AI Daybook
AI Daybook
오늘의 지면
논문Physical AI

COAP, 코드 기반 로봇 정책으로 재귀적 자기개선 실현

Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement

매체
arXiv
게시
중요도
3/5
화제 지수
5

한국어 요약

논문은 VLA와 에이전트 하네스 대신 순수 코드로 로봇 제어를 하는 Code-Only-as-Policy(COAP) 패러다임을 제안했다. 상태를 코드로 명시적으로 추적하고 제어 가능하게 하며, 과제별 라이브러리 재사용으로 능력을 누적시킬 수 있다. RoboDojo의 42개 양팔 작업에서 70.24% 성공률을 달성했다.

같은 소식, 다른 매체 · 2곳

원문 발췌 · English

Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run time. We propose a different view: the embodied world is an Embodied Turing Machine, whose tape is the robot and environment state and rules are the policy. If this state can be represented accurately, the decision making can be written entirely in code. We therefore propose Code-Only-as-Policy (COAP): code measures and tracks the robot, environment, and task state from camera images and proprioception, and makes every decision from it. The same code applies across episodes, and different tasks share one library without a VLM or VLA in the loop. Compared with VLAs and Agent Harnesses, we analyze three advantages of COAP: (i) Explicit State: the state can be stored in code; (ii) Execution: code makes decision making controllable, recovers from failures flexibly, and runs fast and cheaply online; (iii) Extensibility: new tasks reuse, inherit, or extend the shared library, so capabilities can accumulate over tasks. These advantages make COAP a suitable medium for recursive self-improvement (RSI): coding agents develop the library in a closed loop, and each change is explicit and controllable. On RoboDojo's 42 bimanual tasks, the resulting library reaches a success rate of 70.24% without a model at test time. The upper bound of COAP lies in how accurately the state is represented for decision making and how robust the code logic is. We thus propose COAP as a new paradigm for embodied tasks; since it applies across episodes, it can also serve as an efficient data engine for VLAs and Agent Harnesses.

#vla#embodied-ai#robot-control#code-policy
원문 기사 읽기
전체 보기 →