Erdal Kayacan

Hürkan Şahin, Van Huyen Dang, Erdi Sayar et al.

Reinforcement learning (RL) often struggles in real-world tasks with high-dimensional state spaces and long horizons, where sparse or fixed rewards severely slow down exploration and cause agents to get trapped in local optima. This paper presents a fuzzy logic based reward shaping method that integrates human intuition into RL reward design. By encoding expert knowledge into adaptive and interpreable terms, fuzzy rules promote stable learning and reduce sensitivity to hyperparameters. The proposed method leverages these properties to adapt reward contributions based on the agent state, enabling smoother transitions between fast motion and precise control in challenging navigation tasks. Extensive simulation results on autonomous drone racing benchmarks show stable learning behavior and consistent task performance across scenarios of increasing difficulty. The proposed method achieves faster convergence and reduced performance variability across training seeds in more challenging environments, with success rates improving by up to approximately 5 percent compared to non fuzzy reward formulations.

Abdelhakim Amer, Aske Alstrup, Frederik Rasmussen et al.

High-resolution seafloor mapping necessitates stable and precise positioning for underwater robots. This paper introduces a novel mathematical model for SeaVis remotely operated towed vehicles (ROTVs) and develops a gain-scheduled linear-quadratic regulator (LQR) for robust depth and attitude control. We validate the approach in a high-fidelity simulation, benchmarking the LQR against a conventional PID controller over a challenging seabed profile. The presented results demonstrate the LQR's superior performance, with significantly enhanced robustness to disturbances, greater control efficiency, and substantially reduced flap actuation. The gain scheduling also confirms the controller's effectiveness across the full operational velocity range. The complete simulation environment and controller are open-sourced.

Hürkan Şahin, Huy Xuan Pham, Van Huyen Dang et al.

Autonomous navigation in GPS-denied and visually degraded environments remains challenging for unmanned aerial vehicles (UAVs). To this end, we investigate the use of a monocular thermal camera as a standalone sensor on a UAV platform for real-time depth estimation and simultaneous localization and mapping (SLAM). To extract depth information from thermal images, we propose a novel pipeline employing a lightweight supervised network with recurrent blocks (RBs) integrated to capture temporal dependencies, enabling more robust predictions. The network combines lightweight convolutional backbones with a thermal refinement network (T-RefNet) to refine raw thermal inputs and enhance feature visibility. The refined thermal images and predicted depth maps are integrated into ORB-SLAM3, enabling thermal-only localization. Unlike previous methods, the network is trained on a custom non-radiometric dataset, obviating the need for high-cost radiometric thermal cameras. Experimental results on datasets and UAV flights demonstrate competitive depth accuracy and robust SLAM performance under low-light conditions. On the radiometric VIVID++ (indoor-dark) dataset, our method achieves an absolute relative error of approximately 0.06, compared to baselines exceeding 0.11. In our non-radiometric indoor set, baseline errors remain above 0.24, whereas our approach remains below 0.10. Thermal-only ORB-SLAM3 maintains a mean trajectory error under 0.4 m.

Olaya Álvarez-Tuñón, Yury Brodskiy, Erdal Kayacan

This paper overviews different pose representations and metric functions in visual odometry (VO) networks. The performance of VO networks heavily relies on how their architecture encodes the information. The choice of pose representation and loss function significantly impacts network convergence and generalization. We investigate these factors in the VO network DeepVO by implementing loss functions based on Euler, quaternion, and chordal distance and analyzing their influence on performance. The results of this study provide insights into how loss functions affect the designing of efficient and accurate VO networks for camera motion estimation. The experiments illustrate that a distance that complies with the mathematical requirements of a metric, such as the chordal distance, provides better generalization and faster convergence. The code for the experiments can be found at https://github.com/remaro-network/Loss_VO_right

Olaya Alvarez-Tunon, Yury Brodskiy, Erdal Kayacan

With the rise of deep learning, there is a fundamental change in visual SLAM algorithms toward developing different modules trained as end-to-end pipelines. However, regardless of the implementation domain, visual SLAM's performance is subject to diverse environmental challenges, such as dynamic elements in outdoor environments, harsh imaging conditions in underwater environments, or blurriness in high-speed setups. These environmental challenges need to be identified to study the real-world viability of SLAM implementations. Motivated by the aforementioned challenges, this paper surveys the current state of visual SLAM algorithms according to the two main frameworks: geometry-based and learning-based SLAM. First, we introduce a general formulation of the SLAM pipeline that includes most of the implementations in the literature. Second, those implementations are classified and surveyed for geometry and learning-based SLAM. After that, environment-specific challenges are formulated to enable experimental evaluation of the resilience of different visual SLAM classes to varying imaging conditions. We address two significant issues in surveying visual SLAM, providing (1) a consistent classification of visual SLAM pipelines and (2) a robust evaluation of their performance under different deployment conditions. Finally, we give our take on future opportunities for visual SLAM implementations.

Zhongzheng Qiao, Xuan Huy Pham, Savitha Ramasamy et al.

In autonomous and mobile robotics, a principal challenge is resilient real-time environmental perception, particularly in situations characterized by unknown and dynamic elements, as exemplified in the context of autonomous drone racing. This study introduces a perception technique for detecting drone racing gates under illumination variations, which is common during high-speed drone flights. The proposed technique relies upon a lightweight neural network backbone augmented with capabilities for continual learning. The envisaged approach amalgamates predictions of the gates' positional coordinates, distance, and orientation, encapsulating them into a cohesive pose tuple. A comprehensive number of tests serve to underscore the efficacy of this approach in confronting diverse and challenging scenarios, specifically those involving variable lighting conditions. The proposed methodology exhibits notable robustness in the face of illumination variations, thereby substantiating its effectiveness.

Şebnem Sarıözkan, Hürkan Şahin, Olaya Álvarez-Tuñón et al.

Conventional visual simultaneous localization and mapping (SLAM) algorithms often fail under rapid motion, low illumination, or abrupt lighting transitions due to motion blur and limited dynamic range. Event cameras mitigate these issues with high temporal resolution and high dynamic range (HDR), but their sparse, asynchronous outputs complicate feature extraction and integration with other sensors; e.g. inertial measurement units (IMUs) and standard cameras. We present Edged USLAM, a hybrid visual-inertial system that extends Ultimate SLAM (USLAM) with an edge-aware front-end and a lightweight depth module. The frontend enhances event frames for robust feature tracking and nonlinear motion compensation, while the depth module provides coarse, region-of-interest (ROI)-based scene depth to improve motion compensation and scale consistency. Evaluations across public benchmarks and real-world unmanned air vehicle (UAV) flights demonstrate that performance varies significantly by scenario. For instance, event-only methods like point-line event-based visual-inertial odometry (PL-EVIO) or learning-based pipelines such as deep event-based visual odometry (DEVO) excel in highly aggressive or extreme HDR conditions. In contrast, Edged USLAM provides superior stability and minimal drift in slow or structured trajectories, ensuring consistently accurate localization on real flights under challenging illumination. These findings highlight the complementary strengths of event-only, learning-based, and hybrid approaches, while positioning Edged USLAM as a robust solution for diverse aerial navigation tasks.

Jonas le Fevre Sejersen, Toyotaro Suzumura, Erdal Kayacan

This paper presents a novel approach to multi-robot collision avoidance that integrates global path planning with local navigation strategies, utilizing attentive graph neural networks to manage dynamic interactions among agents. We introduce a local navigation model that leverages pre-planned global paths, allowing robots to adhere to optimal routes while dynamically adjusting to environmental changes. The models robustness is enhanced through the introduction of noise during training, resulting in superior performance in complex, dynamic environments. Our approach is evaluated against established baselines, including NH-ORCA, DRL-NAV, and GA3C-CADRL, across various structurally diverse simulated scenarios. The results demonstrate that our model achieves consistently higher success rates, lower collision rates, and more efficient navigation, particularly in challenging scenarios where baseline models struggle. This work offers an advancement in multi-robot navigation, with implications for robust performance in complex, dynamic environments with varying degrees of complexity, such as those encountered in logistics, where adaptability is essential for accommodating unforeseen obstacles and unpredictable changes.

Rui Pimentel de Figueiredo, Jonas le Fevre Sejersen, Jakob Grimm Hansen et al.

In this work we propose a holistic framework for autonomous aerial inspection tasks, using semantically-aware, yet, computationally efficient planning and mapping algorithms. The system leverages state-of-the-art receding horizon exploration techniques for next-best-view (NBV) planning with geometric and semantic segmentation information provided by state-of-the-art deep convolutional neural networks (DCNNs), with the goal of enriching environment representations. The contributions of this article are threefold, first we propose an efficient sensor observation model, and a reward function that encodes the expected information gains from the observations taken from specific view points. Second, we extend the reward function to incorporate not only geometric but also semantic probabilistic information, provided by a DCNN for semantic segmentation that operates in real-time. The incorporation of semantic information in the environment representation allows biasing exploration towards specific objects, while ignoring task-irrelevant ones during planning. Finally, we employ our approaches in an autonomous drone shipyard inspection task. A set of simulations in realistic scenarios demonstrate the efficacy and efficiency of the proposed framework when compared with the state-of-the-art.

Jonas le Fevre Sejersen, Rui Pimentel de Figueiredo, Erdal Kayacan

In the maritime sector, safe vessel navigation is of great importance, particularly in congested harbors and waterways. The focus of this work is to estimate the distance between an object of interest and potential obstacles using a companion UAV. The proposed approach fuses GPS data with long-range aerial images. First, we employ semantic segmentation DNN for discriminating the vessel of interest, water, and potential solid objects using raw image data. The network is trained with both real and images generated and automatically labeled from a realistic AirSim simulation environment. Then, the distances between the extracted vessel and non-water obstacle blobs are computed using a novel GSD estimation algorithm. To the best of our knowledge, this work is the first attempt to detect and estimate distances to unknown objects from long-range visual data captured with conventional RGB cameras and auxiliary absolute positioning systems (e.g. GPS). The simulation results illustrate the accuracy and efficacy of the proposed method for visually aided navigation of vessels assisted by UAV.

Rui Pimentel de Figueiredo, Jakob Grimm Hansen, Jonas Le Fevre et al.

In this work we showcase the design and assessment of the performance of a multi-camera UAV, when coupled with state-of-the-art planning and mapping algorithms for autonomous navigation. The system leverages state-of-the-art receding horizon exploration techniques for Next-Best-View (NBV) planning with 3D and semantic information, provided by a reconfigurable multi stereo camera system. We employ our approaches in an autonomous drone-based inspection task and evaluate them in an autonomous exploration and mapping scenario. We discuss the advantages and limitations of using multi stereo camera flying systems, and the trade-off between number of cameras and mapping performance.

Erkan Kayacan, Erdal Kayacan, Herman Ramon et al.

This paper addresses the trajectory tracking problem of an autonomous tractor-trailer system by using a fast distributed nonlinear model predictive control algorithm in combination with nonlinear moving horizon estimation for the state and parameter estimation in which constraints on the inputs and the states can be incorporated. The proposed control algorithm is capable of driving the tractor-trailer system to any desired trajectory ensuring high control accuracy and robustness against environmental disturbances.

Erkan Kayacan, Erdal Kayacan, Herman Ramon et al.

As a model is only an abstraction of the real system, unmodeled dynamics, parameter variations, and disturbances can result in poor performance of a conventional controller based on this model. In such cases, a conventional controller cannot remain well tuned. This paper presents the control of a spherical rolling robot by using an adaptive neuro-fuzzy controller in combination with a sliding-mode control (SMC)-theory-based learning algorithm. The proposed control structure consists of a neuro-fuzzy network and a conventional controller which is used to guarantee the asymptotic stability of the system in a compact space. The parameter updating rules of the neuro-fuzzy system using SMC theory are derived, and the stability of the learning is proven using a Lyapunov function. The simulation results show that the control scheme with the proposed SMC-theory-based learning algorithm is able to not only eliminate the steady-state error but also improve the transient response performance of the spherical rolling robot without knowing its dynamic equations.

Erkan Kayacan, Erdal Kayacan, Herman Ramon et al.

More efficient agricultural machinery is needed as agricultural areas become more limited and energy and labor costs increase. To increase their efficiency, trajectory tracking problem of an autonomous tractor, as an agricultural production machine, has been investigated in this study. As a widely used model-based approach, model predictive control is preferred in this paper to control the yaw dynamics of the tractor which can deal with the constraints on the states and the actuators in a system. The yaw dynamics is identified by using nonlinear least squares frequency domain system identification. The speed is controlled by a proportional-integral-derivative controller and a kinematic trajectory controller is used to calculate the desired speed and the desired yaw rate signals for the subsystems in order to minimize the tracking errors in both the longitudinal and transversal directions. The experimental results show the accuracy and the efficiency of the proposed control scheme in which the euclidean error is below $40$ cm for time-based straight line trajectories and $60$ cm for time-based curved line trajectories, respectively.

Ilker Bozcan, Erdal Kayacan

The detection of contextual anomalies is a challenging task for surveillance since an observation can be considered anomalous or normal in a specific environmental context. An unmanned aerial vehicle (UAV) can utilize its aerial monitoring capability and employ multiple sensors to gather contextual information about the environment and perform contextual anomaly detection. In this work, we introduce a deep neural network-based method (CADNet) to find point anomalies (i.e., single instance anomalous data) and contextual anomalies (i.e., context-specific abnormality) in an environment using a UAV. The method is based on a variational autoencoder (VAE) with a context sub-network. The context sub-network extracts contextual information regarding the environment using GPS and time data, then feeds it to the VAE to predict anomalies conditioned on the context. To the best of our knowledge, our method is the first contextual anomaly detection method for UAV-assisted aerial surveillance. We evaluate our method on the AU-AIR dataset in a traffic surveillance scenario. Quantitative comparisons against several baselines demonstrate the superiority of our approach in the anomaly detection tasks. The codes and data will be available at https://bozcani.github.io/cadnet.

Erdal Kayacan, Erkan Kayacan, Herman Ramon et al.

Provision of some autonomous functions to an agricultural vehicle would lighten the job of the operator but in doing so, the accuracy should not be lost to still obtain an optimal yield. Autonomous navigation of an agricultural vehicle involves the control of different dynamic subsystems, such as the yaw angle dynamics and the longitudinal speed dynamics. In this study, a proportional-integral-derivative controller is used to control the longitudinal velocity of the tractor. For the control of the yaw angle dynamics, a proportional-derivative controller works in parallel with a type-2 fuzzy neural network. In such an arrangement, the former ensures the stability of the related subsystem, while the latter learns the system dynamics and becomes the leading controller. In this way, instead of modeling the interactions between the subsystems prior to the design of model-based control, we develop a control algorithm which learns the interactions online from the measured feedback error. In addition to the control of the stated subsystems, a kinematic controller is needed to correct the errors in both the x- and the y- axis for the trajectory tracking problem of the tractor. To demonstrate the real-time abilities of the proposed control scheme, an autonomous tractor is equipped with the use of reasonably priced sensors and actuators. Experimental results show the efficacy and efficiency of the proposed learning algorithm.

Erkan Kayacan, Erdal Kayacan, Herman Ramon et al.

This paper addresses the trajectory tracking problem of an autonomous tractor-trailer system by using a decentralized control approach. A fully decentralized model predictive controller is designed in which interactions between subsystems are neglected and assumed to be perturbations to each other. In order to have a robust design, a tube-based approach is proposed to handle the differences between the nominal model and real system. Nonlinear moving horizon estimation is used for the state and parameter estimation after each new measurement, and the estimated values are fed to robust tube-based decentralized nonlinear model predictive controller. The proposed control scheme is capable of driving the tractor-trailer system to any desired trajectory ensuring high control accuracy and robustness against neglected subsystem interactions and environmental disturbances. The experimental results show an accurate trajectory tracking performance on a bumpy grass field.

Erkan Kayacan, Erdal Kayacan, Mojtaba Ahmadieh Khanesar

In order to achieve faster and more robust convergence (especially under noisy working environments), a sliding mode theory-based learning algorithm has been proposed to tune both the premise and consequent parts of type-2 fuzzy neural networks in this paper. Differently from recent studies, where sliding mode control theory-based rules are proposed for only the consequent part of the network, the developed algorithm applies fully sliding mode parameter update rules for both the premise and consequent parts of the type-2 fuzzy neural networks. In addition, the responsible parameter for sharing the contributions of the lower and upper parts of the type-2 fuzzy membership functions is also tuned. Moreover, the learning rate of the network is updated during the online training. The stability of the proposed learning algorithm has been proved by using an appropriate Lyapunov function. Several comparisons have been realized and shown that the proposed algorithm has faster convergence speed than the existing methods such as gradient-based and swarm intelligence-based methods. Moreover, the proposed learning algorithm has a closed form, and it is easier to implement than the other existing methods.

Ilker Bozcan, Erdal Kayacan

Anomaly detection is a key goal of autonomous surveillance systems that should be able to alert unusual observations. In this paper, we propose a holistic anomaly detection system using deep neural networks for surveillance of critical infrastructures (e.g., airports, harbors, warehouses) using an unmanned aerial vehicle (UAV). First, we present a heuristic method for the explicit representation of spatial layouts of objects in bird-view images. Then, we propose a deep neural network architecture for unsupervised anomaly detection (UAV-AdNet), which is trained on environment representations and GPS labels of bird-view images jointly. Unlike studies in the literature, we combine GPS and image data to predict abnormal observations. We evaluate our model against several baselines on our aerial surveillance dataset and show that it performs better in scene reconstruction and several anomaly detection tasks. The codes, trained models, dataset, and video will be available at https://bozcani.github.io/uavadnet.

Theo Morales, Andriy Sarabakha, Erdal Kayacan

Drone racing is a recreational sport in which the goal is to pass through a sequence of gates in a minimum amount of time while avoiding collisions. In autonomous drone racing, one must accomplish this task by flying fully autonomously in an unknown environment by relying only on computer vision methods for detecting the target gates. Due to the challenges such as background objects and varying lighting conditions, traditional object detection algorithms based on colour or geometry tend to fail. Convolutional neural networks offer impressive advances in computer vision but require an immense amount of data to learn. Collecting this data is a tedious process because the drone has to be flown manually, and the data collected can suffer from sensor failures. In this work, a semi-synthetic dataset generation method is proposed, using a combination of real background images and randomised 3D renders of the gates, to provide a limitless amount of training samples that do not suffer from those drawbacks. Using the detection results, a line-of-sight guidance algorithm is used to cross the gates. In several experimental real-time tests, the proposed framework successfully demonstrates fast and reliable detection and navigation.

Ilker Bozcan, Erdal Kayacan

Unmanned aerial vehicles (UAVs) with mounted cameras have the advantage of capturing aerial (bird-view) images. The availability of aerial visual data and the recent advances in object detection algorithms led the computer vision community to focus on object detection tasks on aerial images. As a result of this, several aerial datasets have been introduced, including visual data with object annotations. UAVs are used solely as flying-cameras in these datasets, discarding different data types regarding the flight (e.g., time, location, internal sensors). In this work, we propose a multi-purpose aerial dataset (AU-AIR) that has multi-modal sensor data (i.e., visual, time, location, altitude, IMU, velocity) collected in real-world outdoor environments. The AU-AIR dataset includes meta-data for extracted frames (i.e., bounding box annotations for traffic-related object category) from recorded RGB videos. Moreover, we emphasize the differences between natural and aerial images in the context of object detection task. For this end, we train and test mobile object detectors (including YOLOv3-Tiny and MobileNetv2-SSDLite) on the AU-AIR dataset, which are applicable for real-time object detection using on-board computers with UAVs. Since our dataset has diversity in recorded data types, it contributes to filling the gap between computer vision and robotics. The dataset is available at https://bozcani.github.io/auairdataset.

Rogerio Bonatti, Wenshan Wang, Cherie Ho et al.

Aerial cinematography is revolutionizing industries that require live and dynamic camera viewpoints such as entertainment, sports, and security. However, safely piloting a drone while filming a moving target in the presence of obstacles is immensely taxing, often requiring multiple expert human operators. Hence, there is demand for an autonomous cinematographer that can reason about both geometry and scene context in real-time. Existing approaches do not address all aspects of this problem; they either require high-precision motion-capture systems or GPS tags to localize targets, rely on prior maps of the environment, plan for short time horizons, or only follow artistic guidelines specified before flight. In this work, we address the problem in its entirety and propose a complete system for real-time aerial cinematography that for the first time combines: (1) vision-based target estimation; (2) 3D signed-distance mapping for occlusion estimation; (3) efficient trajectory optimization for long time-horizon camera motion; and (4) learning-based artistic shot selection. We extensively evaluate our system both in simulation and in field experiments by filming dynamic targets moving through unstructured environments. Our results indicate that our system can operate reliably in the real world without restrictive assumptions. We also provide in-depth analysis and discussions for each module, with the hope that our design tradeoffs can generalize to other related applications. Videos of the complete system can be found at: https://youtu.be/ookhHnqmlaU.

Efe Camci, Erdal Kayacan

In this work, a novel, end-to-end motion planning method is proposed for quadrotor navigation in cluttered environments. The proposed method circumvents the explicit sensing-reconstructing-planning in contrast to conventional navigation algorithms. It uses raw depth images obtained from a front-facing camera and directly generates local motion plans in the form of smooth motion primitives that move a quadrotor to a goal by avoiding obstacles. Promising training and testing results are presented in both AirSim simulations and real flights with DJI F330 Quadrotor equipped with Intel RealSense D435. The proposed system in action can be found in https://youtu.be/pYvKhc8wrTM.

Andriy Sarabakha, Erdal Kayacan

This work presents an online learning-based control method for improved trajectory tracking of unmanned aerial vehicles using both deep learning and expert knowledge. The proposed method does not require the exact model of the system to be controlled, and it is robust against variations in system dynamics as well as operational uncertainties. The learning is divided into two phases: offline (pre-)training and online (post-)training. In the former, a conventional controller performs a set of trajectories and, based on the input-output dataset, the deep neural network (DNN)-based controller is trained. In the latter, the trained DNN, which mimics the conventional controller, controls the system. Unlike the existing papers in the literature, the network is still being trained for different sets of trajectories which are not used in the training phase of DNN. Thanks to the rule-base, which contains the expert knowledge, the proposed framework learns the system dynamics and operational uncertainties in real-time. The experimental results show that the proposed online learning-based approach gives better trajectory tracking performance when compared to the only offline trained network.

Mirko Gschwindt, Efe Camci, Rogerio Bonatti et al.

Aerial filming is constantly gaining importance due to the recent advances in drone technology. It invites many intriguing, unsolved problems at the intersection of aesthetical and scientific challenges. In this work, we propose a deep reinforcement learning agent which supervises motion planning of a filming drone by making desirable shot mode selections based on aesthetical values of video shots. Unlike most of the current state-of-the-art approaches that require explicit guidance by a human expert, our drone learns how to make favorable viewpoint selections by experience. We propose a learning scheme that exploits aesthetical features of retrospective shots in order to extract a desirable policy for better prospective shots. We train our agent in realistic AirSim simulations using both a hand-crafted reward function as well as reward from direct human input. We then deploy the same agent on a real DJI M210 drone in order to test the generalization capability of our approach to real world conditions. To evaluate the success of our approach in the end, we conduct a comprehensive user study in which participants rate the shot quality of our methods. Videos of the system in action can be seen at https://youtu.be/qmVw6mfyEmw.

Siqi Zhou, Andriy Sarabakha, Erdal Kayacan et al.

In this paper, we propose an online learning approach that enables the inverse dynamics model learned for a source robot to be transferred to a target robot (e.g., from one quadrotor to another quadrotor with different mass or aerodynamic properties). The goal is to leverage knowledge from the source robot such that the target robot achieves high-accuracy trajectory tracking on arbitrary trajectories from the first attempt with minimal data recollection and training. Most existing approaches for multi-robot knowledge transfer are based on post-analysis of datasets collected from both robots. In this work, we study the feasibility of impromptu transfer of models across robots by learning an error prediction module online. In particular, we analytically derive the form of the mapping to be learned by the online module for exact tracking, propose an approach for characterizing similarity between robots, and use these results to analyze the stability of the overall system. The proposed approach is illustrated in simulation and verified experimentally on two different quadrotors performing impromptu trajectory tracking tasks, where the quadrotors are required to accurately track arbitrary hand-drawn trajectories from the first attempt.