LEADER: 不確実性下の計画のための運転行動への注意学習
LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty
自動運転の計画において、重要だが稀な人間の行動に注意を向けるニューラルネットワークをミニマックスゲームで学習し、安全な計画を実現する手法。
著者: Mohamad H. Danesh, Panpan Cai, David Hsu
分類: cs.LG, cs.RO
原文アブストラクト
Uncertainty on human behaviors poses a significant challenge to autonomous driving in crowded urban environments. The partially observable Markov decision processes (POMDPs) offer a principled framework for planning under uncertainty, often leveraging Monte Carlo sampling to achieve online performance for complex tasks. However, sampling also raises safety concerns by potentially missing critical events. To address this, we propose a new algorithm, LEarning Attention over Driving bEhavioRs (LEADER), that learns to attend to critical human behaviors during planning. LEADER learns a neural network generator to provide attention over human behaviors in real-time situations. It integrates the attention into a belief-space planner, using importance sampling to bias reasoning towards critical events. To train the algorithm, we let the attention generator and the planner form a min-max game. By solving the min-max game, LEADER learns to perform risk-aware planning without human labeling.
