, for both range measurements between MAVs and sharing their velocities, accelerations, yaw rates, and height with each other. We used this on real MAVs and performed leader-follower flight in an indoor environment. The follower MAVs could follow the leader MAV in close proximity for the entire durations of the flights. The followers were autonomous and used only on-board sensors to track and follow the leader.

Mario Coppola, Jian Guo, Eberhard K. A. Gill et al.

In this work, we explore emergent behaviors by swarms of anonymous, homogeneous, non-communicating, reactive robots that do not know their global position and have limited relative sensing. We introduce a novel method that enables such severely limited robots to autonomously arrange in a desired pattern and maintain it. The method includes an automatic proof procedure to check whether a given pattern will be achieved by the swarm from any initial configuration. An attractive feature of this proof procedure is that it is local in nature, avoiding as much as possible the computational explosion that can be expected with increasing robots, states, and action possibilities. Our approach is based on extracting the local states that constitute a global goal (in this case, a pattern). We then formally show that these local states can only coexist when the global desired pattern is achieved and that, until this occurs, there is always a sequence of actions that will lead from the current pattern to the desired pattern. Furthermore, we show that the agents will never perform actions that could a) lead to intra-swarm collisions or b) cause the swarm to separate. After an analysis of the performance of pattern formation in the discrete domain, we also test the system in continuous time and space simulations and reproduce the results using asynchronous agents operating in unbounded space. The agents successfully form the desired patterns while avoiding collisions and separation.

Diogo Martins, Kevin van Hecke, Guido de Croon

We study how autonomous robots can learn by themselves to improve their depth estimation capability. In particular, we investigate a self-supervised learning setup in which stereo vision depth estimates serve as targets for a convolutional neural network (CNN) that transforms a single still image to a dense depth map. After training, the stereo and mono estimates are fused with a novel fusion method that preserves high confidence stereo estimates, while leveraging the CNN estimates in the low-confidence regions. The main contribution of the article is that it is shown that the fused estimates lead to a higher performance than the stereo vision estimates alone. Experiments are performed on the KITTI dataset, and on board of a Parrot SLAMDunk, showing that even rather limited CNNs can help provide stereo vision equipped robots with more reliable depth maps for autonomous navigation.

G. C. H. E. de Croon

Self-supervised learning (SSL) is a reliable learning mechanism in which a robot enhances its perceptual capabilities. Typically, in SSL a trusted, primary sensor cue provides supervised training data to a secondary sensor cue. In this article, a theoretical analysis is performed on the fusion of the primary and secondary cue in a minimal model of SSL. A proof is provided that determines the specific conditions under which it is favorable to perform fusion. In short, it is favorable when (i) the prior on the target value is strong or (ii) the secondary cue is sufficiently accurate. The theoretical findings are validated with computational experiments. Subsequently, a real-world case study is performed to investigate if fusion in SSL is also beneficial when assumptions of the minimal model are not met. In particular, a flying robot learns to map pressure measurements to sonar height measurements and then fuses the two, resulting in better height estimation. Fusion is also beneficial in the opposite case, when pressure is the primary cue. The analysis and results are encouraging to study SSL fusion also for other robots and sensors.

Ewoud J. J. Smeur, Guido C. H. E. de Croon, Qiping Chu

Micro Aerial Vehicles (MAVs) are limited in their operation outdoors near obstacles by their ability to withstand wind gusts. Currently widespread position control methods such as Proportional Integral Derivative control do not perform well under the influence of gusts. Incremental Nonlinear Dynamic Inversion (INDI) is a sensor-based control technique that can control nonlinear systems subject to disturbances. It was developed for the attitude control of manned aircraft or MAVs. In this paper we generalize this method to the outer loop control of MAVs under severe gust loads. Significant improvements over a traditional Proportional Integral Derivative (PID) controller are demonstrated in an experiment where the quadrotor flies in and out of a windtunnel exhaust at 10 m/s. The control method does not rely on frequent position updates, as is demonstrated in an outside experiment using a standard GPS module. Finally, we investigate the effect of using a linearization to calculate thrust vector increments, compared to a nonlinear calculation. The method requires little modeling and is computationally efficient.

Matěj Karásek, Mustafa Percin, Torbjørn Cunis et al.

Flow visualisations are essential to better understand the unsteady aerodynamics of flapping wing flight. The issues inherent to animal experiments, such as poor controllability and unnatural flapping when tethered, can be avoided by using robotic flyers. Such an approach holds a promise for a more systematic and repeatable methodology for flow visualisation, through a better controlled flight. Such experiments require high precision position control, however, and until now this was not possible due to the challenging flight dynamics and payload restrictions of flapping wing Micro Air Vehicles (FWMAV). Here, we present a new FWMAV-specific control approach that, by employing an external motion tracking system, achieved autonomous wind tunnel flight with a maximum root-mean-square position error of 28 mm at low speeds (0.8 - 1.2 m/s) and 75 mm at high speeds (2 - 2.4 m/s). This allowed the first free-flight flow visualisation experiments to be conducted with an FWMAV. Time-resolved stereoscopic Particle Image Velocimetry (PIV) was used to reconstruct the 3D flow patterns of the FWMAV wake. A good qualitative match was found in comparison to a tethered configuration at similar conditions, suggesting that the obtained free-flight measurements are reliable and meaningful.

V. Strobel, R. Meertens, G. C. H. E. de Croon

Indoor localization for autonomous micro aerial vehicles (MAVs) requires specific localization techniques, since the Global Positioning System (GPS) is usually not available. We present an efficient onboard computer vision approach that estimates 2D positions of an MAV in real-time. This global localization system does not suffer from error accumulation over time and uses a $k$-Nearest Neighbors ($k$-NN) algorithm to predict positions based on textons---small characteristic image patches that capture the texture of an environment. A particle filter aggregates the estimates and resolves positional ambiguities. To predict the performance of the approach in a given setting, we developed an evaluation technique that compares environments and identifies critical areas within them. We conducted flight tests to demonstrate the applicability of our approach. The algorithm has a localization accuracy of approximately 0.6 m on a 5 m$\times$5 m area at a runtime of 32 ms on board of an MAV. Based on random sampling, its computational effort is scalable to different platforms, trading off speed and accuracy.

Mario Coppola, Kimberly McGuire, Kirk Y. W. Scheper et al.

Micro Air Vehicles (MAVs) will unlock their true potential once they can operate in groups. To this end, it is essential for them to estimate on-board the relative location of their neighbors. The challenge lies in limiting the mass and processing burden needed to enable this. We developed a relative localization method that only requires the MAVs to communicate via their wireless transceiver. Communication allows the exchange of on-board states (velocity, height, and orientation), while the signal-strength provides range data. These quantities are fused to provide a full relative location estimate. We used our method to tackle the problem of collision avoidance in tight areas. The system was tested with a team of AR.Drones flying in a 4mx4m area and with miniature drones of ~50g in a 2mx2m area. The MAVs were able to track their relative positions and fly several minutes without collisions. Our implementation used Bluetooth to communicate between the drones. This featured significant noise and disturbances in signal-strength, which worsened as more drones were added. Simulation analysis suggests that results can improve with a more suitable transceiver module.

H. W. Ho, G. C. H. E. de Croon, E. van Kampen et al.

Bio-inspired methods can provide efficient solutions to perform autonomous landing for Micro Air Vehicles (MAVs). Flying insects such as honeybees perform vertical landings by keeping flow divergence constant. This leads to an exponential decay of both height and vertical velocity, and allows for smooth and safe landings. However, the presence of noise and delay in obtaining flow divergence estimates will cause instability of the landing when the control gains are not adapted to the height. In this paper, we propose a strategy that deals with this fundamental problem of optical flow control. The key to the strategy lies in the use of a recent theory that allows the MAV to see distance by means of its control instability. At the start of a landing, the MAV detects the height by means of an oscillating movement and sets the control gains accordingly. Then, during descent, the gains are reduced exponentially, with mechanisms in place to reduce or increase the gains if the actual trajectory deviates too much from an ideal constant divergence landing. Real-world experiments demonstrate stable landings of the MAV in both indoor and windy outdoor environments.