Guido C. H. E. 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.

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.

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.

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.

Robin Ferede, Till Blaha, Erin Lucassen et al.

In high-speed quadcopter racing, finding a single controller that works well across different platforms remains challenging. This work presents the first neural network controller for drone racing that generalizes across physically distinct quadcopters. We demonstrate that a single network, trained with domain randomization, can robustly control various types of quadcopters. The network relies solely on the current state to directly compute motor commands. The effectiveness of this generalized controller is validated through real-world tests on two substantially different crafts (3-inch and 5-inch race quadcopters). We further compare the performance of this generalized controller with controllers specifically trained for the 3-inch and 5-inch drone, using their identified model parameters with varying levels of domain randomization (0%, 10%, 20%, 30%). While the generalized controller shows slightly slower speeds compared to the fine-tuned models, it excels in adaptability across different platforms. Our results show that no randomization fails sim-to-real transfer while increasing randomization improves robustness but reduces speed. Despite this trade-off, our findings highlight the potential of domain randomization for generalizing controllers, paving the way for universal AI controllers that can adapt to any platform.

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.

Stavrow A. Bahnam, Christophe De Wagter, Guido C. H. E. de Croon

Ego-motion estimation is vital for drones when flying in GPS-denied environments. Vision-based methods struggle when flight speed increases and close-by objects lead to difficult visual conditions with considerable motion blur and large occlusions. To tackle this, vision is typically complemented by state estimation filters that combine a drone model with inertial measurements. However, these drone models are currently learned in a supervised manner with ground-truth data from external motion capture systems, limiting scalability to different environments and drones. In this work, we propose a self-supervised learning scheme to train a neural-network-based drone model using only onboard monocular video and flight controller data (IMU and motor feedback). We achieve this by first training a self-supervised relative pose estimation model, which then serves as a teacher for the drone model. To allow this to work at high speed close to obstacles, we propose an improved occlusion handling method for training self-supervised pose estimation models. Due to this method, the root mean squared error of resulting odometry estimates is reduced by an average of 15%. Moreover, the student neural drone model can be successfully obtained from the onboard data. It even becomes more accurate at higher speeds compared to its teacher, the self-supervised vision-based model. We demonstrate the value of the neural drone model by integrating it into a traditional filter-based VIO system (ROVIO), resulting in superior odometry accuracy on aggressive 3D racing trajectories near obstacles. Self-supervised learning of ego-motion estimation represents a significant step toward bridging the gap between flying in controlled, expensive lab environments and real-world drone applications. The fusion of vision and drone models will enable higher-speed flight and improve state estimation, on any drone in any environment.

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.

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.

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.

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.

Shuo Li, Ekin Ozturk, Christophe De Wagter et al.

Optimal control holds great potential to improve a variety of robotic applications. The application of optimal control on-board limited platforms has been severely hindered by the large computational requirements of current state of the art implementations. In this work, we make use of a deep neural network to directly map the robot states to control actions. The network is trained offline to imitate the optimal control computed by a time consuming direct nonlinear method. A mixture of time optimality and power optimality is considered with a continuation parameter used to select the predominance of each objective. We apply our networks (termed G\&CNets) to aggressive quadrotor control, first in simulation and then in the real world. We give insight into the factors that influence the `reality gap' between the quadrotor model used by the offline optimal control method and the real quadrotor. Furthermore, we explain how we set up the model and the control structure on-board of the real quadrotor to successfully close this gap and perform time-optimal maneuvers in the real world. Finally, G\&CNet's performance is compared to state-of-the-art differential-flatness-based optimal control methods. We show, in the experiments, that G\&CNets lead to significantly faster trajectory execution due to, in part, the less restrictive nature of the allowed state-to-input mappings.

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.

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.

Bas J. Pijnacker Hordijk, Kirk Y. W. Scheper, Guido C. H. E. de Croon

Small flying robots can perform landing maneuvers using bio-inspired optical flow by maintaining a constant divergence. However, optical flow is typically estimated from frame sequences recorded by standard miniature cameras. This requires processing full images on-board, limiting the update rate of divergence measurements, and thus the speed of the control loop and the robot. Event-based cameras overcome these limitations by only measuring pixel-level brightness changes at microsecond temporal accuracy, hence providing an efficient mechanism for optical flow estimation. This paper presents, to the best of our knowledge, the first work integrating event-based optical flow estimation into the control loop of a flying robot. We extend an existing 'local plane fitting' algorithm to obtain an improved and more computationally efficient optical flow estimation method, valid for a wide range of optical flow velocities. This method is validated for real event sequences. In addition, a method for estimating the divergence from event-based optical flow is introduced, which accounts for the aperture problem. The developed algorithms are implemented in a constant divergence landing controller on-board of a quadrotor. Experiments show that, using event-based optical flow, accurate divergence estimates can be obtained over a wide range of speeds. This enables the quadrotor to perform very fast landing maneuvers.

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.

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.

Kirk Y. W. Scheper, Sjoerd Tijmons, Coen C. de Visser et al.

Evolutionary Robotics allows robots with limited sensors and processing to tackle complex tasks by means of sensory-motor coordination. In this paper we show the first application of the Behaviour Tree framework to a real robotic platform using the Evolutionary Robotics methodology. This framework is used to improve the intelligibility of the emergent robotic behaviour as compared to the traditional Neural Network formulation. As a result, the behaviour is easier to comprehend and manually adapt when crossing the reality gap from simulation to reality. This functionality is shown by performing real-world flight tests with the 20-gram DelFly Explorer flapping wing Micro Air Vehicle equipped with a 4-gram onboard stereo vision system. The experiments show that the DelFly can fully autonomously search for and fly through a window with only its onboard sensors and processing. The success rate of the optimised behaviour in simulation is 88% and the corresponding real-world performance is 54% after user adaptation. Although this leaves room for improvement, it is higher than the 46% success rate from a tuned user-defined controller.