SUN: Persistent Programs For Language-Grounded Control-to-Learning-to-Real Policies

2026-08-31

AI Summary

该研究通过引入SUN程序，统一了控制和学习策略中的任务语义，解决了长时操作中模型控制与学习策略之间的不一致问题。

Abstract

Bridging model-based control and learned policies in long-horizon manipulation has harbored a silent disagreement: control executes specified objectives, learning amortizes that behavior into a reactive policy, yet existing protocols discard task semantics, leaving rewards hand-crafted and behavior drifting from what control verified.We introduce Semantically UNified (SUN) Programs, typed executables where geometric and contact relations are defined once and compiled into aligned Model Predictive Control (MPC) costs, satisfaction predicates, RL rewards, transition guards, and diagnostics. Our system, Kuafu, driven by large vision language systems, automatically synthesizes SUN Programs from language and scene semantics, screens feasibility via MPC, and retains semantics while training stage-conditioned policies. Across nine tasks, Kuafu achieves 82.03% macro-success, outperforming sparse-reward (35.67%) and Stage-BC (24.75%) baselines. At 8192-way scale, it generates 10.57x the successful trajectory time per hour of human teleoperation. With 500 trajectories per task, Kuafu data trains DP3 policies to 46.0% simulation success (vs. 22.4% for alternatives) and 34.7% on physical Franka and Kinova robots. These results establish that simulation-screened task semantics can effectively amortize control into robust policies, without demonstrations or manual dense rewards, unifying symbolic planning and data-driven execution.

Problem

• Model-based Control
• Learned Policies
• Task Semantics
• Long-horizon Manipulation

Innovation

• SUN Programs
• Model Predictive Control (MPC)
• semantic unification
• automated synthesis
• stage-conditioned policies