Exploration-assisted Bottleneck Transition Toward Robust and Data-efficient Deformable Object Manipulation

Abstract

Imitation learning has demonstrated impressive results in robotic manipulation but fails under out-of-distribution (OOD) states. This limitation is particularly critical in Deformable Object Manipulation (DOM), where the near-infinite possible configurations render comprehensive data collection infeasible. Although several methods address OOD states, they typically require exhaustive data or highly precise perception. Such requirements are often impractical for DOM owing to its inherent complexities, including self-occlusion. To address the OOD problem in DOM, we propose a novel framework, Exploration-assisted Bottleneck Transition for Deformable Object Manipulation (ExBot), which addresses the OOD challenge through two key advantages. First, we introduce bottleneck states, standardized configurations that serve as starting points for task execution. This enables the reconceptualization of OOD challenges as the problem of transitioning diverse initial states to these bottleneck states, significantly reducing demonstration requirements. Second, to account for imperfect perception, we partition the OOD state space based on recognizability and employ dual action primitives. This approach enables ExBot to manipulate even unrecognizable states without requiring accurate perception. By concentrating demonstrations around bottleneck states and leveraging exploration to alter perceptual conditions, ExBot achieves both data efficiency and robustness to severe OOD scenarios. Real-world experiments on rope and cloth manipulation demonstrate successful task completion from diverse OOD states, including severe self-occlusions.

Figures (12)

• Figure 1: Exploration-assisted Bottleneck Transition for Deformable Object Manipulation (ExBot). ExBot enables robust rope and cloth manipulation by introducing exploration-guided transitions through bottleneck states. Our framework successfully completes learned tasks from the out-of-distribution (OOD) states, including severe self-occluded or crumpled conditions. The red arrow represents exploration action, and the red frame represents bottleneck states. This mechanism promotes both data-efficiency and robustness in deformable object manipulation.
• Figure 2: System architecture. The Object Recognition Module and Action Decision Policy handle OOD states by selecting between Preparation Action $a_p$ and Exploration Action $a_e$, transitioning the object into a bottleneck state. Once t his transition is conducted, the Behavior Cloning (BC) Model executes the tasks from the bottleneck state.
• Figure 3: Examples of images with keypoint representations for input of the Action Decision Policy, which receives both the raw image and the image with representation. (Top row) Rope manipulation: two endpoints are extracted. (Bottom row) Cloth manipulation: represents two adjacent corners with an adjacent guideline are represented.
• Figure 4: General VLM prompt structure for verification tasks.
• Figure 5: Exploration Action of rope and cloth manipulation