Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Real-time obstacle avoidance is a challenge in mobile robotics, as it is an ongoing process and remains difficult to achieve in crowded, dynamic environments, where conventional planning algorithms, such as local planners, often offer limited adaptability. This paper presents a Proximal Policy Optimization-based deep reinforcement learning approach for real-time obstacle avoidance for mobile robots. The proposed system is end-to-end policy learning based on inputs from LiDAR and other auxiliary sensors, and is trained in a Gazebo-ROS environment using domain randomization to enhance robustness to sim-to-real transfer. The framework was implemented on a TurtleBot3 Burger platform and tested both in simulation and in an indoor physical environment with varying numbers of obstacles. In simulation, the proposed policy achieved a success rate of 94.2%, a 68.6% reduction in collision rate compared to the Dynamic Window Approach baseline policy, a path efficiency of 16.5%, and a 14.6% reduction in average time to goal. In real experiments, the policy has maintained success rates above 88, even under high-density conditions. The optimized onboard inference pipeline achieved less than 20 ms latency and over 50 Hz throughput on embedded hardware. These results indicate that the proposed framework is a successful and computationally feasible solution to real-time robotic navigation in dynamic environments.

Keywords

Mobile robotics Deep reinforcement learning Proximal policy optimization Real-time navigation Obstacle avoidance

Article Details

How to Cite
BA, R., Mishra, P. ., Kalaimani, M., Juyal, P. ., Anjani, P. ., Dua, R. ., & Mamoria, P. . (2026). Real-time obstacle avoidance in mobile robots using deep reinforcement learning . Future Technology, 5(3), 69–76. Retrieved from https://fupubco.com/futech/article/view/797
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. J. Choi, G. Lee, and C. Lee, “Reinforcement learning-based dynamic obstacle avoidance and integration of path planning,” Intelligent Service Robotics, vol. 14, no. 4, pp. 663–677, 2021, https://doi.org/10.1007/s11370-021-00387-2
  2. G. Chen et al., “Deep reinforcement learning of map-based obstacle avoidance for mobile robot navigation,” SN Computer Science, vol. 2, p. 417, 2021, https://doi.org/10.1007/s42979-021-00865-2
  3. K. Zhu and T. Zhang, “Deep reinforcement learning based mobile robot navigation: A review,” Tsinghua Science and Technology, 2021. DOI: 10.26599/TST.2021.9010012
  4. L. Tai, G. Paolo, and M. Liu, “Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS), 2017, pp. 31–36. DOI: 10.1109/IROS.2017.8202134
  5. L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement learning: A survey,” Journal of Artificial Intelligence Research, vol. 4, pp. 237–285, 1996. https://doi.org/10.1613/jair.301
  6. L. Kästner et al., “Arena-rosnav: Towards deployment of deep-reinforcement-learning-based obstacle avoidance into conventional autonomous navigation systems,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS), 2021, pp. 6456–6463. DOI: 10.1109/IROS51168.2021.9636226
  7. M. Pfeiffer et al., “Reinforced imitation: Sample efficient deep reinforcement learning for map-less navigation by leveraging prior demonstrations,” IEEE Robotics and Automation Letters, vol. 3, no. 4, pp. 4423–4430, 2018, https://doi.org/10.1109/LRA.2018.2869643
  8. W. Zhao et al., “Sim-to-real transfer in deep reinforcement learning for robotics: A survey,” SSCI, 2020. DOI: 10.1109/SSCI47803.2020.9308468
  9. J. Ibarz et al., “How to train your robot with deep reinforcement learning: Lessons we have learned,” International Journal of Robotics Research, vol. 40, no. 4–5, pp. 698–721, 2021. https://doi.org/10.1177/0278364920987859
  10. J. Mendoza, P. Bustos, and D. Rodriguez-Losada, “Improving the accuracy of mobile robot localisation using laser range finder and RGB-D sensor fusion,” Sensors, vol. 19, no. 12, p. 2724, 2019, https://doi.org/10.3390/s19122724
  11. Zlotnik, H. Kim, and M. Sznaier, “Improving mobile robot localization in cluttered environments using inertial measurement units,” Robotics, vol. 10, no. 3, p. 96, 2021, doi: 10.3390/robotics10030096
  12. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint, arXiv:1707.06347, 2017. [Online]. Available: https://doi.org/10.48550/arXiv.1707.06347
  13. T. Wang, Q. Wu, and C. Liu, “Autonomous navigation for mobile robots using deep reinforcement learning,” Robotics and Autonomous Systems, vol. 127, p. 103506, 2020, https://doi.org/10.1016/j.robot.2020.103506
  14. N. Koenig and A. Howard, “Design and use paradigms for Gazebo, an open-source multi-robot simulator,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2004, pp. 2149–2154, https://doi.org/10.1109/IROS.2004.1389727
  15. J. Tobin et al., “Domain randomization for transferring deep neural networks from simulation to the real world,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp. 23–30, https://doi.org/10.1109/IROS.2017.8202130
  16. L. Tai, G. Paolo, and M. Liu, “Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp. 31–36, https://doi.org/10.1109/IROS.2017.8202134
  17. V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, no. 7540, pp. 529–533, 2015, https://doi.org/10.1038/nature14236
  18. M. Kollmitz et al., “Real-time navigation in crowded environments,” in 2015 IEEE International Conference on Robotics and Automation (ICRA), 2015, pp. 2880–2887, https://doi.org/10.1109/ICRA.2015.7139535
  19. Dosovitskiy et al., “CARLA: An open urban driving simulator,” in Proceedings of the 1st Conference on Robot Learning (CoRL), 2017, pp. 1–16. [Online]. Available: https://carla.org
  20. J. Kirkpatrick et al., “Overcoming catastrophic forgetting in neural networks,” Proceedings of the National Academy of Sciences, vol. 114, no. 13, pp. 3521–3526, 2017, https://doi.org/10.1073/pnas.1611835114
  21. T. Haarnoja et al., “Soft actor-critic algorithms and applications,” arXiv preprint, arXiv:1812.05905, 2018. [Online]. Available: https://arxiv.org/abs/1812.05905
  22. Anderson et al., “Explainable artificial intelligence for autonomous systems,” AI Magazine, vol. 40, no. 2, pp. 29–41, 2019, https://doi.org/10.1609/aimag.v40i2.2850