检索结果-内蒙古大学图书馆

The Visual-Inertial-Dynamical Multirotor Dataset

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Kunyi Yang, Tiankai Ding, Ziming Yang, Sheng Ma, Teng Li, Mingyang Xu, Chao Gao, Fei State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China Huzhou Institute Zhejiang University Huzhou313000 China Alibaba DAMO Academy Autonomous Driving Lab Hangzhou311121 China

Recently, the community has witnessed numerous datasets built for developing and testing state estimators. However, for some applications such as aerial transportation or search-and-rescue, the contact force or other disturbance must be perceived for robust planning and control, which is beyond the capacity of these datasets. This paper introduces a Visual-Inertial-Dynamical (VID) dataset, not only focusing on traditional six degrees of freedom (6-DOF) pose estimation but also providing dynamical characteristics of the flight platform for external force perception or dynamics-aided estimation. The VID dataset contains hardware synchronized imagery and inertial measurements, with accurate ground truth trajectories for evaluating common visual-inertial estimators. Moreover, the proposed dataset highlights rotor speed and motor current measurements, control inputs, and ground truth 6-axis force data to evaluate external force estimation. To the best of our knowledge, the proposed VID dataset is the first public dataset containing visual-inertial and complete dynamical information in the real world for pose and external force evaluation. The dataset and related files are open-sourced. © 2021, CC BY.

关键词： Degrees of freedom (mechanics)

HILONet: Hierarchical imitation learning from non-aligned observations

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Shanqi Cao, Junjie Chen, Wenzhou Wen, Licheng Liu, Yong The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang310027 China

It is challenging learning from demonstrated observation-only trajectories in a non-time-aligned environment because most imitation learning methods aim to imitate experts by following the demonstration step-by-step. However, aligned demonstrations are seldom obtainable in real-world scenarios. In this work, we propose a new imitation learning approach called Hierarchical Imitation Learning from Observation(HILONet), which adopts a hierarchical structure to choose feasible subgoals from demonstrated observations dynamically. Furthermore, our method can learn different kinds of policy corresponding to different tasks by using a novel reward structure. We also present three different ways to increase sample efficiency in the hierarchical structure. We conduct extensive experiments using several environments. The results show the improvement in both performance and learning efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Efficiency

Alternating minimization based trajectory generation for quadrotor aggressive flight

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Zhepei Zhou, Xin Xu, Chao Chu, Jian Gao, Fei State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China

With much research has been conducted into trajectory planning for quadrotors, planning with spatial and temporal optimal trajectories in real-time is still challenging. In this paper, we propose a framework for generating large-scale piecewise polynomial trajectories for aggressive autonomous flights, with highlights on its superior computational efficiency and simultaneous spatial-temporal optimality. Exploiting the implicitly decoupled structure of the planning problem, we conduct alternating minimization between boundary conditions and time durations of trajectory pieces. In each minimization phase, we leverage the algebraic convenience of the sub-problem to escape poor local minima and achieve the lowest time consumption. Theoretical analysis for the global/local convergence rate of our proposed method is provided. Moreover, based on polynomial theory, an extremely fast feasibility check method is designed for various kinds of constraints. By incorporating the method into our alternating structure, a constrained minimization algorithm is constructed to optimize trajectories on the premise of feasibility. Benchmark evaluation shows that our algorithm outperforms state-of-the-art methods regarding efficiency, optimality, and scalability. Aggressive flight experiments in a limited space with dense obstacles are presented to demonstrate the performance of the proposed algorithm. We release our implementation as an open-source ros-package1. Copyright © 2020, The Authors. All rights reserved.

关键词： Constrained optimization

Moving forward in formation: A decentralized hierarchical learning approach to multi-agent moving together

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Shanqi Wen, Licheng Cui, Jinhao Yang, Xuemeng Cao, Junjie Liu, Yong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang310027 China

Multi-agent path finding in formation has many potential real-world applications like mobile warehouse robots. However, previous multi-agent path finding (MAPF) methods hardly take formation into consideration. Furthermore, they are usually centralized planners and require the whole state of the environment. Other decentralized partially observable approaches to MAPF are reinforcement learning (RL) methods. However, these RL methods encounter difficulties when learning path finding and formation problem at the same time. In this paper, we propose a novel decentralized partially observable RL algorithm that uses a hierarchical structure to decompose the multi-objective task into unrelated ones. It also calculates a theoretical weight that makes every task’s reward has equal influence on the final RL value function. Additionally, we introduce a communication method that helps agents cooperate with each other. Experiments in simulation show that our method outperforms other end-to-end RL methods and our method can naturally scale to large world sizes where centralized planner struggles. We also deploy and validate our method in a real-world scenario. Copyright © 2020, The Authors. All rights reserved.

关键词： Multi agent systems

Fast-tracker: a robust aerial system for tracking agile target in cluttered environments

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Han, Zhichao Zhang, Ruibin Pan, Neng Xu, Chao Gao, Fei State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China

This paper proposes a systematic solution that uses an unmanned aerial vehicle (UAV) to aggressively and safely track an agile target. The solution properly handles the challenging situations where the intent of the target and the dense environments are unknown to the UAV. Our work is divided into two parts: target motion prediction and tracking trajectory planning. The target motion prediction method utilizes target observations to reliably predict the future motion of the target considering dynamic constraints. The tracking trajectory planner follows the traditional hierarchical workflow. A target informed kinodynamic searching method is adopted as the front-end, which heuristically searches for a safe tracking trajectory. The back-end optimizer then refines it into a spatial-temporal optimal and collision-free trajectory. The proposed solution is integrated into an onboard quadrotor system. We fully test the system in challenging real-world tracking missions. Moreover, benchmark comparisons validate that the proposed method surpasses the cutting-edge methods on time efficiency and tracking effectiveness. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion estimation

Adaptive Pseudo Inverse control for a Class of Nonlinear Asymmetric and Saturated Nonlinear Hysteretic systems

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第4期8卷 916-928页

作者： Xiuyu Zhang Ruijing Jing Zhiwei Li Zhi Li Xinkai Chen Chun-Yi Su School of Automation Engineering Northeast Electric Power Universityand also with Jilin Province International Research Center of Precision Drive and Intelligent ControlJilin 132012China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819China Department of Electronic and Information Systems Shibaura Institute of TechnologySaitama 337-8570Japan Department of Mechanical and Industrial Engineering Concordia UniversityQCMontreal H3B 1R6Canada

This paper aims at eliminating the asymmetric and saturated hysteresis nonlinearities by designing hysteresis pseudo inverse compensator and robust adaptive dynamic surface control(DSC)***"pseudo inverse"means that an on-line calculation mechanism of approximate control signal is developed by applying a searching method to the designed temporary control signal where the true control signal is *** main contributions are summarized as:1)to our best knowledge,it is the first time to compensate the asymmetric and saturated hysteresis by using hysteresis pseudo inverse compensator because the construction of the true saturated-type hysteresis inverse model is very difficult;2)by designing the saturated-type hysteresis pseudo inverse compensator,the construction of true explicit hysteresis inverse and the identifications of its corresponding unknown parameters are not required when dealing with the saturated-type hysteresis;3)by combining DSC technique with the tracking error transformed function,the"explosion of complexity"problem in backstepping method is overcome and the prespecified tracking performance is *** of stability and experimental results on the hardware-inloop platform illustrate the effectiveness of the proposed adaptive pseudo inverse control scheme.

关键词： Adaptive dynamic surface control adaptive pseudo inverse control asymmetric and saturated hysteresis robust control

Radar-on-Lidar: metric radar localization on prior lidar maps

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yin, Huan Wang, Yue Tang, Li Xiong, Rong The State Key Laboratory of Industrial Control and Technology The Institute of Cyber-Systems and Control Zhejiang University Hangzhou310058 China

Radar and lidar, provided by two different range sensors, each has pros and cons of various perception tasks on mobile robots or autonomous driving. In this paper, a Monte Carlo system is used to localize the robot with a rotating radar sensor on 2D lidar maps. We first train a conditional generative adversarial network to transfer raw radar data to lidar data, and achieve reliable radar points from generator. Then an efficient radar odometry is included in the Monte Carlo system. Combining the initial guess from odometry, a measurement model is proposed to match the radar data and prior lidar maps for final 2D positioning. We demonstrate the effectiveness of the proposed localization framework on the public multi-session dataset. The experimental results show that our system can achieve high accuracy for long-term localization in outdoor scenes. Copyright © 2020, The Authors. All rights reserved.

关键词： Radar measurement

Search-based kinodynamic motion planning for omnidirectional quadruped robots

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Pei Zhou, Xiaoyu Zhao, Qingteng Wu, Jun Zhu, Qiuguo The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang310027 China

Autonomous navigation has played an increasingly significant role in quadruped robot system. However, most existing works on quadruped robots navigation using traditional search-based or sample-based methods do not consider the kinodynamic characteristics of quadruped robots, generating kinodynamically infeasible parts, that are difficult to track. In this paper, we introduce a complete navigation system considering the omnidirectional abilities of quadruped robots. First, we use kinodynamic path finding method to obtain smooth, dynamically feasible, time-optimal initial paths and add collision cost as a soft constraint to ensure safety. Then the trajectory is refined by the timed elastic band (TEB) method based on the omnidirectional model of quadruped robots. The superior performance of our work is demonstrated through simulating and real-world experiments on our quadruped robot Jueying Mini. Copyright © 2020, The Authors. All rights reserved.

关键词： Multipurpose robots

TGK-Planner: An efficient topology guided kinodynamic planner for autonomous quadrotors

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ye, Hongkai Zhou, Xin Xu, Chao Chu, Jian Gao, Fei State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China

In this paper, we propose a lightweight yet effective quadrotor planning system for aggressive flights with limited onboard computing resources. The proposed system follows the traditional hierarchical planning workflow, with novel designs to improve the robustness and efficiency in both the pathfinding and trajectory optimization sub-modules. Firstly, we propose the topology guided graph, which roughly captures the topological structure of the environment and guides the state sampling of a sampling-based kinodynamic planner. In this way, we significantly improve the efficiency of finding a safe and dynamically feasible trajectory. Then, we refine the smoothness and continuity of the trajectory in an optimization framework, which incorporates the homotopy constraint to guarantee the safety of the trajectory. The optimization program is formulated as a sequence of quadratic programmings (QPs) and can be iteratively solved in a few milliseconds. Finally, the proposed system is integrated into a fully autonomous quadrotor and validated in various simulated and real-world scenarios. Benchmark comparisons show that our method outperforms state-of-the-art methods with regard to efficiency and trajectory quality. Moreover, we will release our code as an open-source package. Copyright © 2020, The Authors. All rights reserved.

关键词： Trajectories