Trace-Focused Diffusion Policy for Multi-Modal Action Disambiguation in Long-Horizon Robotic Manipulation

TL;DR

This paper introduces TF-DP, a diffusion-based policy that conditions on execution history to disambiguate actions in long-horizon robotic tasks, significantly improving robustness and consistency in visually complex environments.

Contribution

The paper proposes a trace-focused diffusion policy that explicitly incorporates execution history, addressing multi-modal action ambiguity in long-horizon robotic manipulation.

Findings

80.56% improvement over vanilla diffusion policy in ambiguous tasks

86.11% robustness increase under visual disturbances

Only 6.4% increase in inference runtime

Abstract

Generative model-based policies have shown strong performance in imitation-based robotic manipulation by learning action distributions from demonstrations. However, in long-horizon tasks, visually similar observations often recur across execution stages while requiring distinct actions, which leads to ambiguous predictions when policies are conditioned only on instantaneous observations, termed multi-modal action ambiguity (MA2). To address this challenge, we propose the Trace-Focused Diffusion Policy (TF-DP), a simple yet effective diffusion-based framework that explicitly conditions action generation on the robot's execution history. TF-DP represents historical motion as an explicit execution trace and projects it into the visual observation space, providing stage-aware context when current observations alone are insufficient. In addition, the induced trace-focused field emphasizes task-relevant regions associated with historical motion, improving robustness to background visual disturbances. We evaluate TF-DP on real-world robotic manipulation tasks exhibiting pronounced multi-modal action ambiguity and visually cluttered conditions. Experimental results show that TF-DP improves temporal consistency and robustness, outperforming the vanilla diffusion policy by 80.56 percent on tasks with multi-modal action ambiguity and by 86.11 percent under visual disturbances, while maintaining inference efficiency with only a 6.4 percent runtime increase. These results demonstrate that execution-trace conditioning offers a scalable and principled approach for robust long-horizon robotic manipulation within a single policy.