{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T02:20:21Z","timestamp":1771294821660,"version":"3.50.1"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Mobile robots have emerged as a reliable solution for dynamic navigation in real-world applications. Effective deployment in high-density crowds and emergency scenarios requires not only accurate path planning but also rapid adaptation to changing environments. However, autonomous navigation in such environments remains a significant challenge, particularly in time-sensitive applications such as emergency response. Existing path planning and reinforcement learning approaches often lack adaptability to uncertainties and time-varying obstacles, thereby making them less suitable for unstructured real-world scenarios. To address these limitations, a Deep Reinforcement Learning (DRL) framework for dynamic crowd navigation using three algorithms, Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Deep Q-Network (DQN), is proposed. A context-aware state representation that combines Light Detection and Ranging (LiDAR)-based obstacle perception, goal orientation, and robot kinematics to enhance situational awareness is developed. The proposed framework is implemented in a ROS2 Gazebo simulation environment using the TurtleBot3 platform and tested in challenging scenarios to identify the most effective algorithm. Extensive simulation analysis demonstrates that TD3 outperforms the other approaches in terms of success rate, path efficiency, and collision avoidance. This study contributes a reproducible, constraint-aware DRL navigation architecture suitable for real-time, emergency-oriented mobile robot applications.<\/jats:p>","DOI":"10.3389\/frobt.2025.1612392","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T04:15:10Z","timestamp":1760069710000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive emergency response and dynamic crowd navigation for mobile robot using deep reinforcement learning"],"prefix":"10.3389","volume":"12","author":[{"given":"Anusha","family":"Alexander","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V. N. Suchir","family":"Vangaveeti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kalaichelvi","family":"Venkatesan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinane","family":"Mounsef","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karthikeyan","family":"Ramanujam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"119368","DOI":"10.1109\/access.2022.3220703","article-title":"Intelligent optimization of adaptive dynamic Window approach for mobile robot motion control using fuzzy logic","volume":"10","author":"Abubakr","year":"2022","journal-title":"IEEE Access"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1075647","DOI":"10.3389\/fnbot.2022.1075647","article-title":"Toward robust and scalable deep spiking reinforcement learning","volume":"16","author":"Akl","year":"2023","journal-title":"Front. Neurorobotics"},{"key":"B3","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/s10846-024-02118-y","article-title":"Deep model-based reinforcement learning for predictive control of robotic systems with dense and sparse rewards","volume":"110","author":"Antonyshyn","year":"2024","journal-title":"J. Intelligent & Robotic Syst."},{"key":"B4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/09544062231151213","article-title":"A digital twin-driven dynamic path planning approach for multiple AGVs based on deep reinforcement learning","volume":"238","author":"Bao","year":"2024","journal-title":"Proc. Institution Mech. Eng. Part C J. Mech. Eng. Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.neucom.2022.05.006","article-title":"A deep reinforcement learning based method for real-time path planning and dynamic obstacle avoidance","volume":"497","author":"Chen","year":"2022","journal-title":"Neurocomputing"},{"key":"B6","doi-asserted-by":"publisher","first-page":"166","DOI":"10.3390\/act12040166","article-title":"A real-time path planning algorithm based on the Markov decision process in a dynamic environment for Wheeled mobile robots","author":"Chen","year":"2023","journal-title":"Actuators"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1096053","DOI":"10.3389\/fninf.2023.1096053","article-title":"An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms","volume":"17","author":"Dong","year":"2023","journal-title":"Front. Neuroinformatics"},{"key":"B8","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"arXiv preprint arXiv:1604","author":"Duan","year":"2016"},{"key":"B9","first-page":"1224","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th international conference on machine learning (ICML 2018)","author":"Fujita","year":"2018"},{"key":"B10","article-title":"ETGL-DDPG: a deep deterministic policy gradient algorithm for sparse reward continuous control","volume-title":"arXiv preprint arXiv:2410","author":"Futuhi","year":"2024"},{"key":"B11","doi-asserted-by":"publisher","first-page":"16266","DOI":"10.48550\/arXiv.2405.16266","article-title":"Deep reinforcement learning with enhanced PPO for safe mobile robot navigation","author":"Hamid","year":"2024","journal-title":"arXiv Prepr. arXiv:2405"},{"key":"B12","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1109\/ojies.2022.3179617","article-title":"Past, present and future of path-planning algorithms for mobile robot navigation in dynamic environments","volume":"3","author":"Hewawasam","year":"2022","journal-title":"IEEE Open J. Industrial Electron. Soc."},{"key":"B13","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.jautrob.2024.02.008","article-title":"Neamah and Oscar Agustin Mayorga Mayorga. \u201cOptimized TD3 algorithm for robust autonomous navigation in crowded and dynamic human-interaction environments\u201d","volume":"12","author":"Husam","year":"2024","journal-title":"J. Aut. Robotics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"8651","DOI":"10.3390\/s23208651","article-title":"End-to-End autonomous navigation based on deep reinforcement learning with a survival penalty function","volume":"23","author":"Jeng","year":"2023","journal-title":"Sensors"},{"key":"B15","doi-asserted-by":"publisher","first-page":"226","DOI":"10.58346\/JISIS.2024.I2.014","article-title":"Dynamic path planning algorithm for mobile robots: leveraging reinforcement learning for efficient navigation","volume":"2","author":"Kappagantula","year":"2024","journal-title":"J. Internet Serv. Inf. Secur."},{"key":"B16","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10846-023-02003-0","article-title":"A reinforcement learning approach for continuum robot control","volume":"109","author":"Kargin","year":"2023","journal-title":"J. Intelligent & Robotic Syst."},{"key":"B17","doi-asserted-by":"publisher","first-page":"102577","DOI":"10.1016\/j.rcim.2025.102577","article-title":"Multi-agent deep reinforcement learning for cooperative rescue using TD3 algorithm","volume":"85","author":"Kim","year":"2025","journal-title":"Robotics Computer-Integrated Manuf."},{"key":"B18","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s13638-024-02386-0","article-title":"Digital twin based DDPG reinforcement learning for sum-rate maximization of AI-UAV communications","volume":"1","author":"Lee","year":"2024","journal-title":"EURASIP J. Wirel. Commun. Netw."},{"key":"B19","doi-asserted-by":"publisher","first-page":"e32167","DOI":"10.1016\/j.heliyon.2024.e32167","article-title":"Path planning of mobile robot based on improved TD3 algorithm in dynamic environment","author":"Li","year":"","journal-title":"Heliyon"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1109\/ICCASIT62299.2024.10828100","article-title":"Deep reinforcement learning-based obstacle avoidance for robot movement in warehouse environments","volume-title":"arXiv preprint arXiv:2409","author":"Li","year":""},{"key":"B21","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv preprint arXiv:1509","author":"Lillicrap","year":"2015"},{"key":"B22","first-page":"15","article-title":"An evaluation of DDPG, TD3, SAC, and PPO for controlling continuous systems","volume-title":"Proceedings of the 2023 international conference on data science, advanced algorithm and intelligent computing","author":"Liu","year":""},{"key":"B23","first-page":"15","article-title":"An evaluation of DDPG, TD3, SAC, and PPO: deep reinforcement learning algorithms for controlling continuous systems","volume-title":"Proceedings of the 2023 international conference on data science, advanced algorithm and intelligent computing","author":"Liu","year":""},{"key":"B24","doi-asserted-by":"publisher","first-page":"99498","DOI":"10.1109\/ACCESS.2022.3206356","article-title":"ASL-DWA: an improved A-star algorithm for indoor cleaning robots","volume":"10","author":"Liu","year":"2022","journal-title":"IEEE Access"},{"key":"B25","first-page":"1","article-title":"Path planning for the robotic manipulator in dynamic environments based on a deep reinforcement learning method","volume-title":"Journal of intelligent &amp; robotic systems","author":"Liu","year":"2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3895","DOI":"10.3390\/s24123895","article-title":"Autonomous navigation by mobile robot with sensor fusion based on deep reinforcement learning","author":"Ou","year":"2024","journal-title":"Sensors"},{"key":"B27","doi-asserted-by":"publisher","first-page":"102758","DOI":"10.1109\/access.2021.3098706","article-title":"Mobile robot dynamic path planning based on self-adaptive Harmony search algorithm and Morphin algorithm","volume":"9","author":"Quan","year":"2021","journal-title":"IEEE Access"},{"key":"B28","doi-asserted-by":"publisher","first-page":"101517","DOI":"10.1016\/j.swevo.2024.101517","article-title":"Reinforcement learning-assisted evolutionary algorithm: a survey and research opportunities","volume":"86","author":"Song","year":"2024","journal-title":"Swarm Evol. Comput."},{"key":"B29","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1080\/0952813X.2015.1020517","article-title":"An analysis of value function learning with piecewise linear control","volume":"27","author":"Tutsoy","year":"2015","journal-title":"J. Exp. & Theor. Artif. Intell."},{"key":"B30","doi-asserted-by":"publisher","first-page":"104422","DOI":"10.1016\/j.robot.2024.104422","article-title":"Memory-augmented deep reinforcement learning for long-horizon mobile robot navigation","volume":"165","author":"Wang","year":"2024","journal-title":"Robotics Aut. Syst."},{"key":"B31","doi-asserted-by":"publisher","first-page":"111974","DOI":"10.1016\/j.knosys.2024.111974","article-title":"Reinforcement learning-driven dynamic obstacle avoidance for mobile robot trajectory tracking","volume":"297","author":"Xiao","year":"2024","journal-title":"Knowledge-Based Syst."},{"key":"B32","doi-asserted-by":"publisher","first-page":"2300444","DOI":"10.1002\/aisy.202300444","article-title":"Bidirectional obstacle avoidance enhancement-deep deterministic policy gradient: a novel algorithm for mobile-robot path planning in unknown dynamic environments","volume":"6","author":"Xue","year":"2024","journal-title":"Adv. Intell. Syst."},{"key":"B33","doi-asserted-by":"publisher","first-page":"50231","DOI":"10.1109\/ACCESS.2023.3268723","article-title":"Dynamic obstacle avoidance for mobile robots using vision and deep reinforcement learning","volume":"11","author":"Yu","year":"2023","journal-title":"IEEE Access"},{"key":"B34","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/information7010014","article-title":"Deep Q-network (DQN) model for disease prediction using electronic Health records","volume":"1","author":"Zhang","year":"2024","journal-title":"Inf."},{"key":"B35","doi-asserted-by":"publisher","first-page":"5488","DOI":"10.1109\/lra.2023.3296333","article-title":"Prescient collision-free navigation of mobile robots with iterative multimodal motion prediction of dynamic obstacles","volume":"8","author":"Zhang","year":"2023","journal-title":"IEEE Robotics Automation Lett."},{"key":"B36","doi-asserted-by":"publisher","first-page":"111234","DOI":"10.1016\/j.knosys.2025.111234","article-title":"Safe exploration in deep reinforcement learning for robot navigation using curriculum learning","volume":"290","author":"Zhang","year":"2025","journal-title":"Knowledge-Based Syst."},{"key":"B37","doi-asserted-by":"publisher","first-page":"55442","DOI":"10.1109\/access.2023.3282695","article-title":"Dynamic planning for obstacle avoidance of crawler based on Gaussian model","volume":"11","author":"Zhao","year":"2023","journal-title":"IEEE Access"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1612392\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T04:15:12Z","timestamp":1760069712000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1612392\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":37,"alternative-id":["10.3389\/frobt.2025.1612392"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2025.1612392","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"article-number":"1612392"}}