PDRVLA, 물리 역학 이해하는 로봇용 비전-언어-행동 모델
PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations
- 매체
- Hugging Face
- 게시
- 중요도
- 4/5
- 화제 지수
- 25
한국어 요약
Princeton 연구진이 물리 역학 표현을 통합한 로봇 행동 생성 모델 PDRVLA를 제시했다. 가벼운 물리 역학 모듈로 온라인 비디오 생성 없이 행동을 조건화하며, 공개 데이터로만 학습했다.
같은 소식, 다른 매체 · 1곳
원문 발췌 · English
Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited. Video world models can capture scene dynamics, yet generating future videos introduces high latency into the control loop. We introduce PDRVLA, whose lightweight Physical Dynamics Module extracts physical tokens from vision--language features to condition action generation without online video generation. The module learns through direct prediction of future RGB, depth, and optical-flow features, with auxiliary supervision through a frozen pretrained video world model. Training relies entirely on publicly available data, expanded through human-to-robot synthesis, subtask annotation, and embodied chain-of-thought (ECoT) annotation. Across four simulation benchmarks, PDRVLA achieves success rates of 99.3% on LIBERO, 89.9% on LIBERO-Plus, 93.6% on RoboTwin~2.0, and 81.5% on SimplerEnv. Ablations show improved future prediction with world-model supervision and evaluate how subtask conditioning, future object-pose supervision, and ECoT training affect action success.