arXiv cs.AI· Hooman Hamze, Benjamin Houshmand, Deepthi Pathare, Erik B\"orve, Morteza Haghir Chehreghani, Nikolce Murgovski·· 3 小时前AI 评分37
用学习型终端代价改进自动驾驶卡车短时程 MPC 的混合 MPC-RL 框架
Learned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic
AI 导读
一项 arXiv 论文提出混合 MPC 与 RL 框架，用于自动驾驶卡车的高速公路行驶：有限时程 MPC 通过动态规划求解，并使用预训练 RL 模型估计终端代价。在含反应式周围交通的仿真环境中，该方法与零终端代价纯 MPC、基础策略终端代价估计 rollout 及纯 RL 对比，实现零碰撞且总成本最低。RL 弥补了 MPC 短时程约束下的长期决策不足，同时保留了约束满足能力。
正文 · 原文
Abstract:Autonomous highway driving for heavy-duty trucks is a challenging control problem. The greater mass, dimensions and intricate dynamics increase the requirements for cooperation from surrounding traffic in critical maneuvers, requiring a careful balance between safety constraints and efficient long-horizon decision making. Model Predictive Control (MPC) provides rigorous constraint satisfaction but relies on terminal cost which can limit its effectiveness at short, computationally affordable horizons. Reinforcement Learning (RL) captures long-term driving behavior but offers no constraint guarantees and tends toward overly conservative policies when trained under sparse collision penalties. In this paper, we propose a hybrid MPC and RL framework for highway driving in autonomous trucks, where a finite-horizon MPC, solved via dynamic programming, uses a pre-trained RL model for terminal cost estimation. We evaluate the framework in a simulation environment with reactive surrounding traffic and compare it against pure MPC with zero terminal cost, rollout with terminal cost estimation using a base policy, and pure RL. Results show that the hybrid approach achieves zero collisions with the lowest cost of any configuration.
| Comments: | 13 pages, 2 figures, 8 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO); Systems and Control (eess.SY) |
| ACM classes: | I.2.6; I.2.8 |
| Cite as: | arXiv:2610.40257 [cs.LG] |
| (or arXiv:2610.40257v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40257 arXiv-issued DOI via DataCite |
Submission history
From: Benjamin Houshmand [view email]
[v1]
Thu, 29 Oct 2026 15:23:51 UTC (1,155 KB)
来源：arXiv cs.AI · arxiv.org