IRL-DAL: エネルギー誘導拡散モデルによる自動運転のための安全で適応的な軌道計画
IRL-DAL: Safe and Adaptive Trajectory Planning for Autonomous Driving via Energy-Guided Diffusion Models
拡散モデルと逆強化学習を組み合わせ、FSMの模倣学習とPPO微調整により安全な経路計画を実現した自動運転フレームワーク。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Seyed Ahmad Hosseini Miangoleh, Amin Jalal Aghdasian, Farzaneh Abdollahi
分類: cs.RO, cs.AI
原文アブストラクト
This paper proposes a novel inverse reinforcement learning framework using a diffusion-based adaptive lookahead planner (IRL-DAL) for autonomous vehicles. Training begins with imitation from an expert finite state machine (FSM) controller to provide a stable initialization. Environment terms are combined with an IRL discriminator signal to align with expert goals. Reinforcement learning (RL) is then performed with a hybrid reward that combines diffuse environmental feedback and targeted IRL rewards. A conditional diffusion model, which acts as a safety supervisor, plans safe paths. It stays in its lane, avoids obstacles, and moves smoothly. Then, a learnable adaptive mask (LAM) improves perception. It shifts visual attention based on vehicle speed and nearby hazards. After FSM-based imitation, the policy is fine-tuned with Proximal Policy Optimization (PPO). Training is run in the Webots simulator with a two-stage curriculum. A 96\% success rate is reached, and collisions are reduced to 0.05 per 1k steps, marking a new benchmark for safe navigation. By applying the proposed approach, the agent not only drives in lane but also handles unsafe conditions at an expert level, increasing robustness.We make our code publicly available.
