计算机科学
模仿
模型预测控制
人在回路中
领域(数学分析)
控制工程
控制(管理)
控制理论(社会学)
强化学习
人工智能
工程类
心理学
社会心理学
数学分析
数学
作者
Flavia Sofia Acerbo,Jan Swevers,Tinne Tuytelaars,Tong Duy Son
出处
期刊:Cornell University - arXiv
日期:2022-06-24
标识
DOI:10.48550/arxiv.2206.12348
摘要
To ensure user acceptance of autonomous vehicles (AVs), control systems are being developed to mimic human drivers from demonstrations of desired driving behaviors. Imitation learning (IL) algorithms serve this purpose, but struggle to provide safety guarantees on the resulting closed-loop system trajectories. On the other hand, Model Predictive Control (MPC) can handle nonlinear systems with safety constraints, but realizing human-like driving with it requires extensive domain knowledge. This work suggests the use of a seamless combination of the two techniques to learn safe AV controllers from demonstrations of desired driving behaviors, by using MPC as a differentiable control layer within a hierarchical IL policy. With this strategy, IL is performed in closed-loop and end-to-end, through parameters in the MPC cost, model or constraints. Experimental results of this methodology are analyzed for the design of a lane keeping control system, learned via behavioral cloning from observations (BCO), given human demonstrations on a fixed-base driving simulator.
科研通智能强力驱动
Strongly Powered by AbleSci AI