Frontiers in Robotics and AI最新文献

{"title":"Learning faults in time: sequential behavioural modelling for complex fault detection in multi-robot systems.","authors":"Faisal Firas Mazloum, David Portugal, Micael S Couceiro","doi":"10.3389/frobt.2026.1827739","DOIUrl":"10.3389/frobt.2026.1827739","url":null,"abstract":"<p><p>Reliable fault detection in multi-robot systems requires models capable of capturing complex, time-dependent fault signatures that manifest over extended temporal horizons rather than instantaneous observations alone. Existing data-driven approaches operate reactively on behavioural snapshots, failing to capture fault modes whose discriminative signature depends on temporally ordered precursors. This work formalises a theoretical impossibility result demonstrating that memoryless classifiers are provably insufficient, and presents a Long Short Term Memory (LSTM) model operating on generic, primitive behavioural features to learn these latent temporal dependencies without domain-specific priors. Two complex fault types are evaluated: progressive actuator degradation and intermittent actuator dropout, each paired with a distinct swarm movement pattern representing varying levels of temporal complexity. Experimental results demonstrate that sequential models are essential when the fault signature is defined by ordered precursors, while memoryless models partially suffice for simpler temporal structures. Compute benchmarks confirm real-time feasibility for distributed onboard deployment.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1827739"},"PeriodicalIF":3.7,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13461495/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148726921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The human-robot interaction scale database.","authors":"Laura Saad, Eileen Roesler, Elizabeth Phillips, J Gregory Trafton","doi":"10.3389/frobt.2026.1846413","DOIUrl":"10.3389/frobt.2026.1846413","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1846413"},"PeriodicalIF":3.7,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13457007/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148714012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Crowd navigation in a multi-room environment: a model predictive control framework for mobile robots.","authors":"Giovanbattista Gravina, Francesco D'Orazio, Michele Cipriano, Tommaso Belvedere, Giuseppe Oriolo","doi":"10.3389/frobt.2026.1812386","DOIUrl":"10.3389/frobt.2026.1812386","url":null,"abstract":"<p><p>Mobile robots operating in human-populated environments must navigate complex, multi-room spaces while ensuring safety, i.e., generating collision-free motion. In this study, we present a sensor-based model predictive control (MPC) scheme designed for safe crowd navigation in such non-convex environments. The proposed framework decomposes the free space into a set of overlapping convex regions to construct a topological graph, enabling a high-level planner to compute optimal sequences of traversable areas. To effectively perceive the crowd, the system employs a robust perception pipeline that fuses 2D LiDAR data with semantic information from an RGB-D camera, utilizing Kalman filters (KFs) to estimate and predict human motion. These predictions are integrated into an MPC controller which generates robot commands by enforcing safety through discrete-time control barrier function (DT-CBF), ensuring that the robot avoids collisions while remaining within navigable regions. The approach is validated through high-fidelity simulations and real-world experiments using the TIAGo mobile manipulator. The results demonstrate that integrating vision-based semantic data with geometric constraints significantly improves collision avoidance and success rates in cluttered, multi-room scenarios.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1812386"},"PeriodicalIF":3.7,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13453804/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robotic lava tube mapping and multimodal data collection using quadruped and LiDAR.","authors":"A J Hidding, H H Bier, L Peternel, A J Becoy, F A P Romio, G Calabrese","doi":"10.3389/frobt.2026.1855443","DOIUrl":"10.3389/frobt.2026.1855443","url":null,"abstract":"<p><p>As part of TU Delft Rhizome 2.0 and Moonshot projects, focusing on the development of extraterrestrial habitats in lava tubes, the robotic mapping of an analogue lava tube in Sicily has been studied with the future goal of assessing its suitability for building construction. The main objective of the research was to survey a lava tube and acquire a novel dataset for future research, while also analyzing the collected data to evaluate possible future lava tube exploration scenarios for the Moon and Mars. This paper presents the robotic mapping conducted in Grotta di Monte Intraleo, detailing the implementation and outlining challenges and insights, leading to the new dataset. Various mapping and data collection methods, including robotic mapping using LiDAR, was explored. The overall strategy relies on multi-technique scanning to enhance redundancy and ensure comprehensive data acquisition, that is providing a robust foundation for future robotic exploration and habitat planning.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1855443"},"PeriodicalIF":3.7,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13454644/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Advanced sensing, learning and control for effective human-robot interaction.","authors":"Zhenyu Lu, Lu Chen, Yanpeng Guan, Jing Luo, Chao Zeng","doi":"10.3389/frobt.2026.1928993","DOIUrl":"https://doi.org/10.3389/frobt.2026.1928993","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1928993"},"PeriodicalIF":3.7,"publicationDate":"2026-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13447067/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoupling what, how, and when for observing decision-making context in autonomous robots.","authors":"Johannes Ernst, David Lennart Risch, Peter Lehner, Freek Stulp, Andreas Dömel","doi":"10.3389/frobt.2026.1847701","DOIUrl":"10.3389/frobt.2026.1847701","url":null,"abstract":"<p><p>This paper presents an approach that decouples what to observe, how to observe it, and when observations are required for decision-making in autonomous robots. Situation awareness is essential for efficient and reliable autonomous robot operation, but despite advances toward parallelizing perception and action, key challenges remain in making perception aware of the current context and ensuring observability during action execution. To address this, we explicitly model the decision-making context and identify it with dedicated observers running in parallel to the task execution. Observer behaviors are implemented as behavior trees and coordinated by a centralized context manager. We validate the approach on a mobile manipulator that performs autonomous machine-tending tasks in a real medical laboratory, as well as during a public trade fair. Experimental results show that context-driven observers can robustly identify decision-making context without interfering with ongoing actions. Furthermore, parallelized perception leads to substantial runtime improvements, achieving overall task time savings of up to <math><mrow><mn>24</mn> <mi>%</mi></mrow> </math> . These findings demonstrate that explicit context modeling and observer-based perception parallelization enhance the stability and efficiency of existing robotic execution architectures.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1847701"},"PeriodicalIF":3.7,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13437423/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148680332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncertainty-guided informative path planning for ecological monitoring using autonomous surface vehicles under Dubins motion constraints.","authors":"Jalil Chavez-Galaviz, Meredith Bloss, Nina Mahmoudian","doi":"10.3389/frobt.2026.1823324","DOIUrl":"10.3389/frobt.2026.1823324","url":null,"abstract":"<p><p>Autonomous surface vehicles (ASVs) enable efficient in-situ data collection for large-scale ecological monitoring; however, effective environmental mapping requires planning strategies that account for not only informative measurements, but also vehicle motion constraints and limited mission resources. Existing approaches often rely on stationary environmental models or loosely coupled planning frameworks that do not fully exploit model uncertainty when generating feasible trajectories. To address these limitations, we propose a closed-loop informative path planning (IPP) framework that tightly integrates environmental modeling and trajectory generation for autonomous sampling. The proposed approach combines a nonstationary uncertainty representation using Gaussian Process Regression with Attentive Kernels (AK-GPR), uncertainty- guided adaptive sampling, and a Dubins-constrained RRT* planner to generate dynamically feasible and information-rich trajectories. The proposed framework is evaluated through staged experiments, including simulation and field validation, across representative ecological monitoring scenarios such as algal plume tracking, bathymetric mapping, and seagrass probability estimation. The results demonstrate that the proposed planner shows improved performance relative to the baseline planners in different initialization grid densities, with particularly strong performance in scenarios with limited prior information. In all environments, the proposed IPP framework achieved an average reduction of approximately 24% in mean absolute error (MAE) and 32% in predictive uncertainty compared to baseline planners, with improvements reaching up to 33% in MAE and 42%, respectively, in sparse initialization settings. These results demonstrate the benefits of a tightly coupled framework that balances uncertainty reduction and spatial coverage, enabling more efficient environmental exploration under realistic vehicle constraints.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1823324"},"PeriodicalIF":3.7,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13433192/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148674451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IonPad adhesive gripper with variable-stiffness endoskeleton.","authors":"Yuno Takitani, Keisuke Koyama, Weiwei Wan, Kensuke Harada","doi":"10.3389/frobt.2026.1815258","DOIUrl":"10.3389/frobt.2026.1815258","url":null,"abstract":"<p><p>In this study, we develop an innovative adhesion gripper capable of handling plate-like objects with various thicknesses without causing damage. The gripper combines an adhesion pad utilizing intermolecular forces and a variable-stiffness endoskeleton, allowing for precise adjustment of the pressing force during contact and the adhesion force while gripping an object. Central to its design is the fluid-driven and origami-structured endoskeleton that regulates contact and adhesion forces by controlling the fluid temperature. Furthermore, the gripper includes an outer frame which can be used for releasing the grasped objects by contracting the endoskeleton through fluid aspiration. Experimental evaluations demonstrate that the maximum contact force can be adjusted over a 27-fold range, while the adhesion force is tunable by up to a 12-fold variation. Notably, the ability to finely modulate the contact force facilitates the effective handling of thin plate components even on uneven surfaces. These results highlight the gripper's potential for applications that require the delicate and precise manipulation of fragile, thin objects.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1815258"},"PeriodicalIF":3.7,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13433296/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148674379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multimodal dataset for socially aware navigation of heavy-duty construction robots.","authors":"Carlos A P Pizzino, Phani-Teja Singamaneni, Micael S Couceiro, Rachid Alami","doi":"10.3389/frobt.2026.1873168","DOIUrl":"10.3389/frobt.2026.1873168","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1873168"},"PeriodicalIF":3.7,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13423729/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148653744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid task and motion planning with reactive collision handling for multi-robot disassembly of complex products: application to EV batteries.","authors":"Abdelaziz Shaarawy, Cansu Erdogan, Rustam Stolkin, Alireza Rastegarpanah","doi":"10.3389/frobt.2026.1857847","DOIUrl":"10.3389/frobt.2026.1857847","url":null,"abstract":"<p><p>This paper addresses the problem of multi-robot coordination for complex manipulation task sequences. We present a vision-driven task-and-motion planning (TAMP) framework for a real dual-agent platform that integrates task decomposition and allocation with a learning-based planner. A GMM-informed RRT motion planner is coupled with a hybrid safety layer that combines predictive collision checking in a MoveIt/FCL digital twin with reactive avoidance and replanning. This integration is challenging as the system jointly satisfies task precedence, geometric feasibility, dynamic obstacle avoidance, and dual-arm coordination constraints. The framework operates in a closed loop by updating the remaining task sequence from repeated scene scans and completion-state tracking rather than executing a fixed open-loop plan. In EV battery disassembly experiments, compared with baseline RRTConnect under identical perception and task assignments, the proposed system reduces cumulative end-effector path length from 48.8 to 17.9 m <math><mrow><mo>(</mo> <mrow><mo>-</mo> <mn>63.3</mn> <mi>%</mi></mrow> <mo>)</mo></mrow> </math> , improves makespan from 467.9 to 429.8 s <math><mrow><mo>(</mo> <mrow><mo>-</mo> <mn>8.1</mn> <mi>%</mi></mrow> <mo>)</mo></mrow> </math> , and reduces swept volumes (R1: <math><mrow><mn>0.583</mn> <mo>→</mo> <mn>0.139</mn> <mtext> </mtext> <msup><mrow><mi>m</mi></mrow> <mrow><mn>3</mn></mrow> </msup> </mrow> </math> , R2: <math><mrow><mn>0.696</mn> <mo>→</mo> <mn>0.252</mn> <mtext> </mtext> <msup><mrow><mi>m</mi></mrow> <mrow><mn>3</mn></mrow> </msup> </mrow> </math> ) and overlap <math><mrow><mo>(</mo> <mrow><mn>0.064</mn> <mo>→</mo> <mn>0.034</mn> <mtext> </mtext> <msup><mrow><mi>m</mi></mrow> <mrow><mn>3</mn></mrow> </msup> </mrow> <mo>)</mo></mrow> </math> . These results show that combining predictive planning and reactive collision avoidance in a real dual-arm disassembly scenario improves motion compactness, safety, and scalability to broader multi-robot sequential manipulation tasks.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1857847"},"PeriodicalIF":3.7,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13422507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148632234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}