论文标题
基于MPC的模仿学习，以安全和类似人类的自动驾驶
MPC-based Imitation Learning for Safe and Human-like Autonomous Driving
论文作者
论文摘要
为了确保用户接受自动驾驶汽车（AV），正在开发控制系统以模仿所需驾驶行为的人类驾驶员。模仿学习（IL）算法达到了这个目的，但努力为由此产生的闭环系统轨迹提供安全保证。另一方面，模型预测控制（MPC）可以处理具有安全限制的非线性系统，但是用它来实现类似人类的驾驶需要广泛的领域知识。这项工作表明，通过将MPC用作分层IL策略中的可区分控制层，将两种技术的无缝组合从所需驾驶行为的演示中学习安全的AV控制器。通过此策略，IL通过MPC成本，模型或约束的参数在闭环和端到端进行。鉴于人类在固定碱驾驶模拟器上进行了示范，分析了通过行为克隆（BCO）来学习该方法的实验结果，以进行泳道保持控制系统的设计。
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.
