Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Fine manipulation tasks, such as threading cable ties or slotting a battery, are notoriously difficult for robots because they require precision, careful coordination of contact forces, and closed-loop visual feedback. We present a low-cost system that performs end-to-end imitation learning directly from real demonstrations. We develop Action Chunking with Transformers (ACT), which learns a generative model over action sequences, allowing the robot to learn 6 difficult tasks with 80-90% success using only 10 minutes of demos.