Article
Robotics
Juntong Qi, Jinjin Guo, Mingming Wang, Chong Wu, Zhenwei Ma
Summary: This letter proposes a novel distributed cooperative control algorithm to address the problem of collision avoidance and obstacle avoidance for multiple quadrotors during the formation tracking process. The algorithm combines collision avoidance and obstacle avoidance schemes into the control layer, and utilizes a repulsion function based on Hooke's law with damping and a split-merge strategy inspired by pigeons' obstacle avoidance behavior to achieve efficient avoidance and distance adjustment between quadrotors and obstacles.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Jinjin Guo, Juntong Qi, Mingming Wang, Chong Wu, Guang Yang
Summary: This letter proposes a distributed cooperative control algorithm with a separation-merge mechanism to address the issues of safe flight and formation reconfiguration in unknown environments for multiple quadrotors. The separation-merge framework integrates obstacle avoidance, inter-robot collision avoidance, and formation reconfiguration mechanisms, and couples them to the control layer. The proposed method incorporates obstacle detection based on pigeon's behavior, introduces rotational potential energy to handle local minima and oscillations, and designs a collision avoidance mechanism inspired by spring damping system. Furthermore, a formation reconfiguration mechanism is developed based on consensus theory. The effectiveness of the proposed method is verified through visualization simulator and outdoor experiments.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Aerospace
Jinjin Guo, Juntong Qi, Mingming Wang, Chong Wu, Yuan Ping, Shi Li, Jie Jin
Summary: In this paper, a distributed obstacle avoidance controller is proposed, including obstacle avoidance term, inter-robot collision avoidance term, and formation reconstruction. By designing the local obstacle avoidance algorithm, inter-robot collision avoidance algorithm, and distributed formation reconstruction controller, the autonomous flight ability of multiple quadrotors in unknown environments is improved.
AEROSPACE SCIENCE AND TECHNOLOGY
(2023)
Article
Engineering, Marine
Diju Gao, Peng Zhou, Weifeng Shi, Tianzhen Wang, Yide Wang
Summary: The proposed dynamic obstacle avoidance method using PSO and DWA algorithm combined to enhance the efficiency of USVs in collision avoidance, with fuzzy control adapting the weight coefficients in the cost function of the DWA algorithm, experimentally proven to be effective.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Jia Wang, Rongtao Wang, Daohua Lu, Hao Zhou, Tianyi Tao
Summary: This study proposes an autonomous dynamic obstacle avoidance method for unmanned surface vehicles (USVs) based on the enhanced velocity obstacle method, and numerically demonstrates that it optimizes the heading angle, thereby avoiding the risk of ship rollover and achieving more accurate obstacle avoidance actions.
Article
Engineering, Marine
Shilong Li, Yakun Zhu, Jianguo Bai, Ge Guo
Summary: This article studies trajectory tracking and dynamic obstacle avoidance problems of unmanned ships and proposes an event-triggered adaptive nonlinear model predictive control (EANMPC) method to solve these problems.
Article
Automation & Control Systems
Hao Wang, Jinjun Shan
Summary: This article studies the formation control problems for leader-follower multiquadrotor systems in the presence of unknown perturbations and limited resources using an event-triggered mechanism. A distributed adaptive dynamic event-triggered formation control protocol is designed based on a sliding-mode control approach to achieve integral sliding-mode manifold in finite time. A distributed integral sliding-mode surface is proposed to ensure formation tracking performance of the multiquadrotor systems. A novel adaptive dynamic triggering strategy is developed to dynamically adjust the triggering interval and reduce unnecessary resource consumption. The effectiveness of the proposed control scheme is validated through simulations and experiments.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Robotics
Geesara Kulathunga, Dmitry Devitt, Alexandr Klimchik
Summary: This paper presents an optimization-based reference trajectory tracking method for slow-speed maneuvers of quadrotor robots. The proposed method combines planning with controlling paradigm and employs nonlinear model predictive control (NMPC) to predict the optimal control policy in each iteration. By constructing an incremental Euclidean distance transformation map, the method considers obstacle constraints and generates a reference trajectory that ensures dynamic feasibility.
JOURNAL OF FIELD ROBOTICS
(2022)
Article
Automation & Control Systems
Hongjiu Yang, Qing Li, Zhiqiang Zuo, Hai Zhao
Summary: This article examines event-triggered model predictive control for simultaneous tracking and formation of a multi-vehicle system with collision and obstacle avoidance. By establishing an event-triggered mechanism and a compatibility constraint, the safety and convergence of the system are guaranteed.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2021)
Article
Engineering, Marine
Cheng Liu, Qizhi Hu, Xuegang Wang, Jianchuan Yin
Summary: This paper presents a novel event-triggered-based nonlinear model predictive control (ENMPC) solution for trajectory tracking of underactuated ship with multi-obstacle avoidance. The problem of trajectory tracking and automatic obstacle avoidance is solved through optimization problem and event-triggered control mechanism, reducing computational burden.
Article
Engineering, Aerospace
Yang Yuan, Yimin Deng, Sida Luo, Haibin Duan, Chen Wei
Summary: This paper studies a formation control protocol of solar-powered unmanned aerial vehicles (SUAVs) and proposes a behavior-based structure formation control protocol in the horizontal plane and a new obstacle avoidance strategy. The paper also considers the difference of charge and discharge power in energy management in the vertical direction and verifies the effectiveness of the proposed method through numerical simulations.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Aerospace
Hongqian Zhao, Honghua Dai, Zhaohui Dang
Summary: A new guidance algorithm based on dynamic low-resolution image sequences is proposed to reduce the burden of obtaining high-precision lunar surface information during lunar soft landing. The algorithm utilizes a integrated procedure of dynamic descent stage and an acceptance domain algorithm to optimize the final landing site and reduce the burden on the onboard computer. Numerical simulation results confirm the validity, reliability, and effectiveness of the proposed algorithm.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Computer Science, Information Systems
Yong Yuan, You Shi, Song Yue, Shanliang Xue, Changyan Yi, Bing Chen
Summary: In this article, we propose an improved speed obstacle algorithm to address the issue of dynamic obstacle avoidance for AGVs in a dynamic environment. The algorithm estimates the positions of dynamic obstacles using Kalman filtering and builds a speed obstacle buffer based on the estimated positions, allowing the AGV to create a speed obstacle model using the predicted positions for the next moment.
Article
Chemistry, Analytical
Hongyang Zhu, Yi Ding
Summary: Ship collision avoidance is a complex process that requires determining the optimal collision avoidance point (OCAP) based on the relative velocities and kinematic parameters of unmanned surface vehicles (USVs) and obstacles. The proposed approach combines a model for USV dynamics with a velocity obstacle method to detect and avoid obstacles. The algorithm evaluates collision hazards and optimizes USV maneuverability in real-time.
Article
Engineering, Electrical & Electronic
Jingyu Tang, Mingze Sun, Lingjun Zhu, Menghan Hu, Mei Zhou, Jian Zhang, Qingli Li, Guangtao Zhai
Summary: An assistive cane with visual odometry was designed to help blind individuals navigate safely indoors. Experimental results showed that device parameters significantly affected passing time and success rate of obstacle avoidance, while users' visual perception patterns should also be taken into account when adjusting parameters.
IEEE SENSORS JOURNAL
(2021)
Article
Robotics
Giovanni Cioffi, Titus Cieslewski, Davide Scaramuzza
Summary: Robotic practitioners generally approach the vision-based SLAM problem through discrete-time formulations, but these formulations require tailored algorithms and simplifying assumptions in the presence of high-rate and/or asynchronous measurements. On the other hand, continuous-time SLAM allows the fusion of multiple sensor modalities in an intuitive fashion, but may result in worse trajectory estimates.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Leonard Bauersfeld, Davide Scaramuzza
Summary: This article introduces the importance of multicopters in various application areas, and proposes a method for estimating the range, endurance, and optimal speed of multicopters. The accuracy and feasibility of this method are validated through experiments and flights. The article also provides a pen-and-paper algorithm to assist future researchers in building drones with maximum range and endurance.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Fang Nan, Sihao Sun, Philipp Foehn, Davide Scaramuzza
Summary: This study proposes a fault-tolerant controller using nonlinear model predictive control (NMPC) to stabilize and control a quadrotor in the event of complete failure of a single rotor. Unlike existing methods, this approach considers the full nonlinear dynamics of the damaged quadrotor and the thrust constraint of each rotor.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Yunlong Song, Davide Scaramuzza
Summary: A novel framework of policy search for model predictive control is proposed in the study, utilizing policy search to automatically select high-level decision variables for MPC. The formulation of a parameterized controller allows optimizing policies in a self-supervised manner.
IEEE TRANSACTIONS ON ROBOTICS
(2022)
Article
Robotics
Philipp Foehn, Elia Kaufmann, Angel Romero, Robert Penicka, Sihao Sun, Leonard Bauersfeld, Thomas Laengle, Giovanni Cioffi, Yunlong Song, Antonio Loquercio, Davide Scaramuzza
Summary: Agilicious is a hardware and software framework designed for autonomous, agile quadrotor flight, supporting both model-based and neural network-based controllers. It offers a combination of high-performance hardware and flexible software stack, making it suitable for various tasks and environments, as well as hardware-in-the-loop simulation.
Article
Robotics
Angel Romero, Robert Penicka, Davide Scaramuzza
Summary: In this letter, the challenge of flying a quadrotor using time-optimal control policies is addressed. The authors propose a sampling-based method for efficient generation of time-optimal paths and a Model Predictive Contouring Control approach for tracking the paths in real-time, ensuring adaptation to changes and unknown disturbances.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Robert Penicka, Yunlong Song, Elia Kaufmann, Davide Scaramuzza
Summary: This study addresses the problem of minimum-time flight for a quadrotor through a sequence of waypoints in the presence of obstacles. By leveraging deep reinforcement learning and classical topological path planning, a robust neural-network controller is trained to achieve better performance and higher robustness compared to state-of-the-art methods.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Lintong Zhang, Michael Helmberger, Lanke Frank Tarimo Fu, David Wisth, Marco Camurri, Davide Scaramuzza, Maurice Fallon
Summary: To drive the advancement of SLAM systems, we created the Hilti-Oxford Dataset, which includes various challenges to test the performance of SLAM algorithms in different scenarios. We implemented a novel ground truth collection method to accurately measure pose errors with millimeter accuracy. The dataset attracted a large number of researchers to participate in the Hilti SLAM challenge.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Proceedings Paper
Automation & Control Systems
Charith Munasinghe, Fatemeh Mohammadi Amin, Davide Scaramuzza, Hans Wernher van de Venn
Summary: Safe human-robot collaboration is crucial in the emerging Industry 5.0 paradigm, where conventional robots are being replaced by more intelligent and flexible collaborative robots. However, the lack of research and dedicated datasets for 3D semantic segmentation of collaborative robot workspaces hinders safe and efficient collaboration. This work addresses this limitation by developing a new dataset named COVERED and benchmarking state-of-the-art algorithm performance for real-time semantic segmentation.
2022 IEEE 27TH INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION (ETFA)
(2022)
Proceedings Paper
Automation & Control Systems
Maryam Rezayati, Grammatiki Zanni, Ying Zaoshi, Davide Scaramuzza, Hans Wernher van de Venn
Summary: Direct physical interaction with robots is important in flexible production scenarios, but poses risks to operators. Simple measures can prevent injuries, but hinder true human-robot cooperation. More sophisticated solutions are needed in human-robot collaboration scenarios.
2022 IEEE 27TH INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION (ETFA)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhaoning Sun, Nico Messikommer, Daniel Gehrig, Davide Scaramuzza
Summary: This research introduces ESS (Event-based Semantic Segmentation), a method that transfers the semantic segmentation task from labeled image datasets to unlabeled events through unsupervised domain adaptation (UDA). Compared to existing methods, our approach aligns event embeddings with image embeddings without the need for video data or per-pixel alignment between images and events, and without the need to infer motion from still images. We also introduce DSEC-Semantic, a large-scale event-based dataset with fine-grained labels. Experimental results show that ESS outperforms existing UDA approaches using image labels alone and even surpasses state-of-the-art supervised approaches when combined with event labels in both DDD17 and DSEC-Semantic datasets. ESS is a general-purpose method that opens up new and previously inaccessible research directions for event cameras.
COMPUTER VISION, ECCV 2022, PT XXXIV
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Stepan Tulyakov, Alfredo Bochicchio, Daniel Gehrig, Stamatios Georgoulis, Yuanyou Li, Davide Scaramuzza
Summary: This study addresses several issues in video frame interpolation, including unstable fusion process of complementary interpolation results, inefficient motion estimation process, and potential artifacts in low contrast regions. Additionally, a large-scale dataset with challenging scenes is constructed, and the reconstruction quality is improved through multi-scale feature-level fusion and one-shot non-linear inter-frame motion computation.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Simon Schaefer, Daniel Gehrig, Davide Scaramuzza
Summary: This research introduces a novel event-processing paradigm called Asynchronous, Event-based Graph Neural Networks (AEGNNs), which generalize standard GNNs to process events as evolving spatio-temporal graphs. AEGNNs significantly reduce computation and latency by only recomputing network activations for the nodes affected by each new event. The experimental results show a reduction in computational complexity by up to 200-fold and similar or even better performance compared to state-of-the-art asynchronous methods, making AEGNNs a promising approach for low-latency event-based processing.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Javier Hidalgo-Carrio, Guillermo Gallego, Davide Scaramuzza
Summary: EDS is a direct monocular visual odometry method that uses events and frames, and it overcomes the problem of changing appearance in indirect methods. It outperforms previous event-based odometry solutions and can work at lower frame rates, making it suitable for low-power motion-tracking applications.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Theory & Methods
Nico Messikommer, Stamatios Georgoulis, Daniel Gehrig, Stepan Tulyakov, Julius Erbach, Alfredo Bochicchio, Yuanyou Li, Davide Scaramuzza
Summary: This paper proposes a multi-bracket HDR pipeline combining a standard camera with an event camera to address the issues of saturation and noise in LDR images in dynamic scenes. The results show that using events can improve overall robustness and image quality.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022
(2022)