Robotics and Autonomous Systems最新文献_第3页

An integrated framework for obstacle avoidance path planning and tracking of autonomous vehicles considering risk potential fields 考虑潜在风险场的自动驾驶汽车避障路径规划与跟踪集成框架

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-16 DOI: 10.1016/j.robot.2025.105153

Jinhua Zhang, Weilong Fu

引用次数: 0

Intelligent automated gesture planning for reconfigurable soft gripper system in food handling 食品处理中可重构软抓取系统的智能自动手势规划

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-16 DOI: 10.1016/j.robot.2025.105159

Yangfan Li , Jun Liu , Wenyu Liang , Jin Huat Low , Yadan Zeng , Chen-Hua Yeow , I-Ming Chen , Zhuangjian Liu

{"title":"Intelligent automated gesture planning for reconfigurable soft gripper system in food handling","authors":"Yangfan Li , Jun Liu , Wenyu Liang , Jin Huat Low , Yadan Zeng , Chen-Hua Yeow , I-Ming Chen , Zhuangjian Liu","doi":"10.1016/j.robot.2025.105159","DOIUrl":"10.1016/j.robot.2025.105159","url":null,"abstract":"<div><div>Soft grippers, that can mimic human fingers grasping objects, have emerged as a game-changer in the automated food service industry. Their flexibility and compliance enable them to handle various food items, regardless of size, shape, or stiffness, outperforming their rigid counterparts while maintaining cost-efficiency and greater adaptability. However, the working scenarios for soft grippers are also more complex and unpredictable, leading to a challenge in pre-programming the gesture and trajectory of the system. Current research on soft grippers primarily focuses on their compliance characteristics, which is effective for objects with characteristic features but faces challenges with cut food items. For such cut objects, both vertical friction and compliance play crucial roles in grasping, highlighting the need for a reconfigurable soft gripper system (RSGS) with multiple degrees of freedom actuators. To address these challenges, we introduce an intelligent automated gesture planning strategy for RSGSs with multiple degrees of freedom. Our proposed framework comprises five modules: Feature Engineering, which parameterizes and samples arbitrary polygon cross-sections of food items; Simulation, which automates the creation of numerical models in the design space, run and post-processing of simulation; GraspingFormer, which estimates reaction forces during grasping; AgentVAE, which uses a generative variational autoencoder to sample feasible grasping gestures in latent space; Planner, which identifies the optimized gestures by solving an inverse problem. This strategy can facilitate gesture planning when grasping a target object with a RSGS, to enhance the picking-up success rate. The proposed framework can potentially benefit food-handling-like tasks and expand the use of soft robots in real-world applications.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105159"},"PeriodicalIF":5.2,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144890758","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

Integration of linear extended state observer within proxy-based sliding mode control for a cable-driven aerial manipulator 基于代理的滑模控制中线性扩展状态观测器的集成

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-16 DOI: 10.1016/j.robot.2025.105161

Li Ding , Yong Yao , Mingyue Lu , Yangmin Li , Yaoyao Wang

引用次数: 0

Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning 混合表征学习和强化学习的动态复杂机器人运动规划

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-14 DOI: 10.1016/j.robot.2025.105167

Chengmin Zhou , Xin Lu , Jiapeng Dai , Xiaoxu Liu , Bingding Huang , Pasi Fränti

{"title":"Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning","authors":"Chengmin Zhou , Xin Lu , Jiapeng Dai , Xiaoxu Liu , Bingding Huang , Pasi Fränti","doi":"10.1016/j.robot.2025.105167","DOIUrl":"10.1016/j.robot.2025.105167","url":null,"abstract":"<div><div>Motion planning is the soul of robot decision making. Classical planning algorithms like graph search and reaction-based algorithms face challenges in cases of dense and dynamic obstacles. Deep learning algorithms generate suboptimal one-step predictions that cause many collisions. Reinforcement learning algorithms generate optimal or near-optimal time-sequential predictions. However, they suffer from slow convergence, suboptimal converged results, and unstable training. This paper introduces a hybrid algorithm for robotic motion planning: <em><u>l</u>ong short-term memory</em> (LSTM) and <u>s</u>kip connection for <u>a</u>ttention-based <u>d</u>iscrete <u>s</u>oft <u>a</u>ctor <u>c</u>ritic (LSA-DSAC). First, graph network (relational graph) and attention network (attention weight) interpret the environmental state for the learning of the discrete soft actor critic algorithm. The expressive power of attention network outperforms that of graph in our task by difference analysis of these two representation methods. However, attention based DSAC faces the problem of unstable training (vanishing gradient). Second, the skip connection method is integrated to attention based DSAC to mitigate unstable training and improve convergence speed. Third, LSTM is taken to replace the sum operator of attention weigh and eliminate unstable training by slightly sacrificing convergence speed at early-stage training. Experiments show that LSA-DSAC outperforms the state-of-the-art in training and most evaluations. Physical robots are also implemented and tested in the real world.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105167"},"PeriodicalIF":5.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144890753","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 enhanced autonomous counter-drone system with jamming and relative positioning capabilities 具有干扰和相对定位能力的增强型自主反无人机系统

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-14 DOI: 10.1016/j.robot.2025.105160

Nicolas Souli , Panayiotis Kolios , Georgios Ellinas

{"title":"An enhanced autonomous counter-drone system with jamming and relative positioning capabilities","authors":"Nicolas Souli , Panayiotis Kolios , Georgios Ellinas","doi":"10.1016/j.robot.2025.105160","DOIUrl":"10.1016/j.robot.2025.105160","url":null,"abstract":"<div><div>The rise of unlawful and unauthorized operations of unmanned aerial vehicles (UAVs) has led to the need for versatile counter-drone systems. In this work, an autonomous counter-drone system is developed (denoted as RPS-JS-DNN — relative positioning and simultaneous jamming system with deep neural network learning), where a pursuer drone employs algorithms for detection, tracking, and jamming a rogue drone in real-time. The proposed system incorporates wireless interception capabilities to jam the rogue drone, together with self-positioning for the pursuer drone by employing a relative positioning system methodology based on signals of opportunity fused with inertial measurements. The performance of the proposed system depends on the switching between the jamming and self-localization modules, essentially leading to a jamming duration and positioning accuracy trade-off. The overall objective is the maximization of the jamming module’s operation time, while also increasing the performance of the self-localization module. In the proposed system, a software-defined radio (SDR) is utilized, facilitating jamming and spectrum sweeping capabilities to realize the desired GPS disturbance and self-localization, respectively. A prototype system is developed, implemented, deployed, and tested over extensive field experiments, demonstrating its effectiveness to jam a rogue drone and also achieve relative navigation in a real-world environment under various parameter settings.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105160"},"PeriodicalIF":5.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893569","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

Swarm self-organized multi-heterogeneous target trapping based on the distribution of agent movement influence 基于agent运动影响分布的群体自组织多异构目标捕获

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-14 DOI: 10.1016/j.robot.2025.105158

Hanqiao Huang , Yuchen Zhou , Wei Yin , Bo Zhang

{"title":"Swarm self-organized multi-heterogeneous target trapping based on the distribution of agent movement influence","authors":"Hanqiao Huang , Yuchen Zhou , Wei Yin , Bo Zhang","doi":"10.1016/j.robot.2025.105158","DOIUrl":"10.1016/j.robot.2025.105158","url":null,"abstract":"<div><div>In existing swarm-based self-organized trapping algorithms, the majority of studies have concentrated on single-target or homogeneous multi-target scenarios within two-dimensional spaces, with limited attention paid to the spatial trapping of multiple heterogeneous targets in three-dimensional environments. The problem of enabling trapping agents to self-organize through mutual perception to trap multiple dispersed and evasive heterogeneous targets in three-dimensional space presents a novel and challenging research direction. To address this gap, this paper proposes a self-organized swarm trapping approach for multiple heterogeneous targets based on the distribution of agent movement influence. First, evaluation criteria for trapping success are established through the definition of nearest-distance and morphological indices. Then, a single-step movement distribution field is constructed based on the incremental motion of neighboring agents to represent the local movement tendencies of trapping agents. This field is used to infer the trapping requirements of heterogeneous targets and to develop a target selection strategy that integrates target demands, density fields, and inter-target distances. Subsequently, the trapping agents achieve a swarm-level self-organized trap in three-dimensional space through the combined effects of four virtual forces: density regulation, target attraction, inter-agent repulsion, and self-propulsion. The feasibility of the proposed method is demonstrated through both algorithmic analysis and simulation-based validation. Results show that even under conditions with minimal redundancy in the number of trapping agents, the proposed strategy can adaptively select heterogeneous targets and form stable trap configurations with high efficiency.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105158"},"PeriodicalIF":5.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144851960","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

3D point cloud-based 6D pose estimation using the pedicel morphological features of fruits and vegetables 基于果蔬花梗形态特征的三维点云6D位姿估计

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-13 DOI: 10.1016/j.robot.2025.105151

Yonghyun Park , Jeonghyeon Pak , Changjo Kim , Hyoung Il Son

{"title":"3D point cloud-based 6D pose estimation using the pedicel morphological features of fruits and vegetables","authors":"Yonghyun Park , Jeonghyeon Pak , Changjo Kim , Hyoung Il Son","doi":"10.1016/j.robot.2025.105151","DOIUrl":"10.1016/j.robot.2025.105151","url":null,"abstract":"<div><div>This study proposes a method to estimate the 6D pose of pedicels using the morphological features of fruits and vegetables. The pedicel, a critical element connecting fruits to their stems, significantly influences the precision and efficiency of agricultural harvesting robots. The proposed system employs 3D point cloud data obtained from RGB-D cameras, using differences in width and curvature to identify the location and orientation of the pedicel. A lightweight YOLOv8n-seg architecture is employed to detect fruits and vegetables, computing the local curvature to estimate pedicel positions. The experimental evaluations on tomatoes and <em>Cucumis melo</em> (<em>C. melo</em>) demonstrate the capability of the proposed system to handle diverse agricultural environments. For <em>C. melo</em>, the system achieved a precision of 0.927, recall of 0.809 and F1-score of 0.864. For tomatoes, precision and recall were both 0.837, resulting in an F1-score of 0.837. Positional errors along the <span><math><mi>x</mi></math></span>-, <span><math><mi>y</mi></math></span>- and <span><math><mi>z</mi></math></span>-axes averaged 1.34, 3.19 and 4.79 mm , respectively, for the <em>C. melo</em>, with corresponding root mean squared errors of 7.95, 5.46 and 5.13 mm. Orientational errors averaged 2.14°, 1.14°and -1.49°for <span><math><mi>ϕ</mi></math></span>, <span><math><mi>θ</mi></math></span> and <span><math><mi>ψ</mi></math></span>, respectively. Smoothing algorithms, including linear interpolation for translation and spherical linear interpolation for rotation, address positional and orientational instability, further enhancing trajectory precision. The system achieved real-time operation with a processing speed exceeding 20 fps with smoothing, making it suitable for dynamic agricultural tasks. The results highlight the robust performance of the system in accurately identifying and approaching pedicels, even in occluded or clustered conditions.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105151"},"PeriodicalIF":5.2,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144860516","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

Data-driven predictive control of nonholonomic robots based on a bilinear Koopman realization: Data does not replace geometry 基于双线性Koopman实现的非完整机器人数据驱动预测控制：数据不能取代几何

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-12 DOI: 10.1016/j.robot.2025.105156

Mario Rosenfelder , Lea Bold , Hannes Eschmann , Peter Eberhard , Karl Worthmann , Henrik Ebel

{"title":"Data-driven predictive control of nonholonomic robots based on a bilinear Koopman realization: Data does not replace geometry","authors":"Mario Rosenfelder , Lea Bold , Hannes Eschmann , Peter Eberhard , Karl Worthmann , Henrik Ebel","doi":"10.1016/j.robot.2025.105156","DOIUrl":"10.1016/j.robot.2025.105156","url":null,"abstract":"<div><div>Advances in machine learning and the growing trend towards effortless data generation in real-world systems have led to an increasing interest for data-inferred models and data-based control in robotics. It seems appealing to govern robots solely based on data, bypassing the traditional, more elaborate pipeline of system modeling through first-principles and subsequent controller design. One promising data-driven approach is the Extended Dynamic Mode Decomposition (EDMD) for control-affine systems, a system class which contains many vehicles and machines of immense practical importance including, e.g., typical wheeled mobile robots. EDMD can be highly data-efficient, computationally inexpensive, can deal with nonlinear dynamics as prevalent in robotics and mechanics, and has a sound theoretical foundation rooted in Koopman theory. On this background, this present paper examines how EDMD models can be integrated into predictive controllers for nonholonomic mobile robots. In addition to the conventional kinematic mobile robot, we also cover the complete data-driven control pipeline – from data acquisition to control design – when the robot is not treated in terms of first-order kinematics but in a second-order manner, allowing to account for actuator dynamics. Using only real-world measurement data, it is shown in both simulations and hardware experiments that the surrogate models enable high-precision predictive controllers in the studied cases. However, the findings raise significant concerns about purely data-centric approaches that overlook the underlying geometry of nonholonomic systems, showing that, for nonholonomic systems, some geometric insight seems necessary and cannot be easily compensated for with large amounts of data.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105156"},"PeriodicalIF":5.2,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144842862","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

Design and motion analysis of a simple screw driven in-pipe inspection robot base on adaptive variable pitch 基于自适应变螺距的简易螺杆管件检测机器人的设计与运动分析

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-11 DOI: 10.1016/j.robot.2025.105148

Jihua Yin , Xuemei Liu, Maokun Rui, Miao Yu

引用次数: 0

Trajectory tracking model predictive control for mobile robot based on deep Koopman operator modeling 基于深度Koopman算子建模的移动机器人轨迹跟踪模型预测控制

IF 5.2 2区计算机科学

Robotics and Autonomous Systems Pub Date : 2025-08-11 DOI: 10.1016/j.robot.2025.105152

Minan Tang , Yaqi Zhang , Shuyou Yu , Jinping Li , Kunxi Tang

{"title":"Trajectory tracking model predictive control for mobile robot based on deep Koopman operator modeling","authors":"Minan Tang , Yaqi Zhang , Shuyou Yu , Jinping Li , Kunxi Tang","doi":"10.1016/j.robot.2025.105152","DOIUrl":"10.1016/j.robot.2025.105152","url":null,"abstract":"<div><div>Trajectory tracking serves as a pivotal performance metric for mobile robot systems, and is crucial for improving the efficiency of robots. The intricate kinematic and dynamic properties of robot systems pose substantial challenges in achieving accurate modeling and effective control, which remain pressing issues within the current research domain. This study focuses on wheeled mobile robot, relying on the deep Koopman operator theory, combined with the extended state observer (ESO) and the adaptive predictive time domain self-triggered model predictive control (APST-MPC) method, to propose a data-driven solution for the trajectory tracking control issue of wheeled mobile robot under uncertain model parameters. Firstly, the dynamic model of the mobile robot is constructed by the deep Koopman operator method. Secondly, to counteract operational disturbances encountered by the robot, an ESO is designed for disturbance estimation and subsequent compensation within the controller. Thirdly, to reduce the computational load, APST-MPC is employed to enhance the trajectory tracking control of wheeled mobile robot. Ultimately, the efficacy of the proposed trajectory tracking controller is confirmed through simulation experiments. The simulation outcomes confirm the deep Koopman operator theory’s efficacy in establishing a robot model with considerable accuracy, the tracking error of the robot is reduced by 46.03% and the total number of triggering times of the system is reduced by more than 59.8% by the APST-MPC controller based on ESO compared with the MPC controller.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105152"},"PeriodicalIF":5.2,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144831180","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