BiRoAD: Learning Shared and Role-Adaptive Representations for Bimanual Manipulation

2026-09-20

AI Summary

为了解决双臂操作中角色适应性学习的问题，BiRoAD通过将特征分解为对称和反对称组件来学习共享且适应角色的表示，提高了在不同角色配置下的鲁棒性。

Abstract

Bimanual manipulation requires policies that coordinate two arms while adapting their functional roles to scene geometry, object configuration, and task context. Learning such scene-conditioned role adaptation remains challenging, as demonstrations may contain uneven role distributions that limit generalization to underrepresented arm--role configurations. In addition, many bimanual policies predict actions in fixed left- and right-arm action spaces. While this provides a natural parameterization for robot control, it does not explicitly specify how behaviors should transform when functional roles are exchanged across arms. Across different scene initializations, the two arms may follow a similar coordination pattern, but the role-specific behavior assigned to each arm should change with the scene. Therefore, we propose BiRoAD, a Bimanual Role-Adaptive Decomposition framework for learning shared and role-adaptive representations in bimanual policies. Given bimanual trajectory or action-token features, BiRoAD decomposes these features into swap--symmetric and swap--antisymmetric components: the former captures coordination structure invariant to arm exchange, and the latter captures role-specific distinctions that vary consistently with functional role assignment. The two components are then recomposed as residual updates to the original paired arm representations, allowing BiRoAD to serve as a modular feature transformation without changing the policy inputs, imitation-learning objective, or requiring manually defined role labels. Across multiple bimanual manipulation tasks with balanced and imbalanced role distributions, BiRoAD improves robustness across role configurations over corresponding base policies, with notable gains on underrepresented role configurations.

Problem

• Bimanual Manipulation
• Role Adaptation
• Scene Geometry
• Action Spaces
• Functional Roles

Innovation

• Bimanual Role-Adaptive Decomposition
• swap-symmetric and swap-antisymmetric components
• role-adaptive representations