日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

視覚オドメトリarXiv:2408.17005

深層強化学習による視覚オドメトリのための効率的なカメラ露出制御

Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement Learning

シェア:XThreadsFacebookLINEはてブBluesky

深層強化学習でカメラ露出を制御するエージェントを訓練し、照明変化の激しい環境でも視覚オドメトリを安定・高精度化する手法を提案。軽量シミュレータでオフライン訓練を可能にし、CPUで1フレーム1.58msの高速推論を実現。

著者: Shuyang Zhang, Jinhao He, Yilong Zhu, Jin Wu, Jie Yuan

分類: cs.RO, cs.CV

原文アブストラクト

The stability of visual odometry (VO) systems is undermined by degraded image quality, especially in environments with significant illumination changes. This study employs a deep reinforcement learning (DRL) framework to train agents for exposure control, aiming to enhance imaging performance in challenging conditions. A lightweight image simulator is developed to facilitate the training process, enabling the diversification of image exposure and sequence trajectory. This setup enables completely offline training, eliminating the need for direct interaction with camera hardware and the real environments. Different levels of reward functions are crafted to enhance the VO systems, equipping the DRL agents with varying intelligence. Extensive experiments have shown that our exposure control agents achieve superior efficiency-with an average inference duration of 1.58 ms per frame on a CPU-and respond more quickly than traditional feedback control schemes. By choosing an appropriate reward function, agents acquire an intelligent understanding of motion trends and anticipate future illumination changes. This predictive capability allows VO systems to deliver more stable and precise odometry results. The codes and datasets are available at https://github.com/ShuyangUni/drl_exposure_ctrl.

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. 2newmo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
  3. 3GXO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
  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