Multi-Modal Manipulation via Multi-Modal Policy Consensus

arXiv:2509.23468v3 Announce Type: replace-cross Abstract: Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalities such as vision can overwhelm sparse but critical signals like touch in contact-rich tasks, and monolithic architectures cannot flexibly incorporate new or missing modalities without retraining. Our method factorizes the policy into a set of diffusion models, each specialized for a single representation (e.g., vision or touch), and employs a router network that learns consensus weights to adaptively combine their contributions, enabling incremental of new representations. We evaluate our approach on simulated manipulation tasks in {RLBench}, as well as real-world tasks such as occluded object picking, in-hand spoon reorientation, and puzzle insertion, where it significantly outperforms feature-concatenation baselines on scenarios requiring multimodal reasoning. Our policy further demonstrates robustness to physical perturbations and sensor corruption. We further conduct perturbation-based importance analysis, which reveals adaptive shifts between modalities.

Related

• Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data
• HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
• Jump-Start Reinforcement Learning with Vision-Language-Action Regularization
• DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning

Source: arXiv cs.LG | 2026-04-17