RLBench: The Robot Learning Benchmark & Learning Environment

TL;DR

RLBench is a comprehensive and scalable benchmark environment with diverse tasks and demonstrations designed to advance research in robot learning, including reinforcement, imitation, and few-shot learning.

Contribution

The paper introduces RLBench, a large-scale, versatile robot learning benchmark with 100 tasks, diverse observations, and an easy-to-extend framework for new tasks and demonstrations.

Findings

Provides 100 unique, hand-designed tasks with varying difficulty

Includes an extensive set of demonstrations via motion planners

Facilitates research in multiple areas like reinforcement and few-shot learning

Abstract

We present a challenging new benchmark and learning-environment for robot learning: RLBench. The benchmark features 100 completely unique, hand-designed tasks ranging in difficulty, from simple target reaching and door opening, to longer multi-stage tasks, such as opening an oven and placing a tray in it. We provide an array of both proprioceptive observations and visual observations, which include rgb, depth, and segmentation masks from an over-the-shoulder stereo camera and an eye-in-hand monocular camera. Uniquely, each task comes with an infinite supply of demos through the use of motion planners operating on a series of waypoints given during task creation time; enabling an exciting flurry of demonstration-based learning. RLBench has been designed with scalability in mind; new tasks, along with their motion-planned demos, can be easily created and then verified by a series of tools, allowing users to submit their own tasks to the RLBench task repository. This large-scale benchmark aims to accelerate progress in a number of vision-guided manipulation research areas, including: reinforcement learning, imitation learning, multi-task learning, geometric computer vision, and in particular, few-shot learning. With the benchmark's breadth of tasks and demonstrations, we propose the first large-scale few-shot challenge in robotics. We hope that the scale and diversity of RLBench offers unparalleled research opportunities in the robot learning community and beyond.