Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models

TL;DR

Generative Skill Chaining (GSC) introduces a probabilistic diffusion-based framework for long-horizon manipulation planning, enabling efficient, scalable, and generalizable task execution by composing learned skill priors during inference.

Contribution

GSC is the first to apply skill-centric diffusion models for long-horizon planning, addressing scalability and reactivity issues in existing skill chaining methods.

Findings

GSC effectively plans long-horizon tasks in simulation and real robots.

It demonstrates improved scalability and reactivity over traditional methods.

GSC successfully handles complex subtask dependencies and geometric constraints.

Abstract

Long-horizon tasks, usually characterized by complex subtask dependencies, present a significant challenge in manipulation planning. Skill chaining is a practical approach to solving unseen tasks by combining learned skill priors. However, such methods are myopic if sequenced greedily and face scalability issues with search-based planning strategy. To address these challenges, we introduce Generative Skill Chaining~(GSC), a probabilistic framework that learns skill-centric diffusion models and composes their learned distributions to generate long-horizon plans during inference. GSC samples from all skill models in parallel to efficiently solve unseen tasks while enforcing geometric constraints. We evaluate the method on various long-horizon tasks and demonstrate its capability in reasoning about action dependencies, constraint handling, and generalization, along with its ability to replan in the face of perturbations. We show results in simulation and on real robot to validate the efficiency and scalability of GSC, highlighting its potential for advancing long-horizon task planning. More details are available at: https://generative-skill-chaining.github.io/