Encoding Predictability and Legibility for Style-Conditioned Diffusion Policy
This addresses the problem of balancing motion transparency and efficiency for robots in collaborative environments, though it is incremental as it builds on pre-trained diffusion models.
The paper tackles the trade-off between efficiency and legibility in robot motion for human-robot collaboration by proposing Style-Conditioned Diffusion Policy (SCDP), a modular framework that adapts trajectory generation to prioritize legibility in ambiguous scenarios and efficiency otherwise, achieving enhanced legibility without sacrificing optimal efficiency.
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.