用无分类器引导提升扩散策略的时序控制能力
Enhancing Diffusion Policy with Classifier-Free Guidance for Temporal Robotic Tasks
- 引入无分类器引导机制，利用时间步跟踪任务进展
- 实测在人形机器人上实现高成功率与极少重复动作
- 适合需要精准时序控制的机器人任务场景
时序顺序任务对人形机器人构成挑战，现有扩散策略（DP）和基于Transformer的动作分块方法（ACT）常因缺乏时序上下文而陷入局部最优并产生过多重复动作。本文提出一种基于无分类器引导的扩散策略（CFG-DP），通过将无分类器引导与条件/无条件模型结合，利用时间步输入追踪任务进展，动态调整动作预测，指导因子可调节以平衡时序连贯性与动作准确性。真实人形机器人实验表明，该框架显著提升任务成功率，减少重复动作；同时评估了动作终止能力及各组件对性能的影响。整体提升了序列化机器人任务的确定性控制与执行可靠性。
原文摘要 · Abstract (English)
Temporal sequential tasks challenge humanoid robots, as existing Diffusion Policy (DP) and Action Chunking with Transformers (ACT) methods often lack temporal context, resulting in local optima traps and excessive repetitive actions. To address these issues, this paper introduces a Classifier-Free Guidance-Based Diffusion Policy (CFG-DP), a novel framework to enhance DP by integrating Classifier-Free Guidance (CFG) with conditional and unconditional models. Specifically, CFG leverages timestep inputs to track task progression and ensure precise cycle termination. It dynamically adjusts action predictions based on task phase, using a guidance factor tuned to balance temporal coherence and action accuracy. Real-world experiments on a humanoid robot demonstrate high success rates and minimal repetitive actions. Furthermore, we assessed the model's ability to terminate actions and examined how different components and parameter adjustments affect its performance. This framework significantly enhances deterministic control and execution reliability for sequential robotic tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。