日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

軌道予測arXiv:2504.13785

振り返りによる学習:誤差フィードバックを用いた自動運転の軌道予測改善

Learning Through Retrospection: Improving Trajectory Prediction for Automated Driving with Error Feedback

シェア:XThreadsFacebookLINEはてブBluesky

自動運転の軌道予測において、過去の予測誤差をフィードバックとして活用し、推論時に系統的誤差を修正する「振り返り」手法を提案。nuScenesとArgoverseで最大31.9%の誤差低減を達成。

著者: Steffen Hagedorn, Aron Distelzweig, Marcel Hallgarten, Alexandru P. Condurache

分類: cs.RO, cs.AI, cs.CV

原文アブストラクト

In automated driving, predicting trajectories of surrounding vehicles supports reasoning about scene dynamics and enables safe planning for the ego vehicle. However, existing models handle predictions as an instantaneous task of forecasting future trajectories based on observed information. As time proceeds, the next prediction is made independently of the previous one, which means that the model cannot correct its errors during inference and will repeat them. To alleviate this problem and better leverage temporal data, we propose a novel retrospection technique. Through training on closed-loop rollouts the model learns to use aggregated feedback. Given new observations it reflects on previous predictions and analyzes its errors to improve the quality of subsequent predictions. Thus, the model can learn to correct systematic errors during inference. Comprehensive experiments on nuScenes and Argoverse demonstrate a considerable decrease in minimum Average Displacement Error of up to 31.9% compared to the state-of-the-art baseline without retrospection. We further showcase the robustness of our technique by demonstrating a better handling of out-of-distribution scenarios with undetected road-users.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  3. 3newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI