CarryOn, 개인화와 안전성을 갖춘 로봇 조작 하네스
CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance
- 매체
- arXiv
- 게시
- 중요도
- 3/5
- 화제 지수
- 4
한국어 요약
CarryOn은 비전-언어-액션(VLA) 정책을 보강하는 이중 루프 하네스다. 계획 루프는 사용자·장면 맥락을 유지해 개인화된 부작업 선택을 가능하게 하고, 실행 루프는 정책 롤아웃을 감시해 위험한 접촉을 차단한다. 실제 로봇 시험에서 안전 위반률을 52.6%에서 6.1%로, 복구 성공률을 13%에서 80%로 높였다.
원문 발췌 · English
While generalist vision-language-action (VLA) models have enabled diverse open-world manipulation, real-world robotic assistance requires two critical capabilities they currently lack: personalization and reliable execution. First, executing an instruction like "make me a sandwich" requires grounding subtask decomposition in persistent user preferences rather than relying on a single generic solution. Second, reliable deployment demands explainable safety assurance that proactively prevents hazards and gracefully recovers from occasional physical failures. To address these gaps, we present CarryOn, a dual-loop harness designed to augment a frozen VLA policy. The planning loop maintains persistent user-level and scene-level context that is continually grounded against new observations and revised through interaction, enabling personalized task selection and execution grounding across conversations and changing scenes. The execution loop actively supervises policy rollouts, shielding actions from predicted hazardous contact. When execution fails, the system invokes reusable control-based recovery skills that restore task progress and are refined through reflection on earlier failures. On a real robot and in simulation, CarryOn dispatches preference-consistent subtasks across users and scenes, reduces the violation rate of an already safety-finetuned VLA from 52.6% to 6.1%, and increases recovery success from 13% to 80% when refined skills are reused.