Research Analyzer
← Back ICRA 2026

MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure Recovery

Baiye Cheng, Tianhai Liang, Suning Huang, Maanping Shao, Feihong Zhang, Botian Xu, Zhengrong Xue, Huazhe Xu

PDF

AI summary

MoE-DP significantly improves robustness in long-horizon robotic manipulation by decomposing policies into specialized, interpretable skills that enable automatic failure recovery and flexible subtask reordering.
Mixture of Experts Diffusion Policy Robotic Manipulation Skill Decomposition Failure Recovery Long-Horizon Tasks

Problem

Standard diffusion policies lack stage-awareness and fail to recover from intermediate subtask failures in long-horizon tasks, often causing cascading errors due to entangled, uninterpretable representations.

Approach

The method inserts a Mixture of Experts layer between the visual encoder and diffusion model to dynamically route observations to specialized expert networks, enabling skill decomposition and recovery without re-training.

Key results

  • 36% average relative success rate improvement under simulated disturbances
  • Significant real-world robustness gains across multiple manipulation tasks
  • Clear mapping between specialized experts and semantic task primitives
  • Inference-time subtask rearrangement and generalization without re-training

Why it matters

Provides a scalable, interpretable framework for robust long-horizon robotic manipulation, enabling flexible high-level control and reliable recovery for real-world deployment.

Abstract

No abstract on file.

Index terms

Imitation Learning Learning from Demonstration Deep Learning in Grasping and Manipulation

Related papers