Robotics and Autonomous Systems最新文献_第9页

Research on VSLAM algorithm based on landmark assistance 基于地标辅助的VSLAM算法研究

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-09 DOI: 10.1016/j.robot.2025.105289

Dianfan Zhang , Lei Zhou , Yu Rong , Xiaodi Wang , Yingfeng Wang , Junbo Wang

The rapid advancement of intelligent driving technology has enabled functions such as autonomous parking, adaptive cruise control, and lane-keeping, which rely on precise vehicle localization. However, traditional satellite-based positioning systems fail to provide accurate localization in complex environments such as tunnels and urban canyons. To overcome these limitations, Simultaneous Localization and Mapping (SLAM) combined with sensor technologies has been widely explored for high-precision localization. However, conventional SLAM methods in outdoor environments are often susceptible to interference from dynamic objects and sensor noise, leading to degraded localization accuracy. To address these challenges, this study proposes an improved localization framework that integrates YOLOv8 with ORB-SLAM2, utilizing detected road signs as robust feature points for enhanced vehicle localization. To mitigate false positives and missed detections in YOLOv8, we optimize the dataset, enhance the feature fusion network, and refine the loss function to improve object detection accuracy. Furthermore, an edge-feature-based point-matching algorithm is introduced to reduce feature point mismatches and improve localization precision. Experimental results on the Apollo Scape dataset and real-world scenarios demonstrate that the proposed approach significantly enhances localization accuracy in dynamic environments with abundant road signs, outperforming conventional SLAM methods.

智能驾驶技术的快速发展使自动泊车、自适应巡航控制、车道保持等功能得以实现，这些功能依赖于精确的车辆定位。然而，传统的卫星定位系统无法在隧道和城市峡谷等复杂环境中提供准确的定位。为了克服这些局限性，同时定位与地图绘制（SLAM）技术与传感器技术相结合的高精度定位技术得到了广泛的探索。然而，传统的SLAM方法在室外环境中容易受到动态物体和传感器噪声的干扰，导致定位精度下降。为了应对这些挑战，本研究提出了一种改进的定位框架，该框架将YOLOv8与ORB-SLAM2集成在一起，利用检测到的道路标志作为增强车辆定位的鲁棒特征点。为了减少YOLOv8中的误报和漏检，我们对数据集进行了优化，增强了特征融合网络，并改进了损失函数以提高目标检测精度。在此基础上，提出了一种基于边缘特征的点匹配算法，以减少特征点不匹配，提高定位精度。在Apollo Scape数据集和真实场景上的实验结果表明，该方法显著提高了道路标志丰富的动态环境下的定位精度，优于传统的SLAM方法。

{"title":"Research on VSLAM algorithm based on landmark assistance","authors":"Dianfan Zhang , Lei Zhou , Yu Rong , Xiaodi Wang , Yingfeng Wang , Junbo Wang","doi":"10.1016/j.robot.2025.105289","DOIUrl":"10.1016/j.robot.2025.105289","url":null,"abstract":"<div><div>The rapid advancement of intelligent driving technology has enabled functions such as autonomous parking, adaptive cruise control, and lane-keeping, which rely on precise vehicle localization. However, traditional satellite-based positioning systems fail to provide accurate localization in complex environments such as tunnels and urban canyons. To overcome these limitations, Simultaneous Localization and Mapping (SLAM) combined with sensor technologies has been widely explored for high-precision localization. However, conventional SLAM methods in outdoor environments are often susceptible to interference from dynamic objects and sensor noise, leading to degraded localization accuracy. To address these challenges, this study proposes an improved localization framework that integrates YOLOv8 with ORB-SLAM2, utilizing detected road signs as robust feature points for enhanced vehicle localization. To mitigate false positives and missed detections in YOLOv8, we optimize the dataset, enhance the feature fusion network, and refine the loss function to improve object detection accuracy. Furthermore, an edge-feature-based point-matching algorithm is introduced to reduce feature point mismatches and improve localization precision. Experimental results on the Apollo Scape dataset and real-world scenarios demonstrate that the proposed approach significantly enhances localization accuracy in dynamic environments with abundant road signs, outperforming conventional SLAM methods.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"198 ","pages":"Article 105289"},"PeriodicalIF":5.2,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037690","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

Multi-robot motion planning based on Nets-within-Nets modeling and simulation 基于Nets-within-Nets建模与仿真的多机器人运动规划

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-08 DOI: 10.1016/j.robot.2025.105287

Sofia Hustiu , Joaquín Ezpeleta , Cristian Mahulea , Marius Kloetzer

This paper focuses on designing motion plans for a heterogeneous team of robots that must cooperate to fulfill a global mission. Robots move in an environment that contains some regions of interest, while the specification for the entire team can include avoidance, visits, or sequencing of these regions of interest. The mission is expressed in terms of a Petri net corresponding to an automaton, while each robot is also modeled by a state machine Petri net. The current work brings about the following contributions with respect to existing solutions for related problems. First, we propose a novel model, denoted High-Level robot team Petri Net (HLrtPN) system, to incorporate the specification and robot models into the Nets-within-Nets paradigm. A guard function, named Global Enabling Function, is designed to synchronize the firing of transitions so that robot motions do not violate the specification. Then, the solution is found by simulating the HLrtPN system in a specific software tool that accommodates Nets-within-Nets. Illustrative examples based on Linear Temporal Logic missions support the computational feasibility of the proposed framework.

本文的重点是设计一个异质机器人团队的运动计划，这些团队必须合作完成一个全局任务。机器人在包含一些感兴趣区域的环境中移动，而整个团队的规范可以包括避免，访问或对这些感兴趣区域进行排序。任务用与自动机对应的Petri网表示，而每个机器人也由状态机Petri网建模。目前的工作对相关问题的现有解决方案带来了以下贡献。首先，我们提出了一个新的模型，称为高级机器人团队Petri网（HLrtPN）系统，将规范和机器人模型纳入nets - in- nets范式。一个名为Global Enabling function的保护函数被设计用来同步过渡的触发，这样机器人的运动就不会违反规范。然后，通过在一个特定的软件工具中模拟HLrtPN系统来找到解决方案，该软件工具可以容纳网中网。基于线性时序逻辑任务的实例验证了该框架的计算可行性。

{"title":"Multi-robot motion planning based on Nets-within-Nets modeling and simulation","authors":"Sofia Hustiu , Joaquín Ezpeleta , Cristian Mahulea , Marius Kloetzer","doi":"10.1016/j.robot.2025.105287","DOIUrl":"10.1016/j.robot.2025.105287","url":null,"abstract":"<div><div>This paper focuses on designing motion plans for a heterogeneous team of robots that must cooperate to fulfill a global mission. Robots move in an environment that contains some regions of interest, while the specification for the entire team can include avoidance, visits, or sequencing of these regions of interest. The mission is expressed in terms of a Petri net corresponding to an automaton, while each robot is also modeled by a state machine Petri net. The current work brings about the following contributions with respect to existing solutions for related problems. First, we propose a novel model, denoted <em>High-Level robot team Petri Net</em> (HLrtPN) system, to incorporate the specification and robot models into the Nets-within-Nets paradigm. A guard function, named <em>Global Enabling Function</em>, is designed to synchronize the firing of transitions so that robot motions do not violate the specification. Then, the solution is found by simulating the HLrtPN system in a specific software tool that accommodates Nets-within-Nets. Illustrative examples based on Linear Temporal Logic missions support the computational feasibility of the proposed framework.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105287"},"PeriodicalIF":5.2,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145737594","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

Real-time algorithm for table tennis with a desktop robotic arm 桌面机械臂乒乓球运动的实时算法

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-08 DOI: 10.1016/j.robot.2025.105288

Baptiste Toussaint, Maxime Raison

Table tennis with collaborative robots has been a challenge in robotics for decades, due to its unique challenges, especially high-speed movements and real-time ball trajectory predictions for responsive and accurate gameplay. Over the years, several table tennis robots have been developed, showing progressively enhanced abilities for returning balls, hitting specific targets, rallying with collaborative human users, and playing amateur-level games. However, these robotic systems remain costly for individuals, often relying on industrial components, or specialized designs. Emerging AI-integrated personal desktop robotic arms could help bridge the performance gap between affordable personal robotic systems and traditional industrial robots, particularly in terms of dexterity, speed, and precision. Despite this potential, desktop robotic arms have not yet been used for table tennis. However, existing table tennis algorithms require specific adaptations to accommodate the constraints of desktop robots. This paper aims to develop a dedicated algorithm for a collaborative table tennis system using a desktop robotic arm to demonstrate the achievable performance of AI-integrated desktop robots. The proposed system utilizes a 5-degree-of-freedom (DOF) serial robot, integrating advanced algorithms and machine learning models to improve performance. This system enables short collaborative rallies, returning 71.3% of balls overall, improving to 81.4% after fine-tuning system parameters — approaching the best one from the literature (88%) using a 7-DOF industrial robotic arm. This underscores the potential of affordable, AI-integrated desktop robotic arms for high-speed human–robot collaboration. Future works will focus on adapting the algorithm for specialized desktop hardware, expanding desktop robots to other applications, and further enhancing their performance.

几十年来，协作机器人的乒乓球运动一直是机器人技术的挑战，因为它具有独特的挑战，特别是高速运动和实时球轨迹预测，以响应和准确的游戏玩法。多年来，一些乒乓球机器人已经被开发出来，显示出越来越强的回球能力，击中特定的目标，与协作的人类用户团结在一起，玩业余水平的游戏。然而，这些机器人系统对个人来说仍然很昂贵，通常依赖于工业部件或专门的设计。新兴的集成人工智能的个人台式机器人手臂可以帮助弥合价格合理的个人机器人系统与传统工业机器人之间的性能差距，特别是在灵活性、速度和精度方面。尽管有这种潜力，台式机械臂还没有用于乒乓球。然而，现有的乒乓球算法需要特定的调整来适应桌面机器人的限制。本文旨在为使用桌面机械臂的协作乒乓球系统开发专用算法，以展示ai集成桌面机器人可实现的性能。该系统利用一个5自由度（DOF）串行机器人，集成了先进的算法和机器学习模型来提高性能。该系统可以实现短时间的协同反弹，总体回球率为71.3%，在微调系统参数后提高到81.4%，接近文献中使用7自由度工业机械臂的最佳回球率（88%）。这凸显了经济实惠、集成人工智能的台式机械臂在高速人机协作方面的潜力。未来的工作将集中在使算法适应专门的桌面硬件，将桌面机器人扩展到其他应用，并进一步提高其性能。

{"title":"Real-time algorithm for table tennis with a desktop robotic arm","authors":"Baptiste Toussaint, Maxime Raison","doi":"10.1016/j.robot.2025.105288","DOIUrl":"10.1016/j.robot.2025.105288","url":null,"abstract":"<div><div>Table tennis with collaborative robots has been a challenge in robotics for decades, due to its unique challenges, especially high-speed movements and real-time ball trajectory predictions for responsive and accurate gameplay. Over the years, several table tennis robots have been developed, showing progressively enhanced abilities for returning balls, hitting specific targets, rallying with collaborative human users, and playing amateur-level games. However, these robotic systems remain costly for individuals, often relying on industrial components, or specialized designs. Emerging AI-integrated personal desktop robotic arms could help bridge the performance gap between affordable personal robotic systems and traditional industrial robots, particularly in terms of dexterity, speed, and precision. Despite this potential, desktop robotic arms have not yet been used for table tennis. However, existing table tennis algorithms require specific adaptations to accommodate the constraints of desktop robots. This paper aims to develop a dedicated algorithm for a collaborative table tennis system using a desktop robotic arm to demonstrate the achievable performance of AI-integrated desktop robots. The proposed system utilizes a 5-degree-of-freedom (DOF) serial robot, integrating advanced algorithms and machine learning models to improve performance. This system enables short collaborative rallies, returning 71.3% of balls overall, improving to 81.4% after fine-tuning system parameters — approaching the best one from the literature (88%) using a 7-DOF industrial robotic arm. This underscores the potential of affordable, AI-integrated desktop robotic arms for high-speed human–robot collaboration. Future works will focus on adapting the algorithm for specialized desktop hardware, expanding desktop robots to other applications, and further enhancing their performance.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105288"},"PeriodicalIF":5.2,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738058","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

Adaptive path planning method for multi-AUVs in complex environments 复杂环境下多auv自适应路径规划方法

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-08 DOI: 10.1016/j.robot.2025.105290

Jianhao Wu , Chang Liu , Vladimir Filaretov , Dmitry Yukhimets

In modern marine scientific exploration, environmental protection, and resource investigation missions, autonomous underwater vehicles (AUV) have seen increasingly widespread applications. However, complex underwater environments present challenges such as multi-objective optimization conflicts and communication constraints, particularly in scenarios with high-density obstacles and dynamic ocean current disturbances. This paper proposes a Distributed Learning-Enhanced Double Deep Q-Network (DLE-DDQN) algorithm for adaptive path planning, integrating deep reinforcement learning with distributed collaborative optimization. The algorithm employs an improved Double Deep Q-Network (DDQN) architecture and a dynamically adaptive reward function. These components guide AUVs in path planning within unknown environments. Meanwhile, distributed learning mechanisms are leveraged to enhance training efficiency under limited communication bandwidth. Experimental results demonstrate that DLE-DDQN achieves an 18.7% improvement in task success rate, a 29.6% increase in path efficiency, and a 51.4% reduction in response time compared to traditional DDQN and Multi-Agent Deep Deterministic Policy Gradient (MADDPG) methods in high-obstacle-density scenarios. Through a cross-attention mechanism that fuses environmental perception with navigational states, the algorithm maintains path curvature stability with a standard deviation below 0.15 rad/m even under abrupt current disturbances. These results validate the algorithm’s robustness and real-time performance in unstructured dynamic environments, confirming its capability to overcome both static obstacles and current interference for rapid, precise path planning.

在现代海洋科学探测、环境保护和资源调查任务中，自主水下航行器（AUV）得到了越来越广泛的应用。然而，复杂的水下环境面临着多目标优化冲突和通信约束等挑战，特别是在高密度障碍物和动态洋流干扰的情况下。将深度强化学习与分布式协同优化相结合，提出了一种分布式学习增强双深度Q-Network （DLE-DDQN）自适应路径规划算法。该算法采用改进的双深度q网络（DDQN）结构和动态自适应的奖励函数。这些组件指导auv在未知环境中进行路径规划。同时，利用分布式学习机制，在有限的通信带宽下提高训练效率。实验结果表明，在高障碍密度场景下，与传统的DDQN和Multi-Agent Deep Deterministic Policy Gradient （MADDPG）方法相比，DLE-DDQN的任务成功率提高了18.7%，路径效率提高了29.6%，响应时间缩短了51.4%。通过融合环境感知和导航状态的交叉注意机制，即使在突发电流干扰下，该算法也能保持低于0.15 rad/m的路径曲率稳定性。这些结果验证了该算法在非结构化动态环境中的鲁棒性和实时性，证实了该算法能够克服静态障碍物和电流干扰，实现快速、精确的路径规划。

{"title":"Adaptive path planning method for multi-AUVs in complex environments","authors":"Jianhao Wu , Chang Liu , Vladimir Filaretov , Dmitry Yukhimets","doi":"10.1016/j.robot.2025.105290","DOIUrl":"10.1016/j.robot.2025.105290","url":null,"abstract":"<div><div>In modern marine scientific exploration, environmental protection, and resource investigation missions, autonomous underwater vehicles (AUV) have seen increasingly widespread applications. However, complex underwater environments present challenges such as multi-objective optimization conflicts and communication constraints, particularly in scenarios with high-density obstacles and dynamic ocean current disturbances. This paper proposes a Distributed Learning-Enhanced Double Deep Q-Network (DLE-DDQN) algorithm for adaptive path planning, integrating deep reinforcement learning with distributed collaborative optimization. The algorithm employs an improved Double Deep Q-Network (DDQN) architecture and a dynamically adaptive reward function. These components guide AUVs in path planning within unknown environments. Meanwhile, distributed learning mechanisms are leveraged to enhance training efficiency under limited communication bandwidth. Experimental results demonstrate that DLE-DDQN achieves an 18.7% improvement in task success rate, a 29.6% increase in path efficiency, and a 51.4% reduction in response time compared to traditional DDQN and Multi-Agent Deep Deterministic Policy Gradient (MADDPG) methods in high-obstacle-density scenarios. Through a cross-attention mechanism that fuses environmental perception with navigational states, the algorithm maintains path curvature stability with a standard deviation below 0.15 rad/m even under abrupt current disturbances. These results validate the algorithm’s robustness and real-time performance in unstructured dynamic environments, confirming its capability to overcome both static obstacles and current interference for rapid, precise path planning.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105290"},"PeriodicalIF":5.2,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145737592","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

Hybrid and trustworthy AI approach to anomaly detection in realistic human–robot collaboration scenarios 基于混合可信人工智能的人机协作异常检测方法

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-08 DOI: 10.1016/j.robot.2025.105286

Rafał Kozik , Szymon Buś , Jakub Główka , Aleksandra Pawlicka , Marek Pawlicki , Rafał Renk , Michał Choraś

DNN (Deep Neural Networks) have recently demonstrated superior performance in various difficult and challenging tasks, such as natural language processing (NLP) and computer vision (CV). However, the researchers often stress the need for more practical cognitive and reasoning abilities of ML systems. In contrast to DNN, symbolic machine learning demonstrates exceptional reasoning capabilities. It is an obvious and beneficial approach to hybridize these two research domains to merge the advantages of both methodologies in order to achieve neuro-symbolic learning systems that exhibit effective perception and reasoning capabilities. In this paper, the authors propose a neuro-symbolic approach for anomaly detection in a real human–robot collaboration scenario. The emphasis in our research is put on constrained and industrial environments where the so-called cobots assist humans in the assembly process. The proposed approach encompasses several symbolic programs which allow enforcing safety guidelines in the human–robot collaboration as well as make the neural system aware of the physical and environmental constraints. The experiments and the ablation studies show each symbolic program plays an important role and contributes to improved anomaly detection capabilities.

DNN（深度神经网络）最近在各种困难和具有挑战性的任务中表现出优异的性能，例如自然语言处理（NLP）和计算机视觉（CV）。然而，研究人员经常强调机器学习系统需要更实用的认知和推理能力。与深度神经网络相比，符号机器学习展示了卓越的推理能力。将这两个研究领域结合起来，融合两种方法的优势，以实现具有有效感知和推理能力的神经符号学习系统，是一种明显而有益的方法。在本文中，作者提出了一种在真实人机协作场景中进行异常检测的神经符号方法。我们的研究重点放在受限和工业环境中，所谓的协作机器人在装配过程中协助人类。提出的方法包括几个象征性的程序，这些程序允许在人机协作中执行安全指导方针，并使神经系统意识到物理和环境约束。实验和烧蚀研究表明，每个符号程序都发挥了重要作用，有助于提高异常检测能力。

{"title":"Hybrid and trustworthy AI approach to anomaly detection in realistic human–robot collaboration scenarios","authors":"Rafał Kozik , Szymon Buś , Jakub Główka , Aleksandra Pawlicka , Marek Pawlicki , Rafał Renk , Michał Choraś","doi":"10.1016/j.robot.2025.105286","DOIUrl":"10.1016/j.robot.2025.105286","url":null,"abstract":"<div><div>DNN (Deep Neural Networks) have recently demonstrated superior performance in various difficult and challenging tasks, such as natural language processing (NLP) and computer vision (CV). However, the researchers often stress the need for more practical cognitive and reasoning abilities of ML systems. In contrast to DNN, symbolic machine learning demonstrates exceptional reasoning capabilities. It is an obvious and beneficial approach to hybridize these two research domains to merge the advantages of both methodologies in order to achieve neuro-symbolic learning systems that exhibit effective perception and reasoning capabilities. In this paper, the authors propose a neuro-symbolic approach for anomaly detection in a real human–robot collaboration scenario. The emphasis in our research is put on constrained and industrial environments where the so-called cobots assist humans in the assembly process. The proposed approach encompasses several symbolic programs which allow enforcing safety guidelines in the human–robot collaboration as well as make the neural system aware of the physical and environmental constraints. The experiments and the ablation studies show each symbolic program plays an important role and contributes to improved anomaly detection capabilities.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105286"},"PeriodicalIF":5.2,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738061","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

Pseudo-kinematic trajectory control and planning of tracked vehicles 履带车辆伪运动学轨迹控制与规划

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-06 DOI: 10.1016/j.robot.2025.105282

Michele Focchi , Daniele Fontanelli , Davide Stocco , Riccardo Bussola , Luigi Palopoli

Tracked vehicles distribute their weight continuously over a large surface area (the tracks). This distinctive feature makes them the preferred choice for vehicles required to traverse soft and uneven terrain. From a robotics perspective, however, this flexibility comes at a cost: the complexity of modeling the system and the resulting difficulty in designing theoretically sound navigation solutions. In this paper, we aim to bridge this gap by proposing a framework for the navigation of tracked vehicles, built upon three key pillars. The first pillar comprises two models: a simulation model and a control-oriented model. The simulation model captures the intricate terramechanics dynamics arising from soil–track interaction and is employed to develop faithful digital twins of the system across a wide range of operating conditions. The control-oriented model is pseudo-kinematic and mathematically tractable, enabling the design of efficient and theoretically robust control schemes. The second pillar is a Lyapunov-based feedback trajectory controller that provides certifiable tracking guarantees. The third pillar is a portfolio of motion planning solutions, each offering different complexity-accuracy trade-offs. The various components of the proposed approach are validated through extensive simulations and experimental evaluations on two different robotic platforms, namely the MAXXII and the LIMO robots.

履带式车辆将其重量连续地分布在一个大的表面区域（履带）上。这种独特的特点使他们的首选车辆需要通过软和不平坦的地形。然而，从机器人的角度来看，这种灵活性是有代价的：系统建模的复杂性和设计理论上合理的导航解决方案的难度。在本文中，我们的目标是通过提出一个基于三个关键支柱的履带式车辆导航框架来弥合这一差距。第一个支柱包括两个模型：仿真模型和面向控制的模型。仿真模型捕获了由土壤-轨道相互作用引起的复杂的地形力学动力学，并用于在广泛的操作条件下开发系统的忠实数字孪生。面向控制的模型是伪运动学的，数学上易于处理，可以设计有效的和理论上鲁棒的控制方案。第二个支柱是基于lyapunov的反馈轨迹控制器，它提供了可验证的跟踪保证。第三个支柱是运动规划解决方案的组合，每个解决方案都提供不同的复杂性和准确性权衡。通过在两种不同的机器人平台（即MAXXII和LIMO机器人）上进行广泛的模拟和实验评估，验证了所提出方法的各个组成部分。

{"title":"Pseudo-kinematic trajectory control and planning of tracked vehicles","authors":"Michele Focchi , Daniele Fontanelli , Davide Stocco , Riccardo Bussola , Luigi Palopoli","doi":"10.1016/j.robot.2025.105282","DOIUrl":"10.1016/j.robot.2025.105282","url":null,"abstract":"<div><div>Tracked vehicles distribute their weight continuously over a large surface area (the tracks). This distinctive feature makes them the preferred choice for vehicles required to traverse soft and uneven terrain. From a robotics perspective, however, this flexibility comes at a cost: the complexity of modeling the system and the resulting difficulty in designing theoretically sound navigation solutions. In this paper, we aim to bridge this gap by proposing a framework for the navigation of tracked vehicles, built upon three key pillars. The first pillar comprises two models: a simulation model and a control-oriented model. The simulation model captures the intricate terramechanics dynamics arising from soil–track interaction and is employed to develop faithful digital twins of the system across a wide range of operating conditions. The control-oriented model is pseudo-kinematic and mathematically tractable, enabling the design of efficient and theoretically robust control schemes. The second pillar is a Lyapunov-based feedback trajectory controller that provides certifiable tracking guarantees. The third pillar is a portfolio of motion planning solutions, each offering different complexity-accuracy trade-offs. The various components of the proposed approach are validated through extensive simulations and experimental evaluations on two different robotic platforms, namely the MAXXII and the LIMO robots.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105282"},"PeriodicalIF":5.2,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738059","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

Incremental learning from virtual demonstrations and task composition for robotic manipulation 从虚拟演示和机器人操作任务组成的增量学习

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-06 DOI: 10.1016/j.robot.2025.105274

Giuseppe Rauso, Riccardo Caccavale, Alberto Finzi

Developing robotic manipulation capabilities that can be incrementally learned, composed, and transferred across platforms remains a significant challenge. In this work, we propose a modular framework that combines imitation learning from virtual demonstrations with reinforcement learning to incrementally train reusable manipulation primitives, which can be flexibly composed into structured tasks. These policies are learned in simplified virtual environments with a limited number of demonstrations and minimal assumptions about the robotic platform or object properties, promoting generality and cross-platform applicability. The learned primitives are also symbolically represented, enabling their reuse and composition through a Hierarchical Task Network (HTN) planning framework. We validate the framework in scenarios involving structured task generation and execution, combining learned and predefined primitives with realistic manipulators and objects. Experimental results demonstrate high success rates in both primitive and long-horizon tasks as well as effective policy transfer across different simulation environments. By integrating incremental skill acquisition with symbolic task composition, our approach provides a modular and scalable solution for adaptive robotic manipulation.

开发可以逐步学习、组合和跨平台转移的机器人操作功能仍然是一个重大挑战。在这项工作中，我们提出了一个模块化框架，将虚拟演示中的模仿学习与强化学习相结合，以增量训练可重用的操作原语，这些原语可以灵活地组成结构化任务。这些策略是在简化的虚拟环境中学习的，通过有限数量的演示和对机器人平台或对象属性的最小假设，提高了通用性和跨平台适用性。学习到的原语也用符号表示，使它们能够通过分层任务网络（HTN）规划框架进行重用和组合。我们在涉及结构化任务生成和执行的场景中验证了该框架，将学习到的和预定义的原语与现实的操作器和对象相结合。实验结果表明，该方法在原始任务和长视界任务中都有很高的成功率，并且在不同的仿真环境中都有有效的策略转移。通过将增量技能获取与符号任务组合相结合，我们的方法为自适应机器人操作提供了模块化和可扩展的解决方案。

{"title":"Incremental learning from virtual demonstrations and task composition for robotic manipulation","authors":"Giuseppe Rauso, Riccardo Caccavale, Alberto Finzi","doi":"10.1016/j.robot.2025.105274","DOIUrl":"10.1016/j.robot.2025.105274","url":null,"abstract":"<div><div>Developing robotic manipulation capabilities that can be incrementally learned, composed, and transferred across platforms remains a significant challenge. In this work, we propose a modular framework that combines imitation learning from virtual demonstrations with reinforcement learning to incrementally train reusable manipulation primitives, which can be flexibly composed into structured tasks. These policies are learned in simplified virtual environments with a limited number of demonstrations and minimal assumptions about the robotic platform or object properties, promoting generality and cross-platform applicability. The learned primitives are also symbolically represented, enabling their reuse and composition through a Hierarchical Task Network (HTN) planning framework. We validate the framework in scenarios involving structured task generation and execution, combining learned and predefined primitives with realistic manipulators and objects. Experimental results demonstrate high success rates in both primitive and long-horizon tasks as well as effective policy transfer across different simulation environments. By integrating incremental skill acquisition with symbolic task composition, our approach provides a modular and scalable solution for adaptive robotic manipulation.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105274"},"PeriodicalIF":5.2,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738124","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

The FriûlBot dataset: Experimental validation of an autonomous ground robot for vineyard 3D mapping fri<s:1> lbot数据集：葡萄园3D测绘自主地面机器人的实验验证

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-05 DOI: 10.1016/j.robot.2025.105283

Diego Tiozzo Fasiolo, Lorenzo Scalera, Eleonora Maset, Alessandro Gasparetto

In this paper, we present the FriûlBot open-source dataset, collected by an autonomous mobile robot for vineyard 3D mapping and monitoring. The dataset is designed to provide a reference testbed for the development and benchmarking of localization, mapping, and multi-sensor data fusion algorithms. It includes detailed information on the robot status, point clouds of the vineyard, and multispectral images, offering valuable resources for future research on autonomous robotic systems in agriculture. The mobile robot employed for the dataset acquisition is capable of autonomously navigating, reaching GNSS way points, and building a map of the canopy integrating geometric and multispectral data. The navigation and mapping approach proposed in this work is based on a SLAM algorithm that integrates multiple odometry sources, and is designed for agricultural environments with plants arranged in rows, e.g., vineyards and orchards. The performance of the proposed mobile robot and navigation approach are tested during an extensive experimental campaign in a vineyard of University of Udine (Italy). During the tests, the robot successfully navigates along several vineyard rows, building point clouds of the environment that are merged with data regarding multiple vegetation indexes. The experimental results confirm the reliability of the autonomous mobile robot and the potential of the proposed dataset to foster further advances in robotics for vineyard 3D mapping.

在本文中，我们展示了fri lbot开源数据集，该数据集由自主移动机器人收集，用于葡萄园3D测绘和监测。该数据集旨在为定位、制图和多传感器数据融合算法的开发和基准测试提供参考测试平台。它包括机器人状态的详细信息，葡萄园的点云和多光谱图像，为未来农业自主机器人系统的研究提供了宝贵的资源。用于数据采集的移动机器人能够自主导航，到达GNSS路径点，并结合几何和多光谱数据构建冠层地图。本文提出的导航和制图方法基于SLAM算法，该算法集成了多个里程计源，适用于植物成行排列的农业环境，例如葡萄园和果园。所提出的移动机器人和导航方法的性能在乌迪内大学（意大利）葡萄园的广泛实验活动中进行了测试。在测试过程中，机器人成功地沿着几行葡萄园进行导航，建立了与多个植被指数数据合并的环境点云。实验结果证实了自主移动机器人的可靠性，以及所提出的数据集的潜力，以促进葡萄园3D测绘机器人技术的进一步发展。

{"title":"The FriûlBot dataset: Experimental validation of an autonomous ground robot for vineyard 3D mapping","authors":"Diego Tiozzo Fasiolo, Lorenzo Scalera, Eleonora Maset, Alessandro Gasparetto","doi":"10.1016/j.robot.2025.105283","DOIUrl":"10.1016/j.robot.2025.105283","url":null,"abstract":"<div><div>In this paper, we present the FriûlBot open-source dataset, collected by an autonomous mobile robot for vineyard 3D mapping and monitoring. The dataset is designed to provide a reference testbed for the development and benchmarking of localization, mapping, and multi-sensor data fusion algorithms. It includes detailed information on the robot status, point clouds of the vineyard, and multispectral images, offering valuable resources for future research on autonomous robotic systems in agriculture. The mobile robot employed for the dataset acquisition is capable of autonomously navigating, reaching GNSS way points, and building a map of the canopy integrating geometric and multispectral data. The navigation and mapping approach proposed in this work is based on a SLAM algorithm that integrates multiple odometry sources, and is designed for agricultural environments with plants arranged in rows, e.g., vineyards and orchards. The performance of the proposed mobile robot and navigation approach are tested during an extensive experimental campaign in a vineyard of University of Udine (Italy). During the tests, the robot successfully navigates along several vineyard rows, building point clouds of the environment that are merged with data regarding multiple vegetation indexes. The experimental results confirm the reliability of the autonomous mobile robot and the potential of the proposed dataset to foster further advances in robotics for vineyard 3D mapping.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105283"},"PeriodicalIF":5.2,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738115","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

Efficient iterative proximal variational inference motion planning 高效迭代近变分推理运动规划

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-04 DOI: 10.1016/j.robot.2025.105267

Zinuo Chang , Hongzhe Yu , Patricio Vela , Yongxin Chen

We cast motion planning under uncertainty as a stochastic optimal control problem, where the optimal posterior distribution has an explicit form. To approximate this posterior, this work frames an optimization problem in the space of Gaussian distributions by solving a Variational Inference (VI) in the path distribution space. For linear-Gaussian stochastic dynamics, a proximal algorithm is proposed to solve for an optimal Gaussian proposal iteratively. The computational bottleneck is evaluating the gradients with respect to the proposal over a dense trajectory. To tackle this issue, the sparse planning factor graph and Gaussian Belief Propagation (GBP) are exploited, allowing for parallel computation of these gradients on Graphics Processing Units (GPUs). We term the novel paradigm the Parallel Gaussian Variational Inference Motion Planning (P-GVIMP). Building on the efficient algorithm for linear Gaussian systems, we then propose an iterative paradigm based on Statistical Linear Regression (SLR) techniques to solve planning problems for nonlinear stochastic systems, where the P-GVIMP serves as a sub-routine for the linearized time-varying system at each iteration. The proposed framework is validated on various robotic systems, demonstrating significant speed acceleration achieved by leveraging parallel computation and successful planning solutions for nonlinear systems under uncertainty. An open-sourced implementation is presented at https://github.com/hzyu17/VIMP.

我们将不确定条件下的运动规划作为一个随机最优控制问题，其中最优后验分布具有显式形式。为了近似这个后验，本工作通过解决路径分布空间中的变分推理（VI），在高斯分布空间中构建了一个优化问题。对于线性-高斯随机动力学，提出了一种迭代求解最优高斯方案的近端算法。计算瓶颈是在密集的轨迹上评估相对于提议的梯度。为了解决这个问题，利用稀疏规划因子图和高斯置信传播（GBP），允许在图形处理单元（gpu）上并行计算这些梯度。我们将这种新模式称为并行高斯变分推理运动规划（P-GVIMP）。在线性高斯系统高效算法的基础上，我们提出了一种基于统计线性回归（SLR）技术的迭代范式来解决非线性随机系统的规划问题，其中P-GVIMP在每次迭代中作为线性化时变系统的子程序。所提出的框架在各种机器人系统上进行了验证，表明通过利用并行计算和不确定性非线性系统的成功规划解决方案实现了显著的速度加速。在https://github.com/hzyu17/VIMP上提供了一个开源的实现。

{"title":"Efficient iterative proximal variational inference motion planning","authors":"Zinuo Chang , Hongzhe Yu , Patricio Vela , Yongxin Chen","doi":"10.1016/j.robot.2025.105267","DOIUrl":"10.1016/j.robot.2025.105267","url":null,"abstract":"<div><div>We cast motion planning under uncertainty as a stochastic optimal control problem, where the optimal posterior distribution has an explicit form. To approximate this posterior, this work frames an optimization problem in the space of Gaussian distributions by solving a Variational Inference (VI) in the path distribution space. For linear-Gaussian stochastic dynamics, a proximal algorithm is proposed to solve for an optimal Gaussian proposal iteratively. The computational bottleneck is evaluating the gradients with respect to the proposal over a dense trajectory. To tackle this issue, the sparse planning factor graph and Gaussian Belief Propagation (GBP) are exploited, allowing for parallel computation of these gradients on Graphics Processing Units (GPUs). We term the novel paradigm the <em>Parallel Gaussian Variational Inference Motion Planning (P-GVIMP)</em>. Building on the efficient algorithm for linear Gaussian systems, we then propose an iterative paradigm based on Statistical Linear Regression (SLR) techniques to solve planning problems for nonlinear stochastic systems, where the P-GVIMP serves as a sub-routine for the linearized time-varying system at each iteration. The proposed framework is validated on various robotic systems, demonstrating significant speed acceleration achieved by leveraging parallel computation and successful planning solutions for nonlinear systems under uncertainty. An open-sourced implementation is presented at <span><span>https://github.com/hzyu17/VIMP</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105267"},"PeriodicalIF":5.2,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685198","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

A hierarchical planning framework for self-assembly and self-reconfiguration of autonomous modular space robots 自主模块化空间机器人自组装与自重构的分层规划框架

IF 5.2 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Robotics and Autonomous Systems

Pub Date : 2025-12-03 DOI: 10.1016/j.robot.2025.105273

Zhen Huang , Yajie Cheng , Rongqiang Liu , Minghe Shan

Owing to the extreme conditions of the space environment and the difficulty of external intervention, autonomous modular robotic systems offer a viable solution for constructing structures in space through self-assembly and self-reconfiguration. This paper presents a comprehensive planning system designed for modular robot self-assembly and self-reconfiguration tasks in space. The proposed system consists of two hierarchical layers: a sequential path planning layer and a task and trajectory planning layer. At the sequential path planning layer, the self-assembly and self-reconfiguration tasks are formulated as time-varying online Multi-Agent Path Finding (MAPF) problems, and are effectively solved using the enhanced Time-Expanded Network (TEN) and Minimum-Cost Maximum-Flow (MCMF) algorithm to generate collision-free and efficient sequential paths. At the task and trajectory planning layer, robot tasks are automatically partitioned based on the connection status and motion characteristics, with corresponding dynamic models generated adaptively according to the current task state. A hybrid iterative Linear Quadratic Regulator (iLQR) algorithm is introduced to achieve rapid response and trajectory optimality while satisfying constraints on the joint angles, actuator torques, and interface forces. Simulations using the HexaFlipBot modular robot platform confirmed that the proposed planning approach can efficiently and accurately complete the construction and reconfiguration of typical structures in space.

由于空间环境的极端条件和外界干预的困难，自主模块化机器人系统通过自组装和自重构为空间结构的构建提供了可行的解决方案。针对模块化机器人在空间中的自组装和自重构任务，提出了一种综合规划系统。该系统由两个层次组成：顺序路径规划层和任务与轨迹规划层。在序列路径规划层，将自组装和自重构任务表述为时变在线多智能体寻路（MAPF）问题，并利用增强型时间扩展网络（TEN）和最小成本最大流量（MCMF）算法有效地求解，生成无碰撞、高效的序列路径。在任务和轨迹规划层，根据连接状态和运动特征自动划分机器人任务，并根据当前任务状态自适应生成相应的动态模型。提出了一种混合迭代线性二次型调节器（iLQR）算法，在满足关节角度、执行机构扭矩和界面力约束的情况下，实现了快速响应和轨迹优化。利用HexaFlipBot模块化机器人平台进行的仿真验证了所提出的规划方法能够高效、准确地完成空间中典型结构的构造和重构。

{"title":"A hierarchical planning framework for self-assembly and self-reconfiguration of autonomous modular space robots","authors":"Zhen Huang , Yajie Cheng , Rongqiang Liu , Minghe Shan","doi":"10.1016/j.robot.2025.105273","DOIUrl":"10.1016/j.robot.2025.105273","url":null,"abstract":"<div><div>Owing to the extreme conditions of the space environment and the difficulty of external intervention, autonomous modular robotic systems offer a viable solution for constructing structures in space through self-assembly and self-reconfiguration. This paper presents a comprehensive planning system designed for modular robot self-assembly and self-reconfiguration tasks in space. The proposed system consists of two hierarchical layers: a sequential path planning layer and a task and trajectory planning layer. At the sequential path planning layer, the self-assembly and self-reconfiguration tasks are formulated as time-varying online Multi-Agent Path Finding (MAPF) problems, and are effectively solved using the enhanced Time-Expanded Network (TEN) and Minimum-Cost Maximum-Flow (MCMF) algorithm to generate collision-free and efficient sequential paths. At the task and trajectory planning layer, robot tasks are automatically partitioned based on the connection status and motion characteristics, with corresponding dynamic models generated adaptively according to the current task state. A hybrid iterative Linear Quadratic Regulator (iLQR) algorithm is introduced to achieve rapid response and trajectory optimality while satisfying constraints on the joint angles, actuator torques, and interface forces. Simulations using the HexaFlipBot modular robot platform confirmed that the proposed planning approach can efficiently and accurately complete the construction and reconfiguration of typical structures in space.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"197 ","pages":"Article 105273"},"PeriodicalIF":5.2,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685203","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