Automating Multi-Turn Cable Routing on the NIST Fixture Board with a Bi-Manual Robot and Caging Grippers

Automated cable routing requires deformable object manipulation in constrained and cluttered environments. However, achieving reliable routing is challenging due to fixture constraints, cable flexibility, and the need for slack management. In this work, we introduce a bi-manual cable routing framework that integrates a learned cable tracer with sliding-based motion planning to achieve desired cable trajectories while ensuring precise slack control. Unlike previous methods that use single-arm manipulation, our approach uses open-loop coordinated bi-manual sliding motions to dynamically adjust the cable configuration to avoid tangling and misrouting. Physical experiments with a modified NIST task board demonstrate 84% average success rate across multiple tiers, significantly outperforming a single-arm approach and underscoring robustness across varied fixture configurations.