Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation
Source abstract
Abstract
This study presents an approach to autonomous navigation for wheeled robots, combining radar-based dynamic obstacle detection with a BiGRU-based deep reinforcement learning (DRL) framework. Using filtering and tracking algorithms, the proposed system leverages radar sensors to cluster object points and track dynamic obstacles, enhancing precision by reducing noise and fluctuations. A BiGRU-enabled DRL model is introduced, allowing the robot to process sequential environmental data and make informed decisions in dynamic and unpredictable environments, achieving collision-free paths and reaching the goal. Simulation and experimental results validate the proposed method’s efficiency and adaptability, highlighting its potential for real-world applications in dynamic scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotic Path Planning Algorithms · Autonomous Vehicle Technology and Safety · Robotics and Sensor-Based Localization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Republic of Korea
Facultad de Ingeniería en Electricidad y Computación, Escuela Superior Politécnica del Litoral (ESPOL), Campus Gustavo Galindo, Guayaquil P.O. Box 09-01-5863, Ecuador
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of Korea
Facultad de Ingeniería Mecánica y Ciencias de la Producción, Escuela Superior Politécnica del Litoral (ESPOL), Campus Gustavo Galindo, Guayaquil P.O. Box 09-01-5863, Ecuador
Faculty of Engineering, Catholic University of Santiago de Guayaquil, Guayaquil 090603, Ecuador
Funding
MSIT (Ministry of Science and ICT), Korea
References (49)
Show source-provided references
1. Tan, Y., Lew, B., Tan, K., Goh, K., Lee, K., and Khor, Z. (2010, January 20–21). A new automated food delivery system using autonomous track guided centre-wheel drive robot. Proceedings of the 2010 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology, Kuala Lumpur, Malaysia.
2. Hunt, A.J., Bachmann, R.J., Murphy, R.R., and Quinn, R.D. (2011, January 25–30). A rapidly reconfigurable robot for assistance in urban search and rescue. Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, San Francisco, CA, USA.10.1109/IROS.2011.6048772 ↗
3. Jeon, J., Jung, H.R., Luong, T., and Moon, H. (2024). Task-Motion Planning System for Socially Viable Service Robots Based on Object Manipulation. Biomimetics, 9.10.3390/biomimetics9070436 ↗
4. Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey10.1109/TNNLS.2022.3167688 ↗
5. Radar sensing for intelligent vehicles in urban environments10.3390/s150614661 ↗
6. Radar-based pedestrian and vehicle detection and identification for driving assistance10.3390/vehicles6030056 ↗
7. Glira, P., Weidinger, C., and Hofbauer, C. (2023, January 6–10). Robust 3D Mobile Mapping with Radar Sensors: A Real-Time Approach for Autonomous Navigation. Proceedings of the 2023 IEEE International Radar Conference (radar), Sydney, Australia.10.1109/RADAR54928.2023.10371041 ↗
8. Li, Y., Zhuang, W., and Yang, G. (2024). MS3D: A Multi-Scale Feature Fusion 3D Object Detection Method for Autonomous Driving Applications. Appl. Sci., 14.10.3390/app142210667 ↗
9. Pico, N., Lee, J., Montero, E., Auh, E., Tadese, M., Jeon, J., Alvarez-Alvarado, M.S., and Moon, H. (2023, January 17–20). Enhancing Autonomous Robot Navigation based on Deep Reinforcement Learning: Comparative Analysis of Reward Functions in Diverse Environments. Proceedings of the 2023 23rd International Conference on Control, Automation and Systems (ICCAS), Yeosu, Republic of Korea.10.23919/ICCAS59377.2023.10316876 ↗
10. Jaradat, M.A., Gruyer, D., and Najjaran, H. (2020). Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review. Sensors, 20.10.3390/s20154220 ↗
11. Costa, M.M., and Silva, M.F. (2019, January 24–26). A Survey on Path Planning Algorithms for Mobile Robots. Proceedings of the 19th IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2019, Porto, Gondomar.10.1109/ICARSC.2019.8733623 ↗
12. Pico, N., Park, S.H., Yi, J.S., and Moon, H. (2022). Six-Wheel Robot Design Methodology and Emergency Control to Prevent the Robot from Falling down the Stairs. Appl. Sci., 12.10.3390/app12094403 ↗
13. Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios10.1177/0278364920916531 ↗
14. Yao, S., Chen, G., Qiu, Q., Ma, J., Chen, X., and Ji, J. (October, January 27). Crowd-aware robot navigation for pedestrians with multiple collision avoidance strategies via map-based deep reinforcement learning. Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic.10.1109/IROS51168.2021.9636579 ↗
15. Steinbaeck, J., Steger, C., Holweg, G., and Druml, N. (2017, January 10–12). Next generation radar sensors in automotive sensor fusion systems. Proceedings of the 2017 Sensor Data Fusion: Trends, Solutions, Applications (SDF), Bonn, Germany.10.1109/SDF.2017.8126389 ↗
16. Barnes, D., Gadd, M., Murcutt, P., Newman, P., and Posner, I. (August, January 31). The oxford radar robotcar dataset: A radar extension to the oxford robotcar dataset. Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France.10.1109/ICRA40945.2020.9196884 ↗
17. Meyer, M., and Kuschk, G. (2019, January 2–4). Automotive radar dataset for deep learning based 3d object detection. Proceedings of the 2019 16th European Radar Conference (EuRAD), Paris, France.
18. Sheeny, M., De Pellegrin, E., Mukherjee, S., Ahrabian, A., Wang, S., and Wallace, A. (June, January 30). RADIATE: A Radar Dataset for Automotive Perception in Bad Weather. Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), Xian, China.10.1109/ICRA48506.2021.9562089 ↗
19. The CornerGuard: Seeing around Corners to Prevent Broadside Collisions10.3390/vehicles6030069 ↗
20. Liu, K., Zhang, Y., Tan, A., Sun, Z., Ding, C., and Chen, J. (2020, January 4–6). Micro-doppler feature and image based human activity classification with FMCW radar. Proceedings of the IET International Radar Conference (IET IRC 2020), Online.10.1049/icp.2021.0555 ↗
21. Radar-ID: Human identification based on radar micro-Doppler signatures using deep convolutional neural networks10.1049/iet-rsn.2017.0511 ↗
22. Indoor person identification using a low-power FMCW radar10.1109/TGRS.2018.2816812 ↗
23. Singh, A.D., Sandha, S.S., Garcia, L., and Srivastava, M. (2019, January 25). Radhar: Human activity recognition from point clouds generated through a millimeter-wave radar. Proceedings of the 3rd ACM Workshop on Millimeter-Wave Networks and Sensing Systems, Los Cabos, Mexico.10.1145/3349624.3356768 ↗
24. Indoor detection and tracking of people using mmwave sensor10.1155/2021/6657709 ↗
25. Real-time people tracking and identification from sparse mm-wave radar point-clouds10.1109/ACCESS.2021.3083980 ↗
26. High precision human detection and tracking using millimeter-wave radars10.1109/MAES.2020.3021322 ↗
27. Enhancement over DBSCAN satellite spatial data clustering10.1155/2024/2330624 ↗
28. A multi-target detection and position tracking algorithm based on mmWave-FMCW radar data10.1016/j.measurement.2024.114797 ↗
29. Motion planning for mobile robots—Focusing on deep reinforcement learning: A systematic review10.1109/ACCESS.2021.3076530 ↗
30. Social force model for pedestrian dynamics10.1103/PhysRevE.51.4282 ↗
31. Van den Berg, J., Lin, M., and Manocha, D. (2008, January 21–25). Reciprocal velocity obstacles for real-time multi-agent navigation. Proceedings of the 2008 IEEE International Conference on Robotics and Automation, Brisbane, Australia.10.1109/ROBOT.2008.4543489 ↗
32. Berg, J.v.d., Guy, S.J., Lin, M., and Manocha, D. (2011). Reciprocal n-body collision avoidance. Robotics Research, Springer.10.1007/978-3-642-19457-3_1 ↗
33. Deep-learned collision avoidance policy for distributed multiagent navigation10.1109/LRA.2017.2651371 ↗
34. Tai, L., Zhang, J., Liu, M., and Burgard, W. (2018, January 21–25). Socially compliant navigation through raw depth inputs with generative adversarial imitation learning. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia.10.1109/ICRA.2018.8460968 ↗
35. Li, K., Xu, Y., Wang, J., and Meng, M.Q. (2019, January 10–14). SARL*: Deep reinforcement learning based human-aware navigation for mobile robot in indoor environments. Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO), Bangkok, Thailand.10.1109/ROBIO49542.2019.8961764 ↗
36. Cao, C., Trautman, P., and Iba, S. (2019, January 20–24). Dynamic channel: A planning framework for crowd navigation. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.10.1109/ICRA.2019.8794192 ↗
37. Chen, Y.F., Everett, M., Liu, M., and How, J.P. (October, January 24). Socially aware motion planning with deep reinforcement learning. Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada.10.1109/IROS.2017.8202312 ↗
38. Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Li, F.-F., and Savarese, S. (2016, January 27–30). Social lstm: Human trajectory prediction in crowded spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.110 ↗
39. Everett, M., Chen, Y.F., and How, J.P. (2018, January 1–5). Motion planning among dynamic, decision-making agents with deep reinforcement learning. Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.10.1109/IROS.2018.8593871 ↗
40. Chen, C., Liu, Y., Kreiss, S., and Alahi, A. (2019, January 20–24). Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.10.1109/ICRA.2019.8794134 ↗
41. Pico, N., Lee, B., Montero, E., Tadese, M., Auh, E., Doh, M., and Moon, H. (2023, January 25–28). Static and Dynamic Collision Avoidance for Autonomous Robot Navigation in Diverse Scenarios based on Deep Reinforcement Learning. Proceedings of the 2023 20th International Conference on Ubiquitous Robots (UR), Honolulu, HI, USA.10.1109/UR57808.2023.10202431 ↗
42. Faust, A., Oslund, K., Ramirez, O., Francis, A., Tapia, L., Fiser, M., and Davidson, J. (2018, January 21–25). Prm-rl: Long-range robotic navigation tasks by combining reinforcement learning and sampling-based planning. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia.10.1109/ICRA.2018.8461096 ↗
43. Long-range indoor navigation with prm-rl10.1109/TRO.2020.2975428 ↗
44. Dynamic warning zone and a short-distance goal for autonomous robot navigation using deep reinforcement learning10.1007/s40747-023-01216-y ↗
45. Collision Avoidance Among Dense Heterogeneous Agents Using Deep Reinforcement Learning10.1109/LRA.2022.3222989 ↗
46. Fletcher, T. (2010). The kalman filter explained. Technical Report, University College London.
47. Jin, F., Zhang, R., Sengupta, A., Cao, S., Hariri, S., Agarwal, N.K., and Agarwal, S.K. (2019, January 22–26). Multiple patients behavior detection in real-time using mmWave radar and deep CNNs. Proceedings of the 2019 IEEE Radar Conference (RadarConf), Boston, MA, USA.10.1109/RADAR.2019.8835656 ↗
48. Chen, Y.F., Liu, M., Everett, M., and How, J.P. (June, January 29). Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. Proceedings of the 2017 IEEE international conference on robotics and automation (ICRA), Singapore.10.1109/ICRA.2017.7989037 ↗
49. A fusion method of local path planning for mobile robots based on LSTM neural network and reinforcement learning10.1155/2021/5524232 ↗