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":"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":"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}

{"title":"Adaptive game-theoretic decision-making with driving style recognition for autonomous vehicles in uninterrupted traffic flows at intersections","authors":"Yuxiao Cao,&nbsp;Yinuo Jiang,&nbsp;Xiangrui Zeng","doi":"10.1016/j.robot.2025.105180","DOIUrl":"10.1016/j.robot.2025.105180","url":null,"abstract":"<div><div>The absence of standardized conflict resolution mechanisms presents critical challenges for autonomous vehicles operating in uninterrupted traffic flows, particularly when managing time-sensitive interactions with heterogeneous road users. Existing approaches either adopt overly conservative policies by oversimplifying multi-agent interactions or neglect the critical influence of heterogeneous driving styles. This paper proposes a game-theoretic decision-making framework for autonomous vehicles in uninterrupted traffic flow scenarios, specifically designed to address the intertwined challenges of multi-objective optimization and driving style adaptation. A hierarchical game-theoretic architecture integrates kinematic state evolution, feasibility constraints, and interactive behavior modeling to rigorously model multi-vehicle interactions under dynamic mixed traffic conditions. A novel online identification mechanism estimates driving styles through real-time interaction pattern analysis, while a machine learning-driven adaptive framework generates parametric policies through offline random forest training coupled with context-aware online policy adjustments. Comprehensive simulations validate the framework’s effectiveness in both single and multiple intersection scenarios, demonstrating enhanced interaction adaptability (more than 10% efficiency improvements) compared to conventional non-adaptive methods. Experimental results demonstrate the model’s capability to efficiently handle heterogeneous driving behaviors and dynamically refine negotiation strategies, providing a systematic, human-like vehicle decision-making solution for mixed traffic environments.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105180"},"PeriodicalIF":5.2,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922641","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":"Geometric methods for aircraft planning and control","authors":"Francesco Trotti,&nbsp;Damiano Rigo,&nbsp;Riccardo Muradore","doi":"10.1016/j.robot.2025.105181","DOIUrl":"10.1016/j.robot.2025.105181","url":null,"abstract":"<div><div>Path planning and control of autonomous aircraft is a critical problem, particularly under conditions of model and sensor uncertainty. This paper presents a hierarchical control architecture that integrates geometric and probabilistic methods to address these challenges. The proposed framework combines a high-level controller, a low-level controller, and an observer, leveraging Lie group theory for geometric modeling. The high-level controller formulates the planning problem as a Markov Decision Process (MDP), solved using Monte Carlo Tree Search (MCTS) to generate reference trajectories while avoiding no-fly zones. The low-level controller exploits the relationship between tangent space velocities and left-trivialized velocities in the Lie algebra to produce control commands. State estimation is achieved using a second-order optimal minimum-energy filter formulated on Lie groups, ensuring robust performance under noisy measurements. Simulation results show the efficacy of the proposed architecture in guiding an aircraft from a start point to a target while satisfying operational constraints.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"194 ","pages":"Article 105181"},"PeriodicalIF":5.2,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144988599","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}