深層逆強化学習によるMPC向け時空間コストマップ推論
Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learning
人間の運転デモから目標条件付き時空間報酬を逆強化学習で学習し、そのコストマップをMPCに用いて手設計なしで自然な自動運転行動を実現する手法を提案した。
著者: Keuntaek Lee, David Isele, Evangelos A. Theodorou, Sangjae Bae
分類: cs.RO, cs.AI
原文アブストラクト
It can be difficult to autonomously produce driver behavior so that it appears natural to other traffic participants. Through Inverse Reinforcement Learning (IRL), we can automate this process by learning the underlying reward function from human demonstrations. We propose a new IRL algorithm that learns a goal-conditioned spatiotemporal reward function. The resulting costmap is used by Model Predictive Controllers (MPCs) to perform a task without any hand-designing or hand-tuning of the cost function. We evaluate our proposed Goal-conditioned SpatioTemporal Zeroing Maximum Entropy Deep IRL (GSTZ)-MEDIRL framework together with MPC in the CARLA simulator for autonomous driving, lane keeping, and lane changing tasks in a challenging dense traffic highway scenario. Our proposed methods show higher success rates compared to other baseline methods including behavior cloning, state-of-the-art RL policies, and MPC with a learning-based behavior prediction model.
関連論文
- スタイルを学ぶ運転:自動運転の汎用プランニングにおける逆強化学習自動運転/逆強化学習
- 逆強化学習とDeep Q-Networkによる自動運転の学習自動運転/逆強化学習
