Encoding Predictability and Legibility for Style-Conditioned Diffusion Policy

2026-03-17

AI Summary

This work addresses the challenge of dynamically balancing action efficiency and readability in human-robot collaboration, where overly expressive motions become redundant in low-ambiguity scenarios. To this end, the authors propose Style-Conditioned Diffusion Policy (SCDP), a lightweight post-training framework built upon a frozen pre-trained diffusion policy. SCDP incorporates a scene encoder, a style-condition predictor, and an ambiguity-aware mechanism that adaptively modulates trajectory generation based on environmental ambiguity levels. This approach enables on-demand switching between efficient and legible motion styles without requiring retraining. Evaluated on manipulation and navigation tasks, SCDP significantly enhances motion readability in high-ambiguity settings while preserving near-optimal efficiency in low-ambiguity contexts, consistently outperforming fixed-style policies across diverse scenarios.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Manipulation
• Computer Vision: Diffusion Models for Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• legibility
• efficiency
• human-robot collaboration
• motion planning
• ambiguity

Innovation

• Style-Conditioned Diffusion Policy
• Legibility-Efficiency Trade-off
• Post-Training Conditioning
• Ambiguity-Aware Motion Generation
• Diffusion Policy Modulation