Robotics and Autonomous Systems最新文献

{"title":"A port water navigation solution based on priority sampling SAC: Taking Yantai port environment as an example","authors":"Yiming Zhao ,&nbsp;Fenglei Han ,&nbsp;Duanfeng Han ,&nbsp;Xiao Peng ,&nbsp;Wangyuan Zhao ,&nbsp;Guihua Xia","doi":"10.1016/j.robot.2025.104956","DOIUrl":"10.1016/j.robot.2025.104956","url":null,"abstract":"<div><div>Navigating port waters is challenging due to obstacles and regulated buoys, making traditional algorithms insufficient. Maritime Autonomous Surface Ships (MASS) must comply with strict International Association of Marine Aids and Lighthouse Authorities (IALA) regulations. This study presents an innovative navigation system integrated into an intelligent research ship, utilizing a Soft Actor-Critic (SAC) approach for decision-making. We train a navigation model in a custom Unity3D simulation that includes the IALA buoy system, employing a novel prioritization method to improve sample efficiency. Results show effective navigation in simulated environments, validated by real-ship testing at Yantai Port. This research enhances port navigation strategies and promotes the intellectualization of maritime operations by improving onboard decision-making and information processing.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"188 ","pages":"Article 104956"},"PeriodicalIF":4.3,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548656","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}

{"title":"Development of a new path-planning algorithm for lattice based self-reconfigurable modular robots with pivoting cube shaped modules","authors":"Halil İbrahim Dokuyucu ,&nbsp;Nurhan Gürsel Özmen","doi":"10.1016/j.robot.2025.104955","DOIUrl":"10.1016/j.robot.2025.104955","url":null,"abstract":"<div><div>In this study, a new path-planning algorithm named “Jellyfish Pump Algorithm (JPA)” for the self-reconfiguration of lattice-based self-reconfigurable modular robots (SRMRs) is presented. The JPA is inspired by the shape changing behavior of a jellyfish during its motion. This motion always satisfies the structural balance of the jellyfish with the help of adaptable and periodic shape changing actions. The proposed approach tries to confirm a physically balanced transformation process of the SRMRs considering external effects such as the gravity. The aim is to conserve the balance by employing a static plus shaped core structure of the robot body during the self-reconfiguration. The mobile modules are allowed to move around this core structure between initial and final configurations. The pivoting cube model is used as the abstraction method of the introduced algorithm. The comparison between pivoting and sliding cube models is presented considering actual world implementation aspects of SRMRs. The JPA is developed as a modification to the well-known self-reconfiguration algorithm of Melt Sort Grow. The JPA allows the robot to reach the final configuration by melting the initial configuration into a balanced intermediate phase having a plus shaped structure instead of a line configuration. The physical balance of the robot is satisfied at each step of the self-reconfiguration process. Appropriate simulations using generic 3D initial configurations have validated the proposed algorithm. Extreme cases such as locomotion and bridge formation are tested with the proposed algorithm considering the robustness and applicability. The time complexity of the JPA is <span><math><mrow><mi>O</mi><mo>(</mo><msup><mrow><mi>n</mi></mrow><mn>2</mn></msup><mo>)</mo></mrow></math></span> for <span><math><mi>n</mi></math></span> modules, whereas the balance restrictions enforce the algorithm to generate number of moves less than the square of number of mobile modules. The proposed algorithm was compared with a validated Melt Sort Grow algorithm considering number of moves and time complexity, and the efficiency of the algorithm was verified.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"188 ","pages":"Article 104955"},"PeriodicalIF":4.3,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548655","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}

{"title":"End2end vehicle multitask perception in adverse weather","authors":"Yifan Dai,&nbsp;Qiang Wang","doi":"10.1016/j.robot.2025.104945","DOIUrl":"10.1016/j.robot.2025.104945","url":null,"abstract":"<div><div>In the research of autonomous driving technology, due to the lack of datasets for various extreme weather conditions, autonomous driving perception in adverse weather is a challenge. To address this problem, this paper introduces an end-to-end multi-task perception system that combines labeled supervised learning and unsupervised domain adaptive learning for bad weather. The key innovations of this system include: a multi-task learning framework that simultaneously handles object detection, lane line detection, and drivable area detection, improving both efficiency and cost-effectiveness for autonomous driving in complex environments; a domain adaptation strategy using unlabeled data for adverse weather, which enables the system to perform robustly without requiring specific labels for harsh weather conditions; the system has strong generalization ability, demonstrated by achieving an prediction mAP of 83.86%, a drivable area mIoU of 91.59%, and lane detection accuracy of 83.9% on the BDD100K dataset, as well as an mAP of 74.85% on the Cityscapes fog dataset without additional training, highlighting its effectiveness in unseen, adverse conditions. The scalable and generalized solution provided in this paper can achieve high-performance navigation in various extreme environments. By combining supervised and unsupervised learning techniques, this model can not only cope with severe weather but also further generalize to unseen scenarios.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"188 ","pages":"Article 104945"},"PeriodicalIF":4.3,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511260","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}

{"title":"Fault tolerant position control of soft bending actuator in the presence of actuator leakage","authors":"Sina Rabiei ,&nbsp;Sajad Sadeghi Nalkenani ,&nbsp;Iman Sharifi ,&nbsp;Heidar Ali Talebi","doi":"10.1016/j.robot.2025.104944","DOIUrl":"10.1016/j.robot.2025.104944","url":null,"abstract":"<div><div>This paper introduces a new control strategy for soft robots in the presence of faults, using a nonlinear fault observer and an Adaptive Sliding Mode Controller (ASMC). Some soft robots use bending pneumatic actuators, which leads to higher adaptability and compliance as compared to those of rigid robots. However, their performance and reliability can be significantly affected by faults, especially punctures in the silicone tissue. The fault observer estimates the magnitude of these faults in the system, which is then used as an auxiliary input in the controller. At the same time, the ASMC is used to maintain the performance and stability of the soft robot in various tasks, such as tracking a desired trajectory. The effectiveness of the proposed method is demonstrated through simulations on a double-section soft bending pneumatic actuator made from silicone. The results show better fault tolerance and control performance as compared to traditional PID controllers or methods that do not employ a fault observer.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"188 ","pages":"Article 104944"},"PeriodicalIF":4.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510675","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}

{"title":"Robust adaptive control for aggressive quadrotor maneuvers via SO(3) and backstepping techniques","authors":"Weibin Gu ,&nbsp;Stefano Primatesta ,&nbsp;Alessandro Rizzo","doi":"10.1016/j.robot.2025.104942","DOIUrl":"10.1016/j.robot.2025.104942","url":null,"abstract":"<div><div>For decades, a number of nonlinear control methodologies such as backstepping control and model predictive control have been studied to guarantee the stability and performance of systems under control. Most of these designs were based on local coordinates like Euler angles or quaternions, coming with inherent limitations such as singularities and unwinding phenomena, thereby hindering practical applications where large angle rotational maneuvers are commanded. In this paper, we propose a novel adaptive geometric tracking controller based on the logarithmic map of <span><math><mrow><mi>SO</mi><mrow><mo>(</mo><mn>3</mn><mo>)</mo></mrow></mrow></math></span>, the special orthogonal group, for aggressive maneuvers of a quadrotor subject to uncertain mass and inertia matrix. By directly synthesizing control laws on <span><math><mrow><mi>SO</mi><mrow><mo>(</mo><mn>3</mn><mo>)</mo></mrow></mrow></math></span>, issues raised by local coordinates can be circumvented. Furthermore, we provide theoretical proofs establishing asymptotic tracking and the boundedness of all signals in the closed-loop system. We enhance robustness by applying projection operators to adaptive laws, addressing nonparametric uncertainties like sensor noise. Through simulation, our proposed controller outperforms prior geometric controllers in tracking aggressive trajectories, particularly excelling in the face of uncertainties.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"188 ","pages":"Article 104942"},"PeriodicalIF":4.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510674","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}

{"title":"Adaptive learning-based model predictive control strategy for drift vehicles","authors":"Bei Zhou ,&nbsp;Cheng Hu ,&nbsp;Jun Zeng ,&nbsp;Zhouheng Li ,&nbsp;Johannes Betz ,&nbsp;Lei Xie ,&nbsp;Hongye Su","doi":"10.1016/j.robot.2025.104941","DOIUrl":"10.1016/j.robot.2025.104941","url":null,"abstract":"<div><div>Drift vehicle control offers valuable insights to support safe autonomous driving in extreme conditions, which hinges on tracking a particular path while maintaining the vehicle states near the drift equilibrium points (DEP). However, conventional tracking methods are not adaptable for drift vehicles due to their opposite steering angle and yaw rate. In this paper, we propose an adaptive path tracking (APT) control method to dynamically adjust drift states to follow the reference path, improving the commonly utilized predictive path tracking methods with released computation burden. Furthermore, existing control strategies necessitate a precise system model to calculate the DEP, which can be more intractable due to the highly nonlinear drift dynamics and sensitive vehicle parameters. To tackle this problem, an adaptive learning-based model predictive control (ALMPC) strategy is proposed based on the APT method, where an upper-level Bayesian optimization is employed to learn the DEP and APT control law to instruct a lower-level MPC drift controller. This hierarchical system architecture can also resolve the inherent control conflict between path tracking and drifting by separating these objectives into different layers. The ALMPC strategy is verified on the Matlab-Carsim platform, and simulation results demonstrate its effectiveness in controlling the drift vehicle to follow a clothoid-based reference path even with the misidentified road friction parameter.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"188 ","pages":"Article 104941"},"PeriodicalIF":4.3,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463548","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}

{"title":"Leveraging motion perceptibility and deep reinforcement learning for visual control of nonholonomic mobile robots","authors":"Takieddine Soualhi,&nbsp;Nathan Crombez,&nbsp;Alexandre Lombard,&nbsp;Yassine Ruichek,&nbsp;Stéphane Galland","doi":"10.1016/j.robot.2025.104920","DOIUrl":"10.1016/j.robot.2025.104920","url":null,"abstract":"<div><div>This paper introduces a novel deep reinforcement learning framework to tackle the problem of visual servoing of nonholonomic mobile robots. The visual control of nonholonomic mobile robots becomes particularly challenging within the classical paradigm of visual servoing, mainly due to motion and visibility constraints, which makes it impossible to reach a given desired pose for certain configurations without losing essential visual information from the camera field of view. Previous work has demonstrated the effectiveness of deep reinforcement learning in addressing various vision-based robotics tasks. In light of this, we propose a framework that integrates deep recurrent policies, intrinsic motivation, and a novel auxiliary task that leverages the interaction matrix, the core of classical visual servoing approaches, to address the problem of vision-based control of nonholonomic robotic systems. Firstly, we analyze the influence of the nonholonomic constraints on control policy learning. Subsequently, we validate and evaluate our approach in both simulated and real-world environments. Our approach exhibits an emergent control behavior that enables the robot to accurately attain the desired pose while maintaining the desired visual content within the camera’s field of view. The proposed method outperforms the state-of-the-art approaches, demonstrating its effectiveness, robustness, and accuracy.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"189 ","pages":"Article 104920"},"PeriodicalIF":4.3,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143580444","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}

{"title":"Enhancing free-space transparency with discrete energy-based compensation in physical human–robot interaction","authors":"Seung Ho Lee,&nbsp;Ji Min Baek,&nbsp;Hyungpil Moon,&nbsp;Hyouk Ryeol Choi,&nbsp;Ja Choon Koo","doi":"10.1016/j.robot.2025.104940","DOIUrl":"10.1016/j.robot.2025.104940","url":null,"abstract":"<div><div>In physical human–robot interaction (pHRi), free-space transparency reflects how accurately a robot interprets and follows human motion intentions. This paper presents a novel discrete energy-based compensator designed to enhance transparency by leveraging an admittance controller that requires real-time input compensation. Transparency, defined as the work performed by interaction forces per unit distance, is improved by analyzing human dynamics to minimize interaction forces linked to transparency. The proposed compensator incorporates time delay control to compute necessary real-time compensation based on interactions between human and robot dynamics represented by admittance parameters. The method was validated through simulations and experiments on a physical robot system, demonstrating its effectiveness in enhancing transparency while addressing practical limitations. This study emphasizes the importance of dynamic analysis in pHRi and proposes a cost-effective approach to compensate for both interaction and robot dynamics.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"187 ","pages":"Article 104940"},"PeriodicalIF":4.3,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429581","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}

{"title":"Background suppression and comprehensive prototype pyramid distillation for few-shot object detection","authors":"Ning Li ,&nbsp;Mingliang Wang ,&nbsp;Gaochao Yang ,&nbsp;Bo Li ,&nbsp;Baohua Yuan ,&nbsp;Shoukun Xu ,&nbsp;Jun Qi","doi":"10.1016/j.robot.2025.104938","DOIUrl":"10.1016/j.robot.2025.104938","url":null,"abstract":"<div><div>Few-Shot Object Detection (FSOD) methods can achieve detection of novel classes with only a small number of annotated samples and have received widespread attention in recent years. Meta-learning has been proven to be a key technology for addressing few-shot problems. Typically, meta-learning-based methods require an additional support branch to extract class prototypes for the few-shot classes, and the detection head performs classification and detection by measuring the distance between the class prototypes and the query features. Since the input to the support branch is the object image annotated with a bounding box, it often contains a large amount of background information, which degrades the quality of the class prototypes. Through our meticulous observation, we found that the center of the bounding box is often the core feature area of the object. Based on this, we designed a lightweight Background Suppression (BS) module that suppresses background features by measuring the similarity between the peripheral and central features of the support features, thereby providing high-quality support features for class prototype extraction. Additionally, in terms of class prototype extraction, we designed a more robust Comprehensive Prototype Pyramid Distillation (CPPD) module. This module first captures the multi-scale feature information of the object from the background-suppressed support features, and then uses a pyramid structure to hierarchically distill the multi-scale features to extract more comprehensive and purer class prototypes. Extensive experimental results on the PASCAL VOC and COCO datasets show that compared to other models under the same architecture and techniques, we achieved the best results.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"187 ","pages":"Article 104938"},"PeriodicalIF":4.3,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379328","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}

{"title":"Achieving adaptive tasks from human instructions for robots using large language models and behavior trees","authors":"Haotian Zhou,&nbsp;Yunhan Lin,&nbsp;Longwu Yan,&nbsp;Huasong Min","doi":"10.1016/j.robot.2025.104937","DOIUrl":"10.1016/j.robot.2025.104937","url":null,"abstract":"<div><div>Combining Large Language Models (LLMs) with Behavior Trees (BTs) provides an alternative to achieve robot adaptive tasks from human instructions. BTs that contain goal conditions are generated by LLMs based on user instructions and then expanded by BT planners to accomplish tasks and handle disturbances. However, current LLMs struggle to handle unclear human instructions and have a relatively weak understanding of spatial geometry between objects, which results in suboptimal BT planning. To address these problems, this paper proposes a two-stage framework. In the first stage, a Feedback module is designed to handle unclear user instructions and guide the LLM to communicate with users, thus making the goal conditions of BTs complete. In the second stage, a BT Adaptive Update algorithm is proposed to optimize the execution order of the goal conditions, thereby improving the task efficiency of BT planner for multi-goal tasks. Experimental results from simulations and the real world indicate that our method enables the robot to generate complete goal conditions from user instructions and accomplish multi-goal tasks efficiently.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"187 ","pages":"Article 104937"},"PeriodicalIF":4.3,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377812","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}