RLBench: The Robot Learning Benchmark & Learning Environment
RLBench: The Robot Learning Benchmark & Learning Environment
复制标题
DOI：
10.1109/lra.2020.2974707
复制
发表时间：
2020-04-01
影响因子：
5.2
通讯作者：
Davison, Andrew J.
中科院分区：
文献类型：
--
作者：
James, Stephen;Ma, Zicong;Davison, Andrew J.
我们提出了一个具有挑战性的新基准和机器人学习环境：RLBench。该基准测试包含100个完全独特的手工设计任务，难度从简单的目标到达和开门到更长的多阶段任务，例如打开烤箱并将托盘放入其中。我们提供了一系列本体感受观察和视觉观察，其中包括来自肩扛式立体相机和手眼式单目相机的RGB，深度和分割掩模。独特的是，每个任务都有无限的演示，通过使用运动规划器在任务创建时给出的一系列航点上操作;实现了令人兴奋的基于演示的学习可能性。RLBench在设计时考虑到了可扩展性;新任务及其运动规划演示沿着可以轻松创建，然后通过一系列工具进行验证，允许用户将自己的任务提交到RLBench任务存储库。这个大规模的基准测试旨在加速许多视觉引导操作研究领域的进展，包括：强化学习，模仿学习，多任务学习，几何计算机视觉，特别是少镜头学习。随着基准的任务和演示的广度，我们提出了机器人技术的第一个大规模的少数镜头的挑战。我们希望RLBench的规模和多样性为机器人学习社区及其他领域提供无与伦比的研究机会。基准测试代码和视频可以在https://sites.google.com/view/rlbench上找到。
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 possibilities. 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. Benchmarking code and videos can be found at https://sites.google.com/view/rlbench.