PACT-VLA: Speculative Action-Chunk Verification with Pre-Commit Observations
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
Vision-language-action (VLA) policies are commonly deployed with asynchronous inference in real-world settings, where the next action chunk is generated while the robot is still executing the previous one. By the time the new chunk is committed, the robot and scene have changed, so the chunk is conditioned on a stale observation and task success drops sharply as this inference delay grows.
초록에서 가져왔습니다. 요약을 준비 중입니다.
이 논문은 라이선스상 전문을 게재할 수 없어 요약과 원문 링크만 제공합니다.