強化学習の事前分布で拡散モデルを洗練させる閉所駐車プランナー
A Diffusion-Refined Planner with Reinforcement Learning Priors for Confined-Space Parking
強化学習で事前学習した方策の行動分布を拡散モデルの訓練に組み込み、閉所での駐車計画の成功率と精度を高めつつ推論ステップを削減した手法を提案。
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: Mingyang Jiang, Yueyuan Li, Jiaru Zhang, Songan Zhang, Ming Yang
分類: cs.RO
原文アブストラクト
The growing demand for parking has increased the need for automated parking planning methods that can operate reliably in confined spaces. In restricted and complex environments, high-precision maneuvers are required to achieve a high success rate in planning, yet existing approaches often rely on explicit action modeling, which faces challenges when accurately modeling the optimal action distribution. In this paper, we propose DRIP, a diffusion-refined planner anchored in reinforcement learning (RL) prior action distribution, in which an RL-pretrained policy provides prior action distributions to regularize the diffusion training process. During the inference phase the denoising process refines these coarse priors into more precise action distributions. By steering the denoising trajectory through the reinforcement learning prior distribution during training, the diffusion model inherits a well-informed initialization, resulting in more accurate action modeling, a higher planning success rate, and reduced inference steps. We evaluate our approach across parking scenarios with varying degrees of spatial constraints. Experimental results demonstrate that our method significantly improves planning performance in confined-space parking environments while maintaining strong generalization in common scenarios.
関連論文
- SunnyParking: 人間らしい駐車のためのマルチショット軌道生成と運動状態認識自動運転/駐車計画
- BEV知覚を用いた自動駐車プランニング自動運転/駐車計画
