FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation

Abstract

Fig. 1: FurnitureBench: reproducible real-world furniture assembly benchmark.Benchmarking furniture assembly poses to address many robotic manipulation challenges: long-horizon planning, dexterous control, and visual perception.FurnitureBench is designed to be easy-to-reproduce and easy-to-use with the 3D printable furniture models, robot control software stack, environment setup guide, and large demonstration data.(Left) A decorated room in the real world with furniture models our robot assembled.(Right) A suite of 8 furniture models in our benchmark.Abstract-Reinforcement learning (RL), imitation learning (IL), and task and motion planning (TAMP) have demonstrated impressive performance across various robotic manipulation tasks.However, these approaches have been limited to learning simple behaviors in current real-world manipulation benchmarks, such as pushing or pick-and-place.To enable more complex, longhorizon behaviors of an autonomous robot, we propose to focus on real-world furniture assembly, a complex, long-horizon robot manipulation task that requires addressing many current robotic manipulation challenges to solve.We present FurnitureBench, a reproducible real-world furniture assembly benchmark aimed at providing a low barrier for entry and being easily reproducible, so that researchers across the world can reliably test their algorithms and compare them against prior work.For ease of use, we provide 200+ hours of pre-collected data (5000+ demonstrations), 3D printable furniture models, a robotic environment setup guide, and systematic task initialization.Furthermore, we provide FurnitureSim, a fast and realistic simulator of FurnitureBench.We benchmark the performance of offline RL and IL algorithms on our assembly tasks and demonstrate the need to improve such algorithms to be able to solve our tasks in the real world, providing ample opportunities for future research.

Topics & Concepts