Robotics and Autonomous Systems最新文献

{"title":"Large-scale multi-robot assembly planning for autonomous manufacturing","authors":"Kyle Brown ,&nbsp;Dylan M. Asmar ,&nbsp;Mac Schwager ,&nbsp;Mykel J. Kochenderfer","doi":"10.1016/j.robot.2025.105179","DOIUrl":"10.1016/j.robot.2025.105179","url":null,"abstract":"<div><div>Mobile autonomous robots have the potential to revolutionize manufacturing processes. However, effective employment of large robot fleets in manufacturing requires addressing numerous challenges including the collision-free movement of multiple agents in a shared workspace, effective multi-robot collaboration to manipulate and transport large payloads, complex task allocation due to coupled manufacturing processes, and spatial planning for parallel assembly and transportation of nested subassemblies. In this work, we propose a full algorithmic stack for large-scale multi-robot assembly planning that addresses these challenges and can synthesize construction plans for complex assemblies with thousands of parts in a matter of minutes. Our approach takes in a CAD-like product specification and automatically plans a full-stack assembly procedure for a group of robots to manufacture the product. We propose an algorithmic stack that comprises: (i) an iterative radial layout optimization procedure to define a global staging layout for the manufacturing facility, (ii) a ‘graph-repair’ mixed-integer program formulation and a modified greedy task allocation algorithm to optimally allocate robots and robot sub-teams to assembly and transport tasks, (iii) a geometric heuristic and a hill-climbing algorithm to plan collaborative carrying configurations of robot sub-teams, and (iv) a distributed control policy that enables robots to execute the assembly motion plan without colliding with each other. We also present an open-source multi-robot manufacturing simulator implemented in Julia as a resource to the research community, to test our algorithmic stack and to facilitate multi-robot manufacturing research more broadly: <span><span>https://github.com/sisl/ConstructionBots.jl</span><svg><path></path></svg></span>. Our empirical results demonstrate the scalability and effectiveness of our approach by generating plans to manufacture a LEGO<span><math><msup><mrow></mrow><mrow><mtext>®</mtext></mrow></msup></math></span> model of a Saturn V launch vehicle with 1845 parts, 306 subassemblies, and 250 robots in under three minutes on a standard laptop computer.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105179"},"PeriodicalIF":5.2,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145057245","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":"Improved BFS-based path planning algorithm with finite time generalized suboptimal search incorporating fixed-wing UAV flight constraints for complex low-altitude airspace","authors":"Zimao Sheng,&nbsp;Hong’an Yang ,&nbsp;Jiakang Wang,&nbsp;Li Jing ,&nbsp;Li Haifeng","doi":"10.1016/j.robot.2025.105164","DOIUrl":"10.1016/j.robot.2025.105164","url":null,"abstract":"<div><div>The booming demands in low-altitude airspace impose stringent requirements on fixed-wing UAV path planning, emphasizing flyability, stealth, real-time performance, and high ground-following ratios. To achieve efficient and highly stealthy low-altitude variable-speed penetration in complex terrains, this study proposes two generalized suboptimal search algorithms — Generalized Suboptimal Search (GSS) and its focal-list enhanced variant (GSS-FS) — under the best-first search (BFS) framework. First, a dynamic node mechanism and constraint-aware neighbor expansion policy are designed to explicitly integrate fixed-wing UAVs’ flight constraints (e.g., attack angle, sideslip angle, angular rate). This addresses the “feasibility gap” in classical methods, where planned paths often fail to meet physical maneuverability requirements. Second, unlike traditional suboptimal algorithms with fragmented theoretical foundations (e.g., weighted A*, pwXD), GSS establishes a unified framework for generalized priority functions. This framework theoretically guarantees how suboptimal solutions approximate the optimal one, resolving the lack of systematic boundary estimation in existing approaches. Third, GSS-FS incorporates an optimized focal list and hybrid storage structure, achieving linear time complexity, which further improves its pathfinding efficiency on large-scale digital elevation maps (DEM). Simulations validate that the proposed algorithms can effectively search for suboptimal even optimal solutions that can weigh multiple flight indicators in finite time domain on large-scale DEM, making them suitable for high-dynamic low-altitude penetration missions.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105164"},"PeriodicalIF":5.2,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048412","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":"Graduated non-convex feature-metric-based 6D object pose refinement via deep reinforcement learning","authors":"Peiyuan Ni,&nbsp;Marcelo H. Ang Jr","doi":"10.1016/j.robot.2025.105177","DOIUrl":"10.1016/j.robot.2025.105177","url":null,"abstract":"<div><div>Recently, many works focus on 6D object pose refinement with a single RGB image. Most of them apply the differentiable Levenberg–Marquardt (LM) algorithm as the solver. However, they may easily ignore the importance of the damping parameter denoted by <span><math><mi>λ</mi></math></span>, which affects the accuracy and efficiency of prediction. In this paper, we present a coarse-to-fine feature-metric-based 6D object pose refinement framework, which utilizes the intermediate layers to predict <span><math><mi>λ</mi></math></span> combined with Region of Interest (ROI) alignment and eigenvalues. To facilitate better convergence during the training process, we propose to leverage graduated non-convexity (GNC) to handle uncertainty and feature residual learning in a pixel-level manner. Moreover, current works have not analyzed the control process during the whole iteration process. We propose to use deep reinforcement learning to fit this non-differentiable process, which can reduce redundant steps during the prediction stage. Finally, with a Transformer-based backbone, our algorithm with no iteration control learning (ICL) achieves better performance with Shape-constraint Recurrent Flow (SRF, state-of-the-art object pose refinement method) (Hai et al. 2023) on Linear Model for Object Detection (LineMOD), LineMOD Occlusion and YCB-Video datasets. Moreover, our full algorithm with VGG-16 as the backbone, accelerated with TensorRT, runs at about 94 FPS. It exhibits superior speed compared to RePose (Iwase et al. 2021), and notably surpasses its accuracy, especially for initial poses with large errors. The code will be available at <span><span>https://github.com/NiPeiyuan/EARePOSE.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105177"},"PeriodicalIF":5.2,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145026586","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":"Improved prescribed performance control for multi-quadrotor payload transport under unknown disturbances","authors":"Xinyu Chen ,&nbsp;Yunsheng Fan ,&nbsp;Guofeng Wang ,&nbsp;Dongdong Mu","doi":"10.1016/j.robot.2025.105184","DOIUrl":"10.1016/j.robot.2025.105184","url":null,"abstract":"<div><div>This paper presents a robust and enhanced control strategy for a multi-quadrotor suspended payload system, which is characterized by complex nonlinear dynamics and unknown external disturbances. A precise dynamic model of the system is formulated using the Udwadia–Kalaba method. A distributed cooperative planning framework, based on graph theory, is employed to enable effective information exchange and cooperative control among multiple quadrotors. To mitigate the impact of unknown disturbances, such as wind fields and variations in payload mass, a disturbance observer is developed to estimate and compensate for these disturbances, thereby enhancing system robustness. Furthermore, an improved prescribed performance control method is proposed to address the issue of exceeding performance boundaries. The steady-state error of the system is effectively reduced by adaptively adjusting the prescribed performance boundary and combining it with integral backstepping, and real-time constraints on tracking errors and closed-loop stability are achieved. Simulation results validate that the proposed control strategy significantly enhances the control performance and disturbance rejection capability of the multi-quadrotor suspended payload system, demonstrating superior robustness.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105184"},"PeriodicalIF":5.2,"publicationDate":"2025-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098645","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":"Towards agile multi-robot systems in the real world: Fast onboard tracking of active blinking markers for relative localization","authors":"Tim Lakemann ,&nbsp;Daniel Bonilla Licea ,&nbsp;Viktor Walter ,&nbsp;Tomáš Báča ,&nbsp;Martin Saska","doi":"10.1016/j.robot.2025.105175","DOIUrl":"10.1016/j.robot.2025.105175","url":null,"abstract":"<div><div>A novel onboard tracking approach enabling vision-based relative localization and communication using Active blinking Marker Tracking (AMT) is introduced in this article. Active blinking markers on multi-robot team members improve the robustness of relative localization for aerial vehicles in tightly coupled multi-robot systems during real-world deployments, while also serving as a resilient communication system. Traditional tracking algorithms struggle with fast-moving blinking markers due to their intermittent appearance in camera frames and the complexity of associating multiple of these markers across consecutive frames. AMT addresses this by using weighted polynomial regression to predict the future appearance of active blinking markers while accounting for uncertainty in the prediction. In outdoor experiments, the AMT approach outperformed state-of-the-art methods in tracking density, accuracy, and complexity. The experimental validation of this novel tracking approach for relative localization and optical communication involved testing motion patterns motivated by our research on agile multi-robot deployment.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105175"},"PeriodicalIF":5.2,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048408","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":"FIT-SLAM 2: Efficient 3D exploration with Fisher information and traversability-based adaptive roadmap","authors":"Suchetan Saravanan,&nbsp;Anais Bains,&nbsp;Caroline P.C. Chanel,&nbsp;Damien Vivet","doi":"10.1016/j.robot.2025.105188","DOIUrl":"10.1016/j.robot.2025.105188","url":null,"abstract":"<div><div>This paper presents FIT-SLAM 2, an enhanced framework for autonomous 3D exploration, integrating Fisher Information and a traversability-aware adaptive roadmap. Building on FIT-SLAM, our approach introduces frontier classification into local and global categories, a scheduling strategy for exploration path computation, and optimized real-time Fisher Information computation using pre-computed lookup tables to assess localization confidence and ensure safe exploration. FIT-SLAM 2 seamlessly integrates with the SLAM backend while iteratively constructing and updating an adaptive roadmap that optimizes both navigation efficiency and safety. This enables the robot to efficiently explore complex environments – including rocky terrains, caves, and mazes – while maintaining robust localization. Extensive experiments demonstrate that FIT-SLAM 2 achieves a 33% increase in exploration rate in unstructured environments along with a notable improvement in localization accuracy and computational efficiency over state-of-the-art methods. For reproducibility and future enhancements, we release our implementation at <span><span>https://github.com/suchetanrs/FIT-SLAM</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105188"},"PeriodicalIF":5.2,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019120","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":"The sequences of bundles of line segments for autonomous robots with limited vision range to escape from blind alley regions","authors":"Phan Thanh An ,&nbsp;Pham Hoang Anh ,&nbsp;Tran Thanh Binh ,&nbsp;Tran Van Hoai","doi":"10.1016/j.robot.2025.105185","DOIUrl":"10.1016/j.robot.2025.105185","url":null,"abstract":"<div><div>Consider the following problem: A robot operating in a 2D environment with a limited vision range finds a path to a goal in an unknown environment containing obstacles. In this paper, we propose a novel algorithm to solve the problem. In some special cases, our algorithm is convergent with respect to <span><math><mrow><mo>‖</mo><mo>.</mo><mo>‖</mo></mrow></math></span>. The problem involves discovering the environmental map and blind alley regions, that are bounded by obstacles, and it provides no possible passage for robots except in and out of their path entry occur, the robot has to return back to some positions outside to escape from such regions such that the returned path is not longer than the path entry (Blind Alley Region problem, (BAR) problem, in short). To solve the (BAR) problem, sequences of bundles of line segments during the robot’s traveling are constructed in our algorithm.</div><div>Some advantages of our algorithm are that (a) It reduces search space in blind alley regions because it only works on the sequences of bundles of the line segments built by the robot’s limited vision range. (b) Our algorithm ensures that the returned path to escape from the regions is not longer than the previous path of the robot. (c) Due to the construction of the sequences of bundles of line segments, our paths are not always “close” obstacles and the number of turns of such paths is smaller ones determined by other shortest path algorithms (e.g., A*, RRT*).</div><div>Our algorithm is implemented in Python and we experience the algorithm on some autonomous robots with different vision ranges in real environment. We also compare our result with RRTX, a state-of-art local path-planning algorithm, and A<span><math><msup><mrow></mrow><mrow><mo>∗</mo></mrow></msup></math></span>, a basic one. The experimental results show that our algorithm provides better solutions than RRTX and A* results in some specific circumstances.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105185"},"PeriodicalIF":5.2,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099424","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":"A skill learning approach based on dynamic movement primitives and quadratic-neural energy functions","authors":"Yongqing Liu ,&nbsp;Chengguo Liu ,&nbsp;Ye He,&nbsp;Xianzu Peng,&nbsp;Maoxuan Li","doi":"10.1016/j.robot.2025.105183","DOIUrl":"10.1016/j.robot.2025.105183","url":null,"abstract":"<div><div>In this paper, we propose a skill learning method based on the combination of energy change and trajectory optimization. First, we propose a novel quadratic-neural energy function (QNEF) to achieve a unified characterization of multiple skill features from demonstrations. Second, the trajectories are segmented using QNEF and its gradient to generate multi-layer energy sequences, which enables accurate segmentation of non-specific trajectories and supports spatio-temporal alignment through Global Time Warping (GTW). In addition, inspired by natural energy systems, we formulate the energy function as a coupling term and integrate it into dynamic movement primitives (DMPs) to construct quadratic-neural energy function dynamic movement primitives (QNEF-DMPs). The proposed method autonomously adjusts trajectories based on energy levels while preserving trajectory features, enabling continuous obstacle avoidance. Moreover, the visualization of the energy field enhances both intuitiveness and physical interpretability. Finally, the effectiveness of the method is demonstrated through practical experiments on the ROKAE robot platform.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105183"},"PeriodicalIF":5.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145003664","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":"Differentiable optimization based time-varying control barrier functions for dynamic obstacle avoidance","authors":"Bolun Dai,&nbsp;Rooholla Khorrambakht,&nbsp;Prashanth Krishnamurthy,&nbsp;Farshad Khorrami","doi":"10.1016/j.robot.2025.105182","DOIUrl":"10.1016/j.robot.2025.105182","url":null,"abstract":"<div><div>Control barrier functions (CBFs) provide a simple yet effective way for safe control synthesis. Recently, work has been done using differentiable optimization (diffOpt) based methods to systematically construct CBFs for static obstacle avoidance tasks between geometric shapes. In this work, we propose a novel pipeline for diffOpt CBFs to perform dynamic obstacle avoidance tasks while considering measurement noise and actuation limits. We show that by using the time-varying CBF (TVCBF) formulation, we can perform obstacle avoidance for dynamic geometric obstacles. Additionally, we show how to enable the TVCBF constraint to consider measurement noise and actuation limits. To demonstrate the efficacy of our proposed approach, we first compare its performance with a model predictive control based method and a circular CBF based method on a simulated dynamic obstacle avoidance task. Then, we demonstrate the performance of our proposed approach in experimental studies using a 7-degree-of-freedom Franka Research 3 robotic manipulator.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105182"},"PeriodicalIF":5.2,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922642","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":"Enhancing fault detection and performance for UAVs with digital twin systems in search and rescue missions","authors":"Cara Rose ,&nbsp;Robert McMurray ,&nbsp;Muhammad Usman Hadi","doi":"10.1016/j.robot.2025.105186","DOIUrl":"10.1016/j.robot.2025.105186","url":null,"abstract":"<div><div>This study presents the development of a Digital Twin for the \"Made in UU\" Field-based Autonomous LiDAR Control for Obstacle Navigation (FALCON), enabling advanced control systems and robust fault detection. The Digital Twin integrates real-time flight data and fault scenarios to enhance UAV stability under challenging conditions. The FALCON was modelled using real-time flight data, with traditional control methods, including Proportional-Integral-Derivative (PID), Linear Quadratic Regulator (LQR), and Linear Quadratic Gaussian (LQG), combined with optimization techniques such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Mayfly Algorithm (MA) to tune state feedback gains. Simulations showed GA-based tuning outperformed manual tuning, PSO, and MA in improving UAV stability and fault recovery. For PID, manual tuning achieved the fastest pitch settling with a 73.8 % improvement, while PSO-tuned PID delivered the quickest roll (52.8 %) and yaw (47.2 %) responses. The PSO-tuned LQG controller minimized settling times across all dynamics. Full State Feedback and PID controllers performed comparably, with GA achieving the best roll settling and both GA and PSO reaching 0.1 s in yaw. Overall, LQR with GA tuning provided the most balanced performance. These findings highlight GA’s robustness in challenging conditions, significantly improving UAV safety and efficiency in search and rescue, environmental monitoring, and disaster response. FALCON UAV and its Digital Twin offer a low-cost, IoT-integrated platform with real-time fault detection and optimal control, paving the way for next-generation UAV systems. Future work involves integrating machine learning for dynamic fault detection and real-world deployments.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105186"},"PeriodicalIF":5.2,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144996483","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}