SNeRL: 強化学習のための意味論認識型ニューラル放射輝度場
SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
多視点画像から意味論と物体中心の3D暗黙表現をNeRFと畳み込みエンコーダで同時学習し、強化学習の性能を向上させる手法を提案。
著者: Dongseok Shim, Seungjae Lee, H. Jin Kim
分類: cs.LG, cs.AI, cs.CV, cs.RO
原文アブストラクト
As previous representations for reinforcement learning cannot effectively incorporate a human-intuitive understanding of the 3D environment, they usually suffer from sub-optimal performances. In this paper, we present Semantic-aware Neural Radiance Fields for Reinforcement Learning (SNeRL), which jointly optimizes semantic-aware neural radiance fields (NeRF) with a convolutional encoder to learn 3D-aware neural implicit representation from multi-view images. We introduce 3D semantic and distilled feature fields in parallel to the RGB radiance fields in NeRF to learn semantic and object-centric representation for reinforcement learning. SNeRL outperforms not only previous pixel-based representations but also recent 3D-aware representations both in model-free and model-based reinforcement learning.
