GaP：一種以圖為策略的多智能體自學習框架，用於變分自動化任務

摘要

為了讓機器人在商業與工業應用中可靠運作，近期代理型程式碼系統的進展能否將可解釋的機器人程式設計與無模型策略的開放世界適應能力相結合？我們聚焦於「變異自動化」（VA），這類任務的物體幾何與姿勢變異程度高於固定自動化。在需持續且可靠執行的商業與工業應用中，無模型策略往往難以彌補VA任務的可靠性差距。受任務與運動規劃（TAMP）及機器人作業系統（ROS）之前研究的啟發，我們提出「圖形即策略」（GaP），這是一種多代理程式碼編排框架，能從模組化開放機器人技能庫（MORSL）中生成包含感知、規劃與控制節點的有向計算圖。GaP接著建立內部模擬環境，平行排練不同圖形結構的任務實例，以迭代優化圖形結構與參數，提升成功率與吞吐量。透過8項新的開放VA任務基準測試（4項模擬、4項真實場景）評估，結果顯示GaP能達到顯著優於基線的成功率。詳細資訊、程式碼與數據可參見線上資源：https://graph-robots.github.io/gap

English

For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot programming with the open-world adaptability of model-free policies? We focus on "Variational Automation" (VA), a class of tasks that have larger variations in object geometry and pose than fixed automation. Model-free policies often struggle to close the reliability gap for VA tasks, which must be executed persistently and reliably in commercial and industrial applications. Motivated by prior work on Task and Motion Planning (TAMP) and the Robot Operating System (ROS), we introduce Graph-as-Policy (GaP), a multi-agent coding harness that generates directed computation graphs with perception, planning, and control nodes from a Modular Open Robot Skill Library (MORSL). GaP then generates an internal simulation environment to rehearse task instances with different graphs in parallel to iteratively refine the graph structure and parameters to improve success rates and throughput. Evaluation with 8 new open VA task benchmarks, 4 in-simulation and 4 in real-world, suggests that GaP can achieve success rates that significantly outperform baselines. Details, code, and data can be found online: https://graph-robots.github.io/gap