Despite the recent progress in robot learning, robotics research and benchmarks today are typically confined to simple short-horizon tasks. However, tasks in our daily lives are much more complicated — consisting of multiple sub-tasks and requiring high dexterity skills — and the typical “learning from scratch” scheme is hardly scale to such complex long-horizon tasks.

In this talk, I propose to extend the range of tasks that robots can learn by acquiring a useful skillset and efficiently harnessing these skills. As a first step, I will introduce a novel benchmark for complex long-horizon manipulation tasks, IKEA furniture assembly environment. Then, I will present skill chaining approaches that enable sequential skill composition to perform long-horizon tasks. Finally, I will talk about how to learn a long-horizon task efficiently using skills and skill priors extracted from diverse data.