BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark

TL;DR

BiGym is a comprehensive benchmark and environment for evaluating mobile bi-manual robotic manipulation using diverse tasks, multimodal observations, and human demonstrations, facilitating research in imitation and reinforcement learning.

Contribution

It introduces a new benchmark with 40 diverse tasks, multimodal observations, and human demonstrations, enabling realistic evaluation of manipulation algorithms.

Findings

Benchmarking of state-of-the-art algorithms conducted

Demonstrates the environment's versatility and realism

Identifies future research opportunities

Abstract

We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.