Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation

TL;DR

Sequential Dexterity introduces a reinforcement learning system that chains dexterous policies for long-horizon manipulation, enabling generalization and zero-shot transfer to real-world robots despite training only in simulation.

Contribution

It proposes a novel system that chains dexterous policies with a transition feasibility function for improved long-horizon manipulation.

Findings

Demonstrates successful zero-shot transfer to real-world robots.

Achieves high success rates in complex, multi-stage manipulation tasks.

Shows generalization to novel object shapes.

Abstract

Many real-world manipulation tasks consist of a series of subtasks that are significantly different from one another. Such long-horizon, complex tasks highlight the potential of dexterous hands, which possess adaptability and versatility, capable of seamlessly transitioning between different modes of functionality without the need for re-grasping or external tools. However, the challenges arise due to the high-dimensional action space of dexterous hand and complex compositional dynamics of the long-horizon tasks. We present Sequential Dexterity, a general system based on reinforcement learning (RL) that chains multiple dexterous policies for achieving long-horizon task goals. The core of the system is a transition feasibility function that progressively finetunes the sub-policies for enhancing chaining success rate, while also enables autonomous policy-switching for recovery from failures and bypassing redundant stages. Despite being trained only in simulation with a few task objects, our system demonstrates generalization capability to novel object shapes and is able to zero-shot transfer to a real-world robot equipped with a dexterous hand. Code and videos are available at https://sequential-dexterity.github.io