{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T13:38:00Z","timestamp":1770298680303,"version":"3.49.0"},"reference-count":30,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Politecnico di Torino","award":["C644866475-00000012|7253.50_DIM37_ALI"],"award-info":[{"award-number":["C644866475-00000012|7253.50_DIM37_ALI"]}]},{"name":"PhD fund","award":["C644866475-00000012|7253.50_DIM37_ALI"],"award-info":[{"award-number":["C644866475-00000012|7253.50_DIM37_ALI"]}]},{"name":"AM2R project, \u201cMobilizing Agenda for Business Innovation in the Two Wheels Sector\u201d","award":["C644866475-00000012|7253.50_DIM37_ALI"],"award-info":[{"award-number":["C644866475-00000012|7253.50_DIM37_ALI"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics"],"abstract":"<jats:p>The primary challenge in robotic navigation lies in enabling robots to adapt effectively to new, unseen environments. Addressing this gap, this paper enhances the Twin Delayed Deep Deterministic Policy Gradient (TD3) model\u2019s adaptability by introducing randomized start and goal points. This approach aims to overcome the limitations of fixed goal points used in prior research, allowing the robot to navigate more effectively through unpredictable scenarios. This proposed extension was evaluated in unseen environments to validate the enhanced adaptability and performance of the TD3 model. The experimental results highlight improved flexibility and robustness in the robot\u2019s navigation capabilities, demonstrating the ability of the model to generalize effectively to unseen environments. Additionally, this paper provides a concise overview of TD3, focusing on its core mechanisms and key components to clarify its implementation.<\/jats:p>","DOI":"10.3390\/robotics14040043","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T08:48:00Z","timestamp":1743410880000},"page":"43","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Robot Navigation Using Randomized Goal Selection with Twin Delayed Deep Deterministic Policy Gradient"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4189-7614","authenticated-orcid":false,"given":"Romisaa","family":"Ali","sequence":"first","affiliation":[{"name":"Department of Computer and Control Engineering (DAUIN), Politecnico di Torino, 10129 Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6696-9362","authenticated-orcid":false,"given":"Sedat","family":"Dogru","sequence":"additional","affiliation":[{"name":"Institute of Systems and Robotics, Department of Electrical and Computer Engineering, University of Coimbra, 3000-214 Coimbra, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9396-986X","authenticated-orcid":false,"given":"Lino","family":"Marques","sequence":"additional","affiliation":[{"name":"Institute of Systems and Robotics, Department of Electrical and Computer Engineering, University of Coimbra, 3000-214 Coimbra, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1921-0126","authenticated-orcid":false,"given":"Marcello","family":"Chiaberge","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunications (DET), Politecnico di Torino, 10129 Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,31]]},"reference":[{"key":"ref_1","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, MIT Press. [2nd ed.]. Available online: https:\/\/mitpress.mit.edu\/9780262039246\/reinforcement-learning\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/s10514-020-09959-0","article-title":"An improved kinematic model for skid-steered wheeled platforms","volume":"45","author":"Dogru","year":"2021","journal-title":"Auton. Robot."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"7965","DOI":"10.1109\/LRA.2021.3101866","article-title":"A CNN-Based Vision-Proprioception Fusion Method for Robust UGV Terrain Classification","volume":"6","author":"Chen","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_4","unstructured":"Lapan, M. (2018). Deep Reinforcement Learning Hands-On: Apply Modern RL Methods, with Deep Q-Networks, Value Iteration, Policy Gradients, TRPO, AlphaGo Zero and More, Packt Publishing Ltd."},{"key":"ref_5","unstructured":"Hafner, D., Lillicrap, T., Norouzi, M., and Ba, J. (2020). Mastering Atari with Discrete World Models. arXiv."},{"key":"ref_6","unstructured":"Roy, S., Bakshi, S., and Maharaj, T. (2020). OPAC: Opportunistic Actor-Critic. arXiv."},{"key":"ref_7","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing Atari with Deep Reinforcement Learning. arXiv."},{"key":"ref_8","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., and Wierstra, D. (2016, January 2\u20134). Continuous Control with Deep Reinforcement Learning. Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico."},{"key":"ref_9","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018, January 10\u201315). Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_10","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. (2017). Proximal Policy Optimization Algorithms. arXiv."},{"key":"ref_11","unstructured":"Roth, A.M. (2025, March 24). JackalCrowdEnv. GitHub Repository. Available online: https:\/\/github.com\/AMR-\/JackalCrowdEnv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Roth, A.M., Liang, J., and Manocha, D. (2021\u20131, January 27). XAI-N: Sensor-Based Robot Navigation Using Expert Policies and Decision Trees. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic.","DOI":"10.1109\/IROS51168.2021.9636759"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Akmandor, N.\u00dc., Li, H., Lvov, G., Dusel, E., and Padir, T. (2022, January 23\u201327). Deep Reinforcement Learning Based Robot Navigation in Dynamic Environments Using Occupancy Values of Motion Primitives. Proceedings of the 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan.","DOI":"10.1109\/IROS47612.2022.9982133"},{"key":"ref_14","unstructured":"Akmandor, N.U., and Dusel, E. (2025, March 24). Tentabot: Deep Reinforcement Learning-Based Navigation. GitHub Repository. Available online: https:\/\/github.com\/RIVeR-Lab\/tentabot\/tree\/master."},{"key":"ref_15","first-page":"619","article-title":"Robot exploration and navigation in unseen environments using deep reinforcement learning","volume":"18","author":"Ali","year":"2024","journal-title":"World Acad. Sci. Eng. Technol. Int. J. Comput. Syst. Eng."},{"key":"ref_16","unstructured":"Xu, Z., Liu, B., Xiao, X., Nair, A., and Stone, P. (June, January 29). Benchmarking Reinforcement Learning Techniques for Autonomous Navigation. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), London, UK."},{"key":"ref_17","first-page":"1582","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","volume":"Volume 80","author":"Fujimoto","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1109\/LRA.2021.3133591","article-title":"Goal-Driven Autonomous Exploration Through Deep Reinforcement Learning","volume":"7","author":"Cimurs","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_19","unstructured":"Cimurs, R. (2025, March 24). DRL-Robot-Navigation. GitHub Repository. Available online: https:\/\/github.com\/reiniscimurs\/DRL-robot-navigation."},{"key":"ref_20","unstructured":"Anas, H., Hong, O.W., and Malik, O.A. (2023). Deep Reinforcement Learning-Based Mapless Crowd Navigation with Perceived Risk of the Moving Crowd for Mobile Robots. arXiv."},{"key":"ref_21","unstructured":"Zerosansan (2025, March 24). TD3, DDPG, SAC, DQN, Q-Learning, SARSA Mobile Robot Navigation. GitHub Repository. Available online: https:\/\/github.com\/zerosansan\/td3_ddpg_sac_dqn_qlearning_sarsa_mobile_robot_navigation."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"26871","DOI":"10.1109\/ACCESS.2021.3056903","article-title":"Motion Planning for Dual-Arm Robot Based on Soft Actor-Critic","volume":"9","author":"Wong","year":"2021","journal-title":"IEEE Access"},{"key":"ref_23","unstructured":"Sylabs (2025, March 24). Installing SingularityCE. Available online: https:\/\/docs.sylabs.io\/guides\/latest\/admin-guide\/installation.html#installation-on-linux."},{"key":"ref_24","unstructured":"Daffan, F. (2025, March 24). ros_jackal. GitHub Repository. Available online: https:\/\/github.com\/Daffan\/ros_jackal."},{"key":"ref_25","unstructured":"Ali, R. (2025, March 24). Extended-ROS-Jackal-Environment. GitHub Repository. Available online: https:\/\/github.com\/Romisaa-Ali\/Extended-ROS-Jackal-Environment."},{"key":"ref_26","unstructured":"Xu, Z., Liu, B., Xiao, X., Nair, A., and Stone, P. (2025, March 24). Benchmarking Reinforcement Learning Techniques for Autonomous Navigation. Available online: https:\/\/cs.gmu.edu\/~xiao\/Research\/RLNavBenchmark\/."},{"key":"ref_27","unstructured":"Daffan, F. (2025, March 24). ROS Jackal: Competition Package. GitHub Repository. Available online: https:\/\/github.com\/Daffan\/ros_jackal\/tree\/competition."},{"key":"ref_28","unstructured":"(2025, March 24). Clearpath Robotics. Simulating Jackal in Gazebo. Available online: https:\/\/docs.clearpathrobotics.com\/docs\/ros1noetic\/robots\/outdoor_robots\/jackal\/tutorials_jackal\/#simulating-jackal."},{"key":"ref_29","unstructured":"Open Source Robotics Foundation (2025, March 24). move_base. ROS Wiki. n.d. Available online: https:\/\/wiki.ros.org\/move_base."},{"key":"ref_30","unstructured":"Zenodo (2025, March 24). Robot Navigation Using TD3 with MoveBase Integration in ENV2. February 2025. Available online: https:\/\/zenodo.org\/records\/14881795."}],"container-title":["Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-6581\/14\/4\/43\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:06:36Z","timestamp":1760029596000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-6581\/14\/4\/43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["robotics14040043"],"URL":"https:\/\/doi.org\/10.3390\/robotics14040043","relation":{},"ISSN":["2218-6581"],"issn-type":[{"value":"2218-6581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,31]]}}}