EEG-Based Inverse Reinforcement Learning for Safety-Oriented Global Path Planning in Dynamic Environments
Source abstract
Abstract
Recent advancements in lightweight electroencephalogram(EEG) signal classification have enabled real-time human–robot interaction, yet challenges persist in balancing computational efficiency and safety in dynamic path planning. This study proposes an EEG-based inverse reinforcement learning (EIRL) framework to simulate human navigation strategies by decoding neural decision preferences. The method integrates a pruned WNFG-SSCCNet-ADMM classifier for EEG signal mapping, apprenticeship learning for reward function extraction, and Q-learning for policy optimization. Experimental validation in an 8 × 8 FrozenLake-v1 environment demonstrates that EIRL reduces average path risk values by 50% compared with traditional reinforcement learning, achieving expert-level safety (Δ = 4) while maintaining optimal path lengths. The framework enhances adaptability in unknown environments by embedding human-like risk aversion into robotic planning, offering a robust solution for applications requiring minimal prior environmental knowledge. Results highlight the synergy between neural feedback and computational models, advancing inclusive human–robot collaboration in safety-critical scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Reinforcement Learning in Robotics · Robotic Path Planning Algorithms · EEG and Brain-Computer Interfaces
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of ASIC and Systems, The Institute of Brain-Inspired Circuits and Systems, Fudan University, Shanghai 201203, China
MOE Key Laboratory of Marine Intelligent Equipment and System, State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Funding
Science and Technology Commission of Shanghai Municipality · National Key Research and Development Program of China · National Natural Science Foundation of China · Guangdong Basic and Applied Basic Research Foundation
References (24)
Show source-provided references
1. Baldi, P., and Sadowski, P.J. (2013, January 3–8). Understanding dropout. Proceedings of the Advances in Neural Information Processing Systems (NIPS), Harrahs and Harveys, Lake Tahoe, VS, USA.
2. Yim, J., Joo, D., Bae, J., and Kim, J. (2017, January 21–26). A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.754 ↗
3. Seizure prediction using directed transfer function and convolution neural network on intracranial EEG10.1109/TNSRE.2020.3035836 ↗
4. A review of recurrent neural network-based methods in computational physiology10.1109/TNNLS.2022.3145365 ↗
5. Distributed optimization and statistical learning via the alternating direction method of multipliers10.1561/2200000016 ↗
6. Variable splitting methods for constrained state estimation in partially observed Markov processes10.1109/LSP.2020.3010159 ↗
7. Ye, S., Zhang, T., Zhang, K., Li, J., Xu, K., Yang, Y., Yu, F., Tang, J., Fardad, M., and Liu, S. (2018). Progressive weight pruning of deep neural networks using ADMM. arXiv.
8. Ssgcnet: A sparse spectra graph convolutional network for epileptic eeg signal classification10.1109/TNNLS.2023.3252569 ↗
9. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state10.1103/PhysRevE.64.061907 ↗
10. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals10.1161/01.CIR.101.23.e215 ↗
11. A first-order primal-dual algorithm for convex problems with applications to imaging10.1007/s10851-010-0251-1 ↗
12. SVM Tutorial-Classification, Regression and Ranking10.1007/978-3-540-92910-9_15 ↗
13. Yang, J., Yu, H., and Kunz, W. (2000, January 5–8). An efficient LDA algorithm for face recognition. Proceedings of the International Conference on Automation, Robotics, and Computer Vision (ICARCV 2000), Singapore.
14. EEG-based spatio–temporal convolutional neural network for driver fatigue evaluation10.1109/TNNLS.2018.2886414 ↗
15. Wright, S.J. (2006). Numerical Optimization, Springer.
16. Vandorpe, J., Van Brussel, H., and Xu, H. (1996, January 22–28). Exact dynamic map building for a mobile robot using geometrical primitives produced by a 2D range finder. Proceedings of the IEEE International Conference on Robotics and Automation, Minneapolis, MN, USA.
17. Liu, Z., Sun, M., Zhou, T., Huang, G., and Darrell, T. (2018). Rethinking the value of network pruning. arXiv.
18. What is the state of neural network pruning?
19. Zhang, T., Ye, S., Zhang, K., Tang, J., Wen, W., Fardad, M., and Wang, Y. (2018, January 8–14). A systematic dnn weight pruning framework using alternating direction method of multipliers. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01237-3_12 ↗
20. Sichkar, V.N. (2019, January 25–29). Reinforcement learning algorithms in global path planning for mobile robot. Proceedings of the 2019 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), Sochi, Russia.10.1109/ICIEAM.2019.8742915 ↗
21. Mobile robot path planning in dynamic environments through globally guided reinforcement learning10.1109/LRA.2020.3026638 ↗
22. Gao, P., Liu, Z., Wu, Z., and Wang, D. (2019, January 6–8). A global path planning algorithm for robots using reinforcement learning. Proceedings of the 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO), Dali, China.10.1109/ROBIO49542.2019.8961753 ↗
23. Abbeel, P., and Ng, A.Y. (2004, January 4–8). Apprenticeship learning via inverse reinforcement learning. Proceedings of the Twenty-First International Conference on Machine Learning, Banff, AB, Canada.10.1145/1015330.1015430 ↗
24. Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., and Zaremba, W. (2016). Openai gym. arXiv.