Encoding Predictability and Legibility for Style-Conditioned Diffusion Policy

TL;DR

This paper introduces SCDP, a modular diffusion-based framework that dynamically balances robot motion efficiency and legibility in human-robot collaboration, improving safety and trust without retraining core policies.

Contribution

The authors propose a post-training, scene-aware diffusion policy that modulates robot trajectories for clarity or efficiency based on environment ambiguity.

Findings

Enhances legibility in ambiguous scenarios

Maintains efficiency in low-ambiguity environments

Operates without retraining the base policy

Abstract

Striking a balance between efficiency and transparent motion is a core challenge in human-robot collaboration, as highly expressive movements often incur unnecessary time and energy costs. In collaborative environments, legibility allows a human observer a better understanding of the robot's actions, increasing safety and trust. However, these behaviors result in sub-optimal and exaggerated trajectories that are redundant in low-ambiguity scenarios where the robot's goal is already obvious. To address this trade-off, we propose Style-Conditioned Diffusion Policy (SCDP), a modular framework that constrains the trajectory generation of a pre-trained diffusion model toward either legibility or efficiency based on the environment's configuration. Our method utilizes a post-training pipeline that freezes the base policy and trains a lightweight scene encoder and conditioning predictor to modulate the diffusion process. At inference time, an ambiguity detection module activates the appropriate conditioning, prioritizing expressive motion only for ambiguous goals and reverting to efficient paths otherwise. We evaluate SCDP on manipulation and navigation tasks, and results show that it enhances legibility in ambiguous settings while preserving optimal efficiency when legibility is unnecessary, all without retraining the base policy.