StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation

2026-09-17

AI Summary

为解决长周期机器人任务中阶段转换问题，提出StageGuard方法，通过代理蒸馏框架结合大规模视觉语言模型和示例轨迹生成紧凑自解释，提高阶段转换预测准确性与效率。

Abstract

Hierarchical planning frameworks combine skills from multiple robot control policies for long-horizon task execution, where determining when to terminate the current skill and advance to the next subtask is essential. Existing approaches often rely on pre-designed completion signal checkers that are hard to obtain in real-world execution. Large-scale vision-language models (VLMs) offer strong reasoning capabilities, but their decision boundaries are not inherently aligned with task completion criteria, while cloud deployment and lengthy reasoning introduce substantial latency, limiting real-time monitoring. We propose StageGuard, an agentic distillation framework for accurate and efficient stage-transition decisions. StageGuard combines teacher-model reasoning with demonstration trajectories to generate structured explanations of subtask completion and policy switching. A lightweight student VLM uses these explanations to generate compact self-explanations, which are used for supervised fine-tuning. We evaluate stage-transition prediction on trajectories from two benchmarks and assess closed-loop task success through integration into hierarchical robot control on BEHAVIOR-1K, with further validation on real robots. Results show substantial improvements in stage-transition prediction while supporting efficient online monitoring.

Problem

• long-horizon task execution
• stage transition
• real-time monitoring

Innovation

• Agentic Distillation
• Stage Transition
• Hierarchical Planning
• Visual-Language Models
• Real-time Monitoring