Robotics and Autonomous Systems最新文献_第4页

RUMOR: Reinforcement learning for understanding a model of the real world for navigation in dynamic environments 谣言：用于理解动态环境中导航的现实世界模型的强化学习

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-23 DOI: 10.1016/j.robot.2025.105020

Diego Martinez-Baselga, Luis Riazuelo, Luis Montano

{"title":"RUMOR: Reinforcement learning for understanding a model of the real world for navigation in dynamic environments","authors":"Diego Martinez-Baselga, Luis Riazuelo, Luis Montano","doi":"10.1016/j.robot.2025.105020","DOIUrl":"10.1016/j.robot.2025.105020","url":null,"abstract":"<div><div>Autonomous navigation in dynamic environments is a complex but essential task for autonomous robots, with recent deep reinforcement learning approaches showing promising results. However, the complexity of the real world makes it infeasible to train agents in every possible scenario configuration. Moreover, existing methods typically overlook factors such as robot kinodynamic constraints, or assume perfect knowledge of the environment. In this work, we present RUMOR, a novel planner for differential-drive robots that uses deep reinforcement learning to navigate in highly dynamic environments. Unlike other end-to-end DRL planners, it uses a descriptive robocentric velocity space model to extract the dynamic environment information, enhancing training effectiveness and scenario interpretation. Additionally, we propose an action space that inherently considers robot kinodynamics and train it in a simulator that reproduces the real world problematic aspects, reducing the gap between the reality and simulation. We extensively compare RUMOR with other state-of-the-art approaches, demonstrating a better performance, and provide a detailed analysis of the results. Finally, we validate RUMOR’s performance in real-world settings by deploying it on a ground robot. Our experiments, conducted in crowded scenarios and unseen environments, confirm the algorithm’s robustness and transferability.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"191 ","pages":"Article 105020"},"PeriodicalIF":4.3,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887414","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

DualQuat-LOAM: LiDAR odometry and mapping parameterized on dual quaternions 双四元数：激光雷达里程计和映射参数化对偶四元数

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-22 DOI: 10.1016/j.robot.2025.105009

Edison P. Velasco-Sánchez , Luis F. Recalde , Guanrui Li , Francisco A. Candelas-Herias , Santiago T. Puente-Mendez , Fernando Torres-Medina

引用次数: 0

DAPTP: Distributed Awareness Planner using Time Potential for dynamic target search DAPTP：使用时间潜能进行动态目标搜索的分布式意识规划器

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-20 DOI: 10.1016/j.robot.2025.105010

Mingyang Li , Yuting Tao , Xiao Cao, Peng Lu

{"title":"DAPTP: Distributed Awareness Planner using Time Potential for dynamic target search","authors":"Mingyang Li , Yuting Tao , Xiao Cao, Peng Lu","doi":"10.1016/j.robot.2025.105010","DOIUrl":"10.1016/j.robot.2025.105010","url":null,"abstract":"<div><div>This paper tackles the challenge of using multiple robots to search for unknown dynamic targets in complex, large environments. As both the number of robots and environmental complexity increase, coordinating efficient distributed searches becomes more difficult. Previous methods define search as either exploration or utilizing an initial target distribution to accelerate the process. However, these methods fail to dynamically build or update the target distribution from scratch and overlook the differences between the already searched regions during the search. We propose DAPTP, a novel Distributed Awareness Planner using Time Potential for dynamic target search. At the core of DAPTP is the concept of the time potential map, which estimates the target distribution in the environment based on historical search information. The importance of the searched regions is distinguished based on their corresponding time potential. Building on this, the coverage and search direction for each robot is then planned by maximizing the change in time potential, ensuring that areas with the greatest potential variation receive prioritized attention. We conduct extensive experiments both in simulations and real-world scenarios. The results demonstrate that our approach significantly surpasses state-of-the-art methods in terms of reducing search steps and improving collective environmental awareness, area search rate, detected target number, and success rate. The source code is available at: <span><span>https://github.com/arclab-hku/DAPTP</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"191 ","pages":"Article 105010"},"PeriodicalIF":4.3,"publicationDate":"2025-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863444","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

Quadrotors’ perching on moving inclined surfaces using uncertainty tolerant planner and thrust regulation 基于不确定性容限规划和推力调节的四旋翼飞行器在运动斜面上的悬停

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-19 DOI: 10.1016/j.robot.2025.105011

Sensen Liu, Wenkang Hu, Zhaoying Wang, Wei Dong, Xinjun Sheng

{"title":"Quadrotors’ perching on moving inclined surfaces using uncertainty tolerant planner and thrust regulation","authors":"Sensen Liu, Wenkang Hu, Zhaoying Wang, Wei Dong, Xinjun Sheng","doi":"10.1016/j.robot.2025.105011","DOIUrl":"10.1016/j.robot.2025.105011","url":null,"abstract":"<div><div>Quadrotors with the ability to perch on moving inclined surfaces can save energy and extend their travel distance by leveraging ground vehicles. Achieving dynamic perching places high demands on the performance of trajectory planning and tracking control in SE(3). However, in the perching process, uncertainties in target prediction and tracking errors may cause trajectory planning failure. And, independent control of position and attitude is also difficult for underactuated quadrotors. To address these challenges, we first propose a trajectory planner that considers adaptation to uncertainties in target prediction and tracking errors. In the planner, waypoints are optimized using the average coverage of their reachable set over the uncertain target as a criterion. A real-time trajectory planner based on optimized waypoints is developed accordingly. Secondly, thrust regulation is also implemented in the terminal attitude tracking stage. Therefore, positions and velocities can be controlled simultaneously when a quadrotor’s attitudes are commanded to align with surfaces. Extensive simulation experiments demonstrate that our methods can improve the accuracy of terminal states under uncertainties. The success rate is approximately increased by 50% compared to the two-end planner without using thrust regulation. Perching on the rear window of a car is also achieved outdoors to validate the feasibility and practicality of our methods.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"191 ","pages":"Article 105011"},"PeriodicalIF":4.3,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874353","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

Evaluating the influence of UEXO-II on human performance: A torque and muscle level analysis 评估UEXO-II对人体性能的影响：扭矩和肌肉水平分析

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-17 DOI: 10.1016/j.robot.2025.105012

Tianyi Sun , Haoran Zhan , Zhenlei Chen , Qing Guo , Yao Yan

{"title":"Evaluating the influence of UEXO-II on human performance: A torque and muscle level analysis","authors":"Tianyi Sun , Haoran Zhan , Zhenlei Chen , Qing Guo , Yao Yan","doi":"10.1016/j.robot.2025.105012","DOIUrl":"10.1016/j.robot.2025.105012","url":null,"abstract":"<div><div>Despite the increasing prevalence of exoskeleton technology, the lack of standardized evaluation methods poses significant challenges. This study aims to comprehensively generate direct dynamic evaluation indicators regarding the impact of the UEXO-II exoskeleton technology on human performance, with a focus on both torque and muscle levels. By inverse dynamics analysis based on identified parameters and optimization-based muscle force estimation techniques, we directly elucidate the effects of exoskeleton on human joint torque generation and muscle force exertion. Furthermore, this study investigates the influence of variations in motion frequency and exoskeleton controller parameters on human performance outcomes through statistical analysis at both torque and muscle levels. This contributes to the discussion on the optimal control of exoskeletons for movements at different frequencies. Results of this study indicate that both joint torque and muscle force varies, with some phases of the motion sequence being laborious and others being effortless, following exoskeleton utilization. Notably, the motion frequency and parameters of the exoskeleton controller emerge as influential factors, significantly impacting human energy consumption and muscular strength both under without and with exoskeleton conditions. This study holds promise as an effective method for evaluating performance of UEXO-II.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"191 ","pages":"Article 105012"},"PeriodicalIF":4.3,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863446","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

Robust AUV navigation with non-Gaussian noise: Enhanced UKF with Maximum Correntropy and M-estimation methods 非高斯噪声下的鲁棒AUV导航：基于最大相关熵和m估计方法的增强UKF

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-15 DOI: 10.1016/j.robot.2025.105007

Xiaona Sun , PinChi Li , Jiaming Zhang , Ziyun Chen , Bo He

{"title":"Robust AUV navigation with non-Gaussian noise: Enhanced UKF with Maximum Correntropy and M-estimation methods","authors":"Xiaona Sun , PinChi Li , Jiaming Zhang , Ziyun Chen , Bo He","doi":"10.1016/j.robot.2025.105007","DOIUrl":"10.1016/j.robot.2025.105007","url":null,"abstract":"<div><div>Unscented Kalman Filter (UKF) is widely used in autonomous underwater vehicle (AUV) underwater navigation. The minimum mean square error (MMSE) criterion is the main optimization metric of UKF, which exhibits excellent performance under Gaussian noise assumption. However, the performance degrades drastically when the Doppler Velocity Log (DVL) measurement system is characterized by heavy-tailed noise. For this reason, this paper proposes two Student’s T-distribution kernel-based Maximum Correntropy Unscented Kalman variants, referred to as MCSTUKF and STUKF, respectively, which are processed using both linear and nonlinear regression models. Despite the integration of higher-order statistics in the Maximum Correntropy Criterion (MCC), residual errors caused by extremely large outliers in the DVL measurements can still exist, so this paper couples four M-estimation methods to further improve the performance of the variants by adjusting the noise weights and truncating the measurements. Notably, these innovative UKF filters are real-time in nature, validated by simulations and Sailfish 260 AUV sea trial date.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"192 ","pages":"Article 105007"},"PeriodicalIF":4.3,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144090300","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

Predicting elbow motion intention based on different electromyography and inertial measurement unit sensor fusion structure 基于不同肌电和惯性测量单元传感器融合结构预测肘关节运动意图

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-15 DOI: 10.1016/j.robot.2025.105029

Hye-Won Oh , Jin-Woo Kang , Young-Dae Hong

{"title":"Predicting elbow motion intention based on different electromyography and inertial measurement unit sensor fusion structure","authors":"Hye-Won Oh , Jin-Woo Kang , Young-Dae Hong","doi":"10.1016/j.robot.2025.105029","DOIUrl":"10.1016/j.robot.2025.105029","url":null,"abstract":"<div><div>As information on motion intention prediction methods, bioelectrical and physical signals have been commonly used. However, both types of signals have opposing weaknesses and strengths. To compensate for these limitations, many studies have fused and utilized both signal types, but they have rarely discussed how to fuse them in terms of input/output structure, despite the significant impact of such discussion on prediction performance. Therefore, in this study, we designed and analyzed various sensor fusion structures using electromyography (EMG), one of the bioelectrical signals, and inertial measurement unit (IMU) signal, one of the physical signals, and then determined an optimal structure for using in our prediction model. To predict future motion intention in advance, the concept of the response time difference between EMG and IMU signals was employed in artificial neural network (ANN) training. Various experiments with a simple motion and two various motion scenarios were conducted with three subjects to verify the effectiveness and robustness of the proposed method. The results show that proposed method can predict future elbow angles with high accuracy and performance consistency across all subjects. Furthermore, these results allow joint angle synchronization of robot and human, and consequently reduce the discomfort of the subject from a muscle usage perspective.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"191 ","pages":"Article 105029"},"PeriodicalIF":4.3,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848053","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

Human-inspired dynamic obstacle and inter-collision avoidance algorithm for humanoid biped robots 仿人两足机器人的动态障碍与避碰算法

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-13 DOI: 10.1016/j.robot.2025.105023

Abhishek Kumar Kashyap , Dayal Parhi

{"title":"Human-inspired dynamic obstacle and inter-collision avoidance algorithm for humanoid biped robots","authors":"Abhishek Kumar Kashyap , Dayal Parhi","doi":"10.1016/j.robot.2025.105023","DOIUrl":"10.1016/j.robot.2025.105023","url":null,"abstract":"<div><div>In order to maximize humanoid robot navigation, this paper introduces the Enhanced DAYANI Arc Contour Intelligent (EDACI) Method, which integrates Dynamic Window Approach (DWA) to choose the best walking parameters for avoiding obstacles and smooth trajectory management. EDACI algorithm provides the best response to guide humanoid robots to the goal by avoiding obstacles and preparing a smooth trajectory. Further, DWA optimizes the walking pattern of humanoid robots by controlling their velocity while encountering an obstacle and finding a smooth trajectory. The performance of the proposed controller is examined by implementing it in humanoid NAOs for navigation in several simulated and experimental terrains. It is implemented on a single humanoid robot for navigation in static and dynamic environments and on multiple humanoid robots on a single platform. Navigation of multiple robots has to deal with the situation of conflict where one robot behaves as a dynamic obstacle to the other. It is solved by setting a Dining Philosopher Controller (DPC) in the base technique. The results obtained from the simulations and experiments have a divergence below 5 %, which demonstrates a satisfactory relation between them. The proposed controller's efficacy is demonstrated by comparing the torque developed at different joints with contrast to the inbuilt controller of NAO. The results show good improvement in torque produced at all joints. In addition, it is compared with an existing controller for navigation, which displays superiority of the proposed controller.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"191 ","pages":"Article 105023"},"PeriodicalIF":4.3,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848054","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

An underactuated gripper design and evaluation with linkage-based system for a front approach 基于连杆系统的欠驱动夹持器设计与评估

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-12 DOI: 10.1016/j.robot.2025.105005

Jeongseok Choi, Jeeho Won, Wonhyoung Lee, TaeWon Seo

引用次数: 0

Unified Vertex Motion Estimation for integrated video stabilization and stitching in tractor–trailer wheeled robots 牵引-拖车轮式机器人视频稳定与拼接的统一顶点运动估计

IF 4.3 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-04-11 DOI: 10.1016/j.robot.2025.105004

Hao Liang , Zhipeng Dong , Hao Li , Yufeng Yue , Mengyin Fu , Yi Yang

{"title":"Unified Vertex Motion Estimation for integrated video stabilization and stitching in tractor–trailer wheeled robots","authors":"Hao Liang , Zhipeng Dong , Hao Li , Yufeng Yue , Mengyin Fu , Yi Yang","doi":"10.1016/j.robot.2025.105004","DOIUrl":"10.1016/j.robot.2025.105004","url":null,"abstract":"<div><div>Tractor–trailer wheeled robots need to perform comprehensive perception tasks to enhance their operations in areas such as logistics parks and long-haul transportation. The perception of these robots faces three major challenges: the asynchronous vibrations between the tractor and trailer, the relative pose change between the tractor and trailer, and the significant camera parallax caused by the large size. In this paper, we employ the Dual Independence Stabilization Motion Field Estimation method to address asynchronous vibrations between the tractor and trailer, effectively eliminating conflicting motion estimations for the same object in overlapping regions. We utilize the Random Plane-based Stitching Motion Field Estimation method to tackle the continuous relative pose changes caused by the articulated hitch between the tractor and trailer, thus eliminating dynamic misalignment in overlapping regions. Furthermore, we apply the Unified Vertex Motion Estimation method to manage the challenges posed by the tractor–trailer’s large physical size, which results in severely low overlapping regions between the tractor and trailer views, thus preventing distortions in overlapping regions from exponentially propagating into non-overlapping areas. Furthermore, this framework has been successfully implemented in real tractor–trailer wheeled robots. The proposed Unified Vertex Motion Video Stabilization and Stitching method has been thoroughly tested in various challenging scenarios, demonstrating its accuracy and practicality in real-world robot tasks. The code is available at <span><span>https://github.com/lhlawrence/UVM-VSS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"191 ","pages":"Article 105004"},"PeriodicalIF":4.3,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838986","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