BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark
This provides a standardized benchmark for researchers in robotics to evaluate algorithms for mobile bi-manual manipulation, though it is incremental as it builds on existing demo-driven approaches.
The authors tackled the problem of benchmarking mobile bi-manual robotic manipulation by introducing BiGym, a new environment with 40 diverse home tasks and human-collected demonstrations, and validated it by benchmarking state-of-the-art imitation and demo-driven reinforcement learning algorithms.
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.