基于FSGP-MPC考虑不确定性的轨迹规划方法
A Trajectory Planning Method Considering Uncertainties Based on FSGP-MPC
摘要: 在自动驾驶和机器人领域，局部轨迹规划中的不确定性处理是影响技术落地和安全的关键。本文针对外部环境障碍物预测结果的不确定性，提出了一种局部轨迹规划方法。该方法使用高斯过程模型预测障碍物信息，并基于高斯分布建模不确定性。通过量化障碍物预测结果的不确定性，并将其通过风险分配系数纳入控制系统，方法考虑了不确定性对轨迹规划的影响。同时，通过构建安全状态集和机会约束并结合模型预测控制(MPC)的动态约束处理能力，生成安全的局部轨迹。针对高斯过程模型样本有限的问题，本文结合高斯分布的矩集中界限理论收紧机会约束，确保即使在样本有限的情况下也能生成安全轨迹。
Abstract: In the fields of autonomous driving and robotics, handling uncertainties in local trajectory planning is crucial for the deployment and safety of these technologies. This paper proposes a local trajectory planning method that addresses the uncertainties in the predicted positions of external environmental obstacles. The method employs Gaussian Process (GP) models to predict obstacle information and uses Gaussian distributions to model uncertainties. By quantifying the uncertainties in obstacle predictions and incorporating them into the control system via risk allocation coefficients, the method accounts for the impact of these uncertainties on trajectory planning. Additionally, by constructing a safe state set and chance constraints, and leveraging the dynamic constraint handling capabilities of Model Predictive Control (MPC), the method generates safe local trajectories. To address the issue of limited samples in GP models, the paper tightens chance constraints using concentration bounds of Gaussian distribution moments, ensuring safe trajectory planning even with a finite number of samples.
文章引用：许天宏, 宋玮, 李朝阳. 基于FSGP-MPC考虑不确定性的轨迹规划方法[J]. 运筹与模糊学, 2025, 15(2): 610-619. https://doi.org/10.12677/orf.2025.152110

参考文献

[1] Van Aerde, M. and Yagar, S. (1988) Dynamic Integrated Freeway/Traffic Signal Networks: Problems and Proposed Solutions. Transportation Research Part A: General, 22, 435-443. [Google Scholar] [CrossRef] 
[2] Jha, S., Raman, V., Sadigh, D. and Seshia, S.A. (2017) Safe Autonomy under Perception Uncertainty Using Chance-Constrained Temporal Logic. Journal of Automated Reasoning, 60, 43-62. [Google Scholar] [CrossRef] 
[3] Sessa, P.G., Frick, D., Wood, T.A. and Kamgarpour, M. (2018) From Uncertainty Data to Robust Policies for Temporal Logic Planning. Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (Part of CPS Week), Porto, 11-13 April 2018, 157-166. [Google Scholar] [CrossRef] 
[4] Busch, F.L., Johnson, J., Zhu, E.L., et al. (2022) A Gaussian Process Model for Opponent Prediction in Autonomous Racing.
[5] Umlauft, J. and Hirche, S. (2020) Feedback Linearization Based on Gaussian Processes with Event-Triggered Online Learning. IEEE Transactions on Automatic Control, 65, 4154-4169. [Google Scholar] [CrossRef] 
[6] Carvalho, A., Gao, Y., Lefevre, S., et al. (2014) Stochastic Predictive Control of Autonomous Vehicles in Uncertain Environments. 12th International Symposium on Advanced Vehicle Control, Tokyo, 22-26 September 2014, 9.
[7] Blackmore, L., Ono, M. and Williams, B.C. (2011) Chance-Constrained Optimal Path Planning with Obstacles. IEEE Transactions on Robotics, 27, 1080-1094. [Google Scholar] [CrossRef] 
[8] Kolaric, P., Jing, J., Huang, C., Qu, S., Liu, J., Zhao, Y., et al. (2023) Gaussian Process Model of Uncertainty in Safety-Critical Autonomous Driving. 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, 24-28 September 2023, 4436-4442. [Google Scholar] [CrossRef] 
[9] Lefkopoulos, V. and Kamgarpour, M. (2021) Trajectory Planning under Environmental Uncertainty with Finite-Sample Safety Guarantees. Automatica, 131, Article 109754. [Google Scholar] [CrossRef] 
[10] Calafiore, G.C. and Ghaoui, L.E. (2006) On Distributionally Robust Chance-Constrained Linear Programs. Journal of Optimization Theory and Applications, 130, 1-22. [Google Scholar] [CrossRef] 

为你推荐