Robotics and Autonomous Systems最新文献

英文中文

Position-based acoustic visual servo control for docking of autonomous underwater vehicle using deep reinforcement learning

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-01-06 DOI: 10.1016/j.robot.2024.104914

Zhao Wang , Xianbo Xiang , Xinyang Xiong , Shaolong Yang

In this paper, a position-based acoustic visual servo control scheme is proposed to achieve efficient docking for underactuated autonomous underwater vehicle (AUV). To address the issue that docking station can hardly be kept in the limited field of onboard imaging sonar using conventional controllers, deep reinforcement learning (DRL) is proposed to learn an optimal control strategy to achieve both field control and precise docking. First, a visualized underwater docking environment is developed based on robotic operation system (ROS) and Gazebo platform, and imaging sonar is modeled to simulate acoustic image. Subsequently, a deep neural network-inspired detector and a state-of-the-art feature tracker are combined as the perceptual header of docking controller which transforms the output of imaging sonar to the input of control agent rapidly and precisely. Furthermore, cost terms of DRL-based control agents are further designed by incorporating two nonlinear functions with different gradients, yet the change rates of received rewards from the state observation are not same in different situations. In this case, the control agents are enabled to learn the strategy to eliminate offset and keep depth of AUV. Moreover, feature of docking station will also be well kept in acoustic image due to the rapid increasing punishment of great bearing angle when AUV is in high maneuvering. Furthermore, evaluation results and comparative experiments are presented to verify feasibility and efficiency of the proposed servo control scheme using deep reinforcement learning.

{"title":"Position-based acoustic visual servo control for docking of autonomous underwater vehicle using deep reinforcement learning","authors":"Zhao Wang , Xianbo Xiang , Xinyang Xiong , Shaolong Yang","doi":"10.1016/j.robot.2024.104914","DOIUrl":"10.1016/j.robot.2024.104914","url":null,"abstract":"<div><div>In this paper, a position-based acoustic visual servo control scheme is proposed to achieve efficient docking for underactuated autonomous underwater vehicle (AUV). To address the issue that docking station can hardly be kept in the limited field of onboard imaging sonar using conventional controllers, deep reinforcement learning (DRL) is proposed to learn an optimal control strategy to achieve both field control and precise docking. First, a visualized underwater docking environment is developed based on robotic operation system (ROS) and Gazebo platform, and imaging sonar is modeled to simulate acoustic image. Subsequently, a deep neural network-inspired detector and a state-of-the-art feature tracker are combined as the perceptual header of docking controller which transforms the output of imaging sonar to the input of control agent rapidly and precisely. Furthermore, cost terms of DRL-based control agents are further designed by incorporating two nonlinear functions with different gradients, yet the change rates of received rewards from the state observation are not same in different situations. In this case, the control agents are enabled to learn the strategy to eliminate offset and keep depth of AUV. Moreover, feature of docking station will also be well kept in acoustic image due to the rapid increasing punishment of great bearing angle when AUV is in high maneuvering. Furthermore, evaluation results and comparative experiments are presented to verify feasibility and efficiency of the proposed servo control scheme using deep reinforcement learning.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"186 ","pages":"Article 104914"},"PeriodicalIF":4.3,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Interaction-aware motion planning and control based on game theory with human-in-the-loop validation

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-01-04 DOI: 10.1016/j.robot.2024.104908

Mohamed-Khalil Bouzidi , Ehsan Hashemi

An interaction-aware control and motion planning framework is proposed and experimentally verified for time-critical merging scenarios. The framework considers interaction between the automated driving system and other vehicles, including human-driven vehicles, by monitoring lateral and longitudinal response of the neighbor vehicle without communication or having access to their control and safety objective functions. This has not been accounted for safe motion planning and controls in existing merging solutions in mixed traffic. The framework includes a novel inverse differential game based on a long short-term memory network for estimation of the possible path tracking objective function of the human-driven vehicle in real-time. Then, a game-theoretic receding horizon controller is devised for the automated driving system by predicting the trajectory of the human-driven vehicle. The developed framework is validated in several merging scenarios and road surface conditions using CarSim high-fidelity simulations including human-in-the-loop case studies with different test subjects.

{"title":"Interaction-aware motion planning and control based on game theory with human-in-the-loop validation","authors":"Mohamed-Khalil Bouzidi , Ehsan Hashemi","doi":"10.1016/j.robot.2024.104908","DOIUrl":"10.1016/j.robot.2024.104908","url":null,"abstract":"<div><div>An interaction-aware control and motion planning framework is proposed and experimentally verified for time-critical merging scenarios. The framework considers interaction between the automated driving system and other vehicles, including human-driven vehicles, by monitoring lateral and longitudinal response of the neighbor vehicle without communication or having access to their control and safety objective functions. This has not been accounted for safe motion planning and controls in existing merging solutions in mixed traffic. The framework includes a novel inverse differential game based on a long short-term memory network for estimation of the possible path tracking objective function of the human-driven vehicle in real-time. Then, a game-theoretic receding horizon controller is devised for the automated driving system by predicting the trajectory of the human-driven vehicle. The developed framework is validated in several merging scenarios and road surface conditions using <em>CarSim</em> high-fidelity simulations including human-in-the-loop case studies with different test subjects.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"186 ","pages":"Article 104908"},"PeriodicalIF":4.3,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Signal Temporal Logic approach for task-based coordination of multi-aerial systems: A wind turbine inspection case study

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-01-02 DOI: 10.1016/j.robot.2024.104905

Giuseppe Silano , Alvaro Caballero , Davide Liuzza , Luigi Iannelli , Stjepan Bogdan , Martin Saska

The paper addresses task assignment and trajectory generation for collaborative inspection missions using a fleet of multi-rotors, focusing on the wind turbine inspection scenario. The proposed solution enables safe and feasible trajectories while accommodating heterogeneous time-bound constraints and vehicle physical limits. An optimization problem is formulated to meet mission objectives and temporal requirements encoded as Signal Temporal Logic (STL) specifications. Additionally, an event-triggered replanner is introduced to address unforeseen events and compensate for lost time. Furthermore, a generalized robustness scoring method is employed to reflect user preferences and mitigate task conflicts. The effectiveness of the proposed approach is demonstrated through MATLAB and Gazebo simulations, as well as field multi-robot experiments in a mock-up scenario.

引用次数: 0

LLM-controller: Dynamic robot control adaptation using large language models

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-01-02 DOI: 10.1016/j.robot.2024.104913

Rasoul Zahedifar , Mahdieh Soleymani Baghshah , Alireza Taheri

In this study, a dynamic adaptation of a robot controller is investigated using large language models (LLMs). We propose our controller called the LLM-Controller, where, in response to changes in the system dynamics or reference signals, the LLM adapts the controller to the new context. Various scenarios reflecting real-world conditions, including unknown disturbances, unmodeled dynamics, and changing reference signals, were analyzed. Using the proposed LLM-Controller, one can adapt to new conditions automatically without manual tuning. Additionally, the controller's performance is investigated using different prompting techniques, such as zero-shot and few-shot chain-of-thought (COT), which facilitate step-by-step reasoning and improve adaptation to new contexts. The proposed scheme is applied to two case studies involving robot manipulators. First, it is tested on a 2-link robot manipulator, followed by a 3-link manipulator to enhance its generalizability. The algorithm's adaptability and effectiveness are further evaluated across a range of tasks and conditions, demonstrating its versatility in various scenarios. The results demonstrate that the LLM-Controller achieved a 100 % success rate in adapting the controller to new conditions for the 2-link manipulator, with a significant improvement in trial efficiency; while for the 3-link system, the controller maintained a 90 % success rate, showing greater adaptability to changes in reference signals or dynamic conditions in under 20 s. These outcomes could be further enhanced by employing a COT approach, potentially leading to higher success rates, fewer trials, and optimized costs. In contrast, the classic nonlinear adaptive controller struggled to adjust to the new conditions, while the LLM-Controller automatically adapts, guiding the system to new stable states. This research provides valuable insights into how LLMs can enhance decision-making, improving stability and performance in dynamic and uncertain environments.

{"title":"LLM-controller: Dynamic robot control adaptation using large language models","authors":"Rasoul Zahedifar , Mahdieh Soleymani Baghshah , Alireza Taheri","doi":"10.1016/j.robot.2024.104913","DOIUrl":"10.1016/j.robot.2024.104913","url":null,"abstract":"<div><div>In this study, a dynamic adaptation of a robot controller is investigated using large language models (LLMs). We propose our controller called the LLM-Controller, where, in response to changes in the system dynamics or reference signals, the LLM adapts the controller to the new context. Various scenarios reflecting real-world conditions, including unknown disturbances, unmodeled dynamics, and changing reference signals, were analyzed. Using the proposed LLM-Controller, one can adapt to new conditions automatically without manual tuning. Additionally, the controller's performance is investigated using different prompting techniques, such as zero-shot and few-shot chain-of-thought (COT), which facilitate step-by-step reasoning and improve adaptation to new contexts. The proposed scheme is applied to two case studies involving robot manipulators. First, it is tested on a 2-link robot manipulator, followed by a 3-link manipulator to enhance its generalizability. The algorithm's adaptability and effectiveness are further evaluated across a range of tasks and conditions, demonstrating its versatility in various scenarios. The results demonstrate that the LLM-Controller achieved a 100 % success rate in adapting the controller to new conditions for the 2-link manipulator, with a significant improvement in trial efficiency; while for the 3-link system, the controller maintained a 90 % success rate, showing greater adaptability to changes in reference signals or dynamic conditions in under 20 s. These outcomes could be further enhanced by employing a COT approach, potentially leading to higher success rates, fewer trials, and optimized costs. In contrast, the classic nonlinear adaptive controller struggled to adjust to the new conditions, while the LLM-Controller automatically adapts, guiding the system to new stable states. This research provides valuable insights into how LLMs can enhance decision-making, improving stability and performance in dynamic and uncertain environments.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"186 ","pages":"Article 104913"},"PeriodicalIF":4.3,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Active control strategy of lower limb exoskeleton based on variable admittance control

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-01-02 DOI: 10.1016/j.robot.2024.104906

Jiange Kou , Yixuan Wang , Yan Shi , Shaofeng Xu , Haoran Zhan , Qing Guo

Lower limb exoskeleton is a typical wearable robot to assist human motion with physiological power improvement. The active mode experiments based on the constant admittance parameters are carried out to acquire the original data. Then the fast fourier transform(FFT) together with linear fitting methods are used to process the original data and to obtain the optimal admittance parameters with different step frequencies. A variable admittance controller is adopted to implement the active follow-up control of exoskeleton to deal with the time-varying step frequency, which means that the operator’s motion is motivated by his/her intention. Meanwhile, the exoskeleton control tries best to improve the wearable comfortable performance of human–exoskeleton system. The effectiveness of the proposed control scheme is verified by both the comparative simulations and experimental results of the human–exoskeleton cooperative motion.

引用次数: 0

An algorithm for dynamic obstacle avoidance applied to UAVs

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-01-01 DOI: 10.1016/j.robot.2024.104907

Julian Rascon Enriquez , Bernardino Castillo-Toledo , Stefano Di Gennaro , Luis Arturo García-Delgado

This research focuses on developing a navigation method for mobile robots to effectively avoid moving obstacles while accurately tracking a desired path. The approach introduces an enhanced velocity field that incorporates hydrodynamic theory tools. Initially designed for the 2D case, the method is subsequently extended to the 3D scenario by introducing vector field extensions and rotations.

To validate the proposed scheme, experiments are conducted using a UAV model tasked with tracking a circular contour. The control system employs two PD controllers for regulating the vertical position (

z

) and yaw angle (

ψ

), while the roll (

ϕ

) and pitch (

θ

) angles are controlled using a nested saturation method.

The numerical results demonstrate the successful achievement of the tracking objective, even when a moving obstacle crosses the reference path. Notably, this study considers the scenario where an obstacle approaches the vehicle from behind, which is often overlooked in similar investigations. This aspect is examined in both the 2D and 3D cases.

Subsequently, the proposed navigation method is tested on a quadrotor vehicle, yielding favorable results.

{"title":"An algorithm for dynamic obstacle avoidance applied to UAVs","authors":"Julian Rascon Enriquez , Bernardino Castillo-Toledo , Stefano Di Gennaro , Luis Arturo García-Delgado","doi":"10.1016/j.robot.2024.104907","DOIUrl":"10.1016/j.robot.2024.104907","url":null,"abstract":"<div><div>This research focuses on developing a navigation method for mobile robots to effectively avoid moving obstacles while accurately tracking a desired path. The approach introduces an enhanced velocity field that incorporates hydrodynamic theory tools. Initially designed for the 2D case, the method is subsequently extended to the 3D scenario by introducing vector field extensions and rotations.</div><div>To validate the proposed scheme, experiments are conducted using a UAV model tasked with tracking a circular contour. The control system employs two PD controllers for regulating the vertical position (<span><math><mi>z</mi></math></span>) and yaw angle (<span><math><mi>ψ</mi></math></span>), while the roll (<span><math><mi>ϕ</mi></math></span>) and pitch (<span><math><mi>θ</mi></math></span>) angles are controlled using a nested saturation method.</div><div>The numerical results demonstrate the successful achievement of the tracking objective, even when a moving obstacle crosses the reference path. Notably, this study considers the scenario where an obstacle approaches the vehicle from behind, which is often overlooked in similar investigations. This aspect is examined in both the 2D and 3D cases.</div><div>Subsequently, the proposed navigation method is tested on a quadrotor vehicle, yielding favorable results.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"186 ","pages":"Article 104907"},"PeriodicalIF":4.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review of compliant mechanisms for contact robotics applications

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2024-12-30 DOI: 10.1016/j.robot.2024.104902

Zahra Samadikhoshkho, Elliot Saive, Michael G. Lipsett

The challenge of effectively interacting with the environment is a huge obstacle in robotics that needs more attention and innovation. Contact missions, in particular, provide inherent challenges such as adaptability to dynamic environments and ensuring safe and reliable operation. Incorporating compliance into robots is a viable approach to address these challenges, and various methods for doing this are explored in detail in this review. Using compliant mechanisms (CM) is a method that offer a promising solution by providing inherent flexibility and compliance, enabling robots to interact with their environment more effectively. This article provides a comprehensive review on the role of compliant mechanisms in contact robotic applications. It also analyzes several types of these mechanisms, their design approaches, as well as modeling and control strategies.

引用次数: 0

Energy-aware multi-robot task scheduling using meta-heuristic optimization methods for ambiently-powered robot swarms

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2024-12-30 DOI: 10.1016/j.robot.2024.104898

Mohmmadsadegh Mokhtari , Parham Haji Ali Mohamadi , Michiel Aernouts , Ritesh Kumar Singh , Bram Vanderborght , Maarten Weyn , Jeroen Famaey

This paper presents a novel approach to address the challenges of energy-aware task scheduling in a collaborative swarm of robots equipped with energy-harvesting capabilities. With a primary focus on task execution timing, reliable task allocation, and efficient utilization of available energy resources, the task-scheduling process is approached with an energy-aware strategy. The developed architecture employs a centralized and autonomous approach that dynamically responds to a sequence-dependent setup time job shop scheduling demand. The proposed method incorporates energy consumption estimation, charging contingency approach, and energy harvesting prediction to minimize overall task execution time. The problem is optimized using Adaptive Particle Swarm Optimization and compared to other well-known meta-heuristic algorithms. A practical illustration of the proposed approach’s real-world utility is demonstrated through a case study scenario conducted within a heterogeneous pick-drop delivery setting inside a warehouse. The study was conducted utilizing the TurtelBot3 burger robot model within the Robotic Operating System and Gazebo simulation environment. Simulation results demonstrate the superiority of the energy-aware solution for multi-robot scheduling and task allocation problems over the energy-unaware methods by a 15 percent reduction in task completion time.

{"title":"Energy-aware multi-robot task scheduling using meta-heuristic optimization methods for ambiently-powered robot swarms","authors":"Mohmmadsadegh Mokhtari , Parham Haji Ali Mohamadi , Michiel Aernouts , Ritesh Kumar Singh , Bram Vanderborght , Maarten Weyn , Jeroen Famaey","doi":"10.1016/j.robot.2024.104898","DOIUrl":"10.1016/j.robot.2024.104898","url":null,"abstract":"<div><div>This paper presents a novel approach to address the challenges of energy-aware task scheduling in a collaborative swarm of robots equipped with energy-harvesting capabilities. With a primary focus on task execution timing, reliable task allocation, and efficient utilization of available energy resources, the task-scheduling process is approached with an energy-aware strategy. The developed architecture employs a centralized and autonomous approach that dynamically responds to a sequence-dependent setup time job shop scheduling demand. The proposed method incorporates energy consumption estimation, charging contingency approach, and energy harvesting prediction to minimize overall task execution time. The problem is optimized using Adaptive Particle Swarm Optimization and compared to other well-known meta-heuristic algorithms. A practical illustration of the proposed approach’s real-world utility is demonstrated through a case study scenario conducted within a heterogeneous pick-drop delivery setting inside a warehouse. The study was conducted utilizing the TurtelBot3 burger robot model within the Robotic Operating System and Gazebo simulation environment. Simulation results demonstrate the superiority of the energy-aware solution for multi-robot scheduling and task allocation problems over the energy-unaware methods by a 15 percent reduction in task completion time.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"186 ","pages":"Article 104898"},"PeriodicalIF":4.3,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sobol sequence RRT* and numerical optimal joint algorithm-based automatic parking trajectory planning of four-wheel steering vehicles

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2024-12-30 DOI: 10.1016/j.robot.2024.104909

Jiulong Yang , Junnian Wang , Jiajun Li , Xiangzhe Meng , Xingwei Jiang , Changgang Lu

Four-wheel steering can effectively improve turning agility and mitigate parking spatial requirement. Addressing the issues of low sampling point quality and poor efficiency in existing Rapidly-exploring Random Tree (RRT) and its improved algorithms for automatic parking assist (APA) system, a parking trajectory planning algorithm combining Sobol-RRT* with Reeds-Shepp curve and numerical optimal control within four-wheel steering kinematic model constraints is proposed in this paper to improve parking space utilization rate, cope with dynamic obstacles during parking process. First, the hierarchical framework of the proposed path planning algorithm is introduced, which is used as the basis of the planning algorithm, and the kinematics model of the four-wheel steering vehicle is established. Second, the pseudo-random sequences of RRT algorithm are replaced by Sobol sequences with uniform difference characteristics. Then, the parking trajectory planning problem is formulated with consideration of the system dynamic equation constraints based on the four-wheel steering kinematics model and the dynamic obstacle constraints based on the "triangular area method". Finally, the planned parking trajectory for the four-wheel steering vehicle is obtained by solving the optimal control problem and cubic spline curve fitting. Simulation in typical parking conditions validated the proposed planning algorithm on improvement of the APA system adaptability to challenging parking environment with dynamic obstacles.

{"title":"Sobol sequence RRT* and numerical optimal joint algorithm-based automatic parking trajectory planning of four-wheel steering vehicles","authors":"Jiulong Yang , Junnian Wang , Jiajun Li , Xiangzhe Meng , Xingwei Jiang , Changgang Lu","doi":"10.1016/j.robot.2024.104909","DOIUrl":"10.1016/j.robot.2024.104909","url":null,"abstract":"<div><div>Four-wheel steering can effectively improve turning agility and mitigate parking spatial requirement. Addressing the issues of low sampling point quality and poor efficiency in existing Rapidly-exploring Random Tree (RRT) and its improved algorithms for automatic parking assist (APA) system, a parking trajectory planning algorithm combining Sobol-RRT* with Reeds-Shepp curve and numerical optimal control within four-wheel steering kinematic model constraints is proposed in this paper to improve parking space utilization rate, cope with dynamic obstacles during parking process. First, the hierarchical framework of the proposed path planning algorithm is introduced, which is used as the basis of the planning algorithm, and the kinematics model of the four-wheel steering vehicle is established. Second, the pseudo-random sequences of RRT algorithm are replaced by Sobol sequences with uniform difference characteristics. Then, the parking trajectory planning problem is formulated with consideration of the system dynamic equation constraints based on the four-wheel steering kinematics model and the dynamic obstacle constraints based on the \"triangular area method\". Finally, the planned parking trajectory for the four-wheel steering vehicle is obtained by solving the optimal control problem and cubic spline curve fitting. Simulation in typical parking conditions validated the proposed planning algorithm on improvement of the APA system adaptability to challenging parking environment with dynamic obstacles.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"186 ","pages":"Article 104909"},"PeriodicalIF":4.3,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dexterous in-hand manipulation of slender cylindrical objects through deep reinforcement learning with tactile sensing

IF 4.3 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2024-12-30 DOI: 10.1016/j.robot.2024.104904

Wenbin Hu , Bidan Huang , Wang Wei Lee , Sicheng Yang , Yu Zheng , Zhibin Li

Continuous in-hand manipulation is an important physical interaction skill, where tactile sensing provides indispensable contact information to enable dexterous manipulation of objects. In this work, we propose a learning-based framework for dexterous in-hand manipulation that controls the pose of a thin cylindrical object, such as a long stick, to track various continuous trajectories, through multiple contacts of three fingertips of a dexterous robot hand with tactile sensor arrays. We extract the contact information between the stick and each fingertip from the high-dimensional tactile information and show that the robot can effectively learn a policy to achieve the task. The policies are trained with deep reinforcement learning in simulation and successfully transferred to real-world experiments, using coordinated model calibration and domain randomization. We compare the effectiveness of different types of tactile information and find out that the policies trained with contact center positions achieve best tracking results. The sim-to-real performances are validated through real-world experiments.

{"title":"Dexterous in-hand manipulation of slender cylindrical objects through deep reinforcement learning with tactile sensing","authors":"Wenbin Hu , Bidan Huang , Wang Wei Lee , Sicheng Yang , Yu Zheng , Zhibin Li","doi":"10.1016/j.robot.2024.104904","DOIUrl":"10.1016/j.robot.2024.104904","url":null,"abstract":"<div><div>Continuous in-hand manipulation is an important physical interaction skill, where tactile sensing provides indispensable contact information to enable dexterous manipulation of objects. In this work, we propose a learning-based framework for dexterous in-hand manipulation that controls the pose of a thin cylindrical object, such as a long stick, to track various continuous trajectories, through multiple contacts of three fingertips of a dexterous robot hand with tactile sensor arrays. We extract the contact information between the stick and each fingertip from the high-dimensional tactile information and show that the robot can effectively learn a policy to achieve the task. The policies are trained with deep reinforcement learning in simulation and successfully transferred to real-world experiments, using coordinated model calibration and domain randomization. We compare the effectiveness of different types of tactile information and find out that the policies trained with contact center positions achieve best tracking results. The sim-to-real performances are validated through real-world experiments.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"186 ","pages":"Article 104904"},"PeriodicalIF":4.3,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143095623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Robotics and Autonomous Systems

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀