人間らしい自動運転のためのMPCベース模倣学習の評価
Evaluation of MPC-based Imitation Learning for Human-like Autonomous Driving
模倣学習と微分可能なモデル予測制御(MPC)を組み合わせ、人間らしい自動運転を実現する手法を評価した。開ループと閉ループの両方で安全性・快適性・人間らしさを測定し、閉ループ訓練による堅牢性向上も示した。
著者: Flavia Sofia Acerbo, Jan Swevers, Tinne Tuytelaars, Tong Duy Son
分類: cs.RO
原文アブストラクト
This work evaluates and analyzes the combination of imitation learning (IL) and differentiable model predictive control (MPC) for the application of human-like autonomous driving. We combine MPC with a hierarchical learning-based policy, and measure its performance in open-loop and closed-loop with metrics related to safety, comfort and similarity to human driving characteristics. We also demonstrate the value of augmenting open-loop behavioral cloning with closed-loop training for a more robust learning, approximating the policy gradient through time with the state space model used by the MPC. We perform experimental evaluations on a lane keeping control system, learned from demonstrations collected on a fixed-base driving simulator, and show that our imitative policies approach the human driving style preferences.
