{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T17:13:40Z","timestamp":1770052420709,"version":"3.49.0"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100022230","name":"Deanship of Scientific Research, Princess Nourah Bint Abdulrahman University","doi-asserted-by":"publisher","award":["PNURSP2025R140"],"award-info":[{"award-number":["PNURSP2025R140"]}],"id":[{"id":"10.13039\/501100022230","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Telepresence robots (TPRs) must co-navigate with humans in constrained hospital environments, where safety depends on anticipating rather than merely reacting to human motion. Existing approaches rarely integrate short-horizon human-motion forecasting with safety-constrained control, which reduces robustness in dense corridors and ward bays. This study addresses this gap by evaluating an anticipatory, safety-aware co-navigation framework for TPRs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a modular framework that couples a lightweight transformer-based forecaster that predicts multi-agent trajectories under occlusion with a safe reinforcement learning (RL) controller. The forecaster produces short-term distributions over pedestrian states that are embedded into the RL policy state and cost as risk-aware occupancy features. Safety is enforced via constrained policy optimization augmented by a run-time control barrier function (CBF) shield that filters unsafe actions. We benchmarked the approach against a social-force or dynamic window approach (DWA), an attention-based crowd-RL policy, and model predictive control (MPC) with CBF. Experiments were conducted across two hospital-like benchmarks (a crowded corridor and a four-bed ward), totaling 2,400 episodes. Outcomes included task success, collision count, minimum human\u2013robot clearance, near-miss events ( \u2264 0.3 m), time-to-goal, CBF violations, and ablations removing forecasting and the CBF shield.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Relative to the best-performing baseline, the proposed method improved task success by 21.6% and reduced collisions by 47.3%. Median minimum human\u2013robot clearance increased by 0.19 m, and near-miss events decreased by 38.5%. Time-to-goal was maintained within +2.7% of MPC+CBF while incurring zero CBF violations under the shield. Ablation studies showed that removing forecasting degraded success by 14.2%, whereas removing the CBF shield increased constraint breaches from 0% to 6.1% of steps.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Anticipatory perception combined with Safe-RL yields substantially safer and more reliable telepresence co-navigation in human-dense clinical layouts without sacrificing efficiency. The framework is modular, enabling alternative forecasters and safety shields. Limitations include sensitivity to forecast drift during abrupt changes in crowd flow. Future work will explore on-device adaptation, shared-autonomy overlays to incorporate operator intent, and prospective evaluations in live hospital workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnbot.2025.1697518","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T06:32:27Z","timestamp":1770013947000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformer-based human-motion forecasting coupled with safe reinforcement learning for telepresence robot co-navigation"],"prefix":"10.3389","volume":"19","author":[{"given":"Heba G.","family":"Mohamed","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, College of Engineering, Princess Nourah Bint Abdulrahman University","place":["Riyadh, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Nasir","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Government College University Lahore","place":["Lahore, Pakistan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fawad","family":"Naseer","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Beaconhouse International College","place":["Faisalabad, Pakistan"]},{"name":"School of Computer Science and Mathematics, Faculty of Engineering, Liverpool John Moores University","place":["Liverpool, United Kingdom"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Tahir","sequence":"additional","affiliation":[{"name":"Department of Computer Software Engineering, Sir Syed University of Engineering and Technology","place":["Karachi, Pakistan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohsin","family":"Jamil","sequence":"additional","affiliation":[{"name":"Department of Engineering, Brock University","place":["St. Catharines, ON, Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1007\/s10514-023-10143-3","article-title":"Reinforcement learning for shared autonomy drone landings","volume":"47","author":"Backman","year":"2023","journal-title":"Autonomous Robots"},{"key":"B2","volume-title":"Optimal Reciprocal Collision Avoidance for Multi-Agent Navigation","author":"Berg","year":"2010"},{"key":"B3","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/s10846-024-02185-1","article-title":"Intent-based task-oriented shared control for intuitive telemanipulation","volume":"110","author":"Bowman","year":"2024","journal-title":"J. Intell. Robot. Syst."},{"key":"B4","doi-asserted-by":"publisher","first-page":"9068","DOI":"10.1016\/j.ifacol.2023.10.138","article-title":"Safe reinforcement learning for autonomous navigation of a driveable vertical mast lift","volume":"56","author":"Brescia","year":"2023","journal-title":"IFAC-PapersOnLine"},{"key":"B5","doi-asserted-by":"crossref","DOI":"10.1109\/CDC51059.2022.9992834","article-title":"\u201cRobust predictive output-feedback safety filter for uncertain nonlinear control systems,\u201d","volume-title":"2022 IEEE 61st Conference on Decision and Control (CDC)","author":"Brunke","year":"2022"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TITS.2023.3329934","article-title":"Stochastic non-autoregressive transformer-based multi-modal pedestrian trajectory prediction for intelligent vehicles","volume":"25","author":"Chen","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1109\/AIM52237.2022.9863392","article-title":"\u201cCLF-CBF based quadratic programs for safe motion control of nonholonomic mobile robots in presence of moving obstacles,\u201d","volume-title":"2022 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","author":"Desai","year":"2022"},{"key":"B8","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/100.580977","article-title":"The dynamic window approach to collision avoidance","volume":"4","author":"Fox","year":"1997","journal-title":"IEEE Robot. Autom. Mag."},{"key":"B9","doi-asserted-by":"publisher","first-page":"647930","DOI":"10.3389\/fnbot.2021.647930","article-title":"Gaze-based intention estimation for shared autonomy in pick-and-place tasks","volume":"15","author":"Fuchs","year":"2021","journal-title":"Front. Neurorobot."},{"key":"B10","doi-asserted-by":"publisher","first-page":"721317","DOI":"10.3389\/frobt.2021.721317","article-title":"Evaluation of socially-aware robot navigation","volume":"8","author":"Gao","year":"2022","journal-title":"Front. Robot. AI"},{"key":"B11","doi-asserted-by":"publisher","first-page":"100945","DOI":"10.1016\/j.arcontrol.2024.100945","article-title":"Advances in the theory of control barrier functions: addressing practical challenges in safe control synthesis for autonomous and robotic systems","volume":"57","author":"Garg","year":"2024","journal-title":"Ann. Rev. Control"},{"key":"B12","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1109\/THMS.2022.3155716","article-title":"Shared control in robot teleoperation with improved potential fields","volume":"52","author":"Gottardi","year":"2022","journal-title":"IEEE Transac. Hum Mach Syst"},{"key":"B13","doi-asserted-by":"publisher","first-page":"9844","DOI":"10.1109\/TPAMI.2024.3457538","article-title":"A review of safe reinforcement learning: methods, theories and applications","volume":"46","author":"Gu","year":"2024","journal-title":"IEEE Transac. Pattern Anal. Mach. Intell"},{"key":"B14","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1177\/09544070231175536","article-title":"Predicting pedestrian tracks around moving vehicles based on conditional variational transformer","volume":"238","author":"He","year":"2023","journal-title":"Proc. Inst. Mech. Eng. Part D J. Automob. Eng."},{"key":"B15","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1146\/annurev-control-071723-102940","article-title":"The safety filter: a unified view of safety-critical control in autonomous systems","volume":"7","author":"Hsu","year":"2024","journal-title":"Ann. Rev. Control Robot. Auton. Syst."},{"key":"B16","doi-asserted-by":"publisher","first-page":"20552076251319820","DOI":"10.1177\/20552076251319820","article-title":"Care partner experience with telepresence robots in long-term care during COVID-19 pandemic","volume":"11","author":"Hu","year":"2025","journal-title":"Digital Health"},{"key":"B17","doi-asserted-by":"publisher","first-page":"713","DOI":"10.3390\/ijerph22050713","article-title":"The impact of telepresence robots on family caregivers and residents in long-term care","volume":"22","author":"Hung","year":"2025","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"B18","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","article-title":"Planning and acting in partially observable stochastic domains","volume":"101","author":"Kaelbling","year":"1998","journal-title":"Artif. Intell."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2794","DOI":"10.3390\/s24092794","article-title":"Bridging requirements, planning, and evaluation: a review of social robot navigation","volume":"24","author":"Karwowski","year":"2024","journal-title":"Sensors"},{"key":"B20","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/3596444","article-title":"Deep reinforcement learning verification: a survey","volume":"56","author":"Landers","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1007\/s12369-024-01140-2","article-title":"Enhancing robotic collaborative tasks through contextual human motion prediction and intention inference","volume":"16","author":"Laplaza","year":"2024","journal-title":"Int. J. Soc. Robot"},{"key":"B22","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.csbj.2024.01.004","article-title":"Testing scenarios for using telepresence robots in healthcare settings","volume":"24","author":"Leoste","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B23","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1109\/JAS.2023.123075","article-title":"A survey on the control Lyapunov function and control barrier function for nonlinear-affine control systems","volume":"10","author":"Li","year":"2023","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"B24","doi-asserted-by":"publisher","first-page":"3657","DOI":"10.3390\/electronics11223657","article-title":"Optimizable control barrier functions to improve feasibility and add behavior diversity while ensuring safety","volume":"11","author":"Li","year":"2022","journal-title":"Electronics"},{"key":"B25","doi-asserted-by":"publisher","first-page":"3296","DOI":"10.3390\/app13053296","article-title":"Non-autoregressive sparse transformer networks for pedestrian trajectory prediction","volume":"13","author":"Liu","year":"2023","journal-title":"Appl. Sci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1080\/01691864.2022.2043184","article-title":"Socially aware robot navigation in crowds via deep reinforcement learning with resilient reward functions","volume":"36","author":"Lu","year":"2022","journal-title":"Adv. Robot."},{"key":"B27","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/3583741","article-title":"Core challenges of social robot navigation: a survey","volume":"12","author":"Mavrogiannis","year":"2023","journal-title":"ACM Transac. Hum. Robot. Interact."},{"key":"B28","doi-asserted-by":"publisher","first-page":"4112","DOI":"10.1109\/LRA.2025.3576071","article-title":"Chance-constrained sampling-based MPC for collision avoidance in uncertain dynamic environments","volume":"10","author":"Mohamed","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1007\/s12369-021-00805-6","article-title":"Determining shape and size of personal space of a human when passed by a robot","volume":"14","author":"Neggers","year":"2021","journal-title":"Int. J. Soc. Robot."},{"key":"B30","doi-asserted-by":"publisher","first-page":"915972","DOI":"10.3389\/frobt.2022.915972","article-title":"The effect of robot speed on comfortable passing distances","volume":"9","author":"Neggers","year":"2022","journal-title":"Front. Robot. AI"},{"key":"B31","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1186\/s12912-024-01983-0","article-title":"Working with a robot in hospital and long-term care homes: staff experience","volume":"23","author":"Ren","year":"2024","journal-title":"BMC Nurs."},{"key":"B32","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1177\/0278364920917446","article-title":"Human motion trajectory prediction: a survey","volume":"39","author":"Rudenko","year":"2020","journal-title":"Int. J. Robot. Res."},{"key":"B33","doi-asserted-by":"publisher","first-page":"7880","DOI":"10.1109\/LRA.2025.3585713","article-title":"SICNav-diffusion: safe and interactive crowd navigation with diffusion trajectory predictions","volume":"10","author":"Samavi","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"B34","doi-asserted-by":"publisher","first-page":"106489","DOI":"10.1016\/j.conengprac.2025.106489","article-title":"Exponential control barrier function and model predictive control for jerk-level reactive motion planning of quadrotors","volume":"164","author":"Shayan","year":"2025","journal-title":"Control Eng. Pract."},{"key":"B35","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1139\/cjce-2024-0137","article-title":"Transformer-based model for predicting trajectories in autonomous vehicle\u2013pedestrian conflicts: a proactive approach to road safety","volume":"51","author":"Shoman","year":"2024","journal-title":"Can. J. Civil Eng."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1177\/02783649241230562","article-title":"A survey on socially aware robot navigation: taxonomy and future challenges","volume":"43","author":"Singamaneni","year":"2024","journal-title":"Int. J. Robot. Res."},{"key":"B37","doi-asserted-by":"publisher","first-page":"4744","DOI":"10.3390\/electronics12234744","article-title":"Risk-aware deep reinforcement learning for robot crowd navigation","volume":"12","author":"Sun","year":"2023","journal-title":"Electronics"},{"key":"B38","doi-asserted-by":"publisher","first-page":"e33380","DOI":"10.2196\/33380","article-title":"Use of robots in critical care: systematic review","volume":"24","author":"Teng","year":"2022","journal-title":"J. Med. Int. Res."},{"key":"B39","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2011.5980408","article-title":"\u201cReciprocal collision avoidance with acceleration-velocity obstacles,\u201d","volume-title":"2011 IEEE International Conference on Robotics and Automation (ICRA)","author":"van den Berg","year":"2011"},{"key":"B40","doi-asserted-by":"publisher","first-page":"e42870","DOI":"10.2196\/preprints.42870","article-title":"A medical assistive robot for tele-healthcare during the COVID-19 pandemic: development and usability study in an isolation ward","volume":"10","author":"Wang","year":"2022","journal-title":"JMIR Hum. Fact."},{"key":"B41","doi-asserted-by":"publisher","first-page":"44","DOI":"10.3390\/ijgi11010044","article-title":"End-to-end pedestrian trajectory forecasting with transformer network","volume":"11","author":"Yao","year":"2022","journal-title":"ISPRS Int. J. Geo-Inform."},{"key":"B42","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1177\/02783649241312699","article-title":"Shared autonomy policy fine-tuning and alignment for robotic tasks","volume":"44","author":"Yousefi","year":"2025","journal-title":"Int. J. Robot. Res."},{"key":"B43","doi-asserted-by":"publisher","first-page":"445","DOI":"10.20965\/jaciii.2023.p0445","article-title":"Time series self-attention approach for human motion forecasting: a baseline 2D pose forecasting","volume":"27","author":"Yunus","year":"2023","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"key":"B44","doi-asserted-by":"publisher","first-page":"1810","DOI":"10.3390\/s23041810","article-title":"Crowd-aware mobile robot navigation based on improved decentralized structured RNN via deep reinforcement learning","volume":"23","author":"Zhang","year":"2023","journal-title":"Sensors"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1697518\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T06:32:29Z","timestamp":1770013949000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1697518\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":44,"alternative-id":["10.3389\/fnbot.2025.1697518"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2025.1697518","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]},"article-number":"1697518"}}