日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

自動運転arXiv:2410.22752

SoftCTRL: 自動運転のためのTransformer強化学習におけるソフト保守的KL制御

SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving

シェア:XThreadsFacebookLINEはてブBluesky

模倣学習と強化学習をKL制御で組み合わせ、過度な保守性を抑えて都市自動運転の安全性と人間らしさを向上させる手法を提案。

著者: Minh Tri Huynh, Duc Dung Nguyen

分類: cs.RO, cs.AI

原文アブストラクト

In recent years, motion planning for urban self-driving cars (SDV) has become a popular problem due to its complex interaction of road components. To tackle this, many methods have relied on large-scale, human-sampled data processed through Imitation learning (IL). Although effective, IL alone cannot adequately handle safety and reliability concerns. Combining IL with Reinforcement learning (RL) by adding KL divergence between RL and IL policy to the RL loss can alleviate IL's weakness but suffer from over-conservation caused by covariate shift of IL. To address this limitation, we introduce a method that combines IL with RL using an implicit entropy-KL control that offers a simple way to reduce the over-conservation characteristic. In particular, we validate different challenging simulated urban scenarios from the unseen dataset, indicating that although IL can perform well in imitation tasks, our proposed method significantly improves robustness (over 17\% reduction in failures) and generates human-like driving behavior.

関連論文

  1. 1Boston Dynamics、GlobalFoundriesでAtlasを試験へ 半導体製造で2027年初頭から半導体・GPU
  2. 2丸文、RealManのロボットアームやヒューマノイドを国内販売提携・買収
  3. 3NVIDIA、RTX Spark小型デスクトップを発売 ASUS、Dell、MSIから半導体・GPU
  4. 4NVIDIA、SC26で科学研究向けAIエージェントとHPC基盤を発表新製品・発表
  5. 5NVIDIA、科学・工学向けの新GPU「Rubin HPC」を発表半導体・GPU

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI