BridgeData V2: A Dataset for Robot Learning at Scale

by   Homer Walke, et al.
berkeley college

We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research on scalable robot learning. BridgeData V2 contains 60,096 trajectories collected across 24 environments on a publicly available low-cost robot. BridgeData V2 provides extensive task and environment variability, leading to skills that can generalize across environments, domains, and institutions, making the dataset a useful resource for a broad range of researchers. Additionally, the dataset is compatible with a wide variety of open-vocabulary, multi-task learning methods conditioned on goal images or natural language instructions. In our experiments, we train 6 state-of-the-art imitation learning and offline reinforcement learning methods on our dataset, and find that they succeed on a suite of tasks requiring varying amounts of generalization. We also demonstrate that the performance of these methods improves with more data and higher capacity models, and that training on a greater variety of skills leads to improved generalization. By publicly sharing BridgeData V2 and our pre-trained models, we aim to accelerate research in scalable robot learning methods. Project page at


page 1

page 5

page 6

page 7

page 15


Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation

We tackle real-world long-horizon robot manipulation tasks through skill...

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

General-purpose robotic systems must master a large repertoire of divers...

Grounding Language in Play

Natural language is perhaps the most versatile and intuitive way for hum...

Grounding Language with Visual Affordances over Unstructured Data

Recent works have shown that Large Language Models (LLMs) can be applied...

What Matters in Language Conditioned Robotic Imitation Learning

A long-standing goal in robotics is to build robots that can perform a w...

LISA: Learning Interpretable Skill Abstractions from Language

Learning policies that effectually utilize language instructions in comp...

RH20T: A Robotic Dataset for Learning Diverse Skills in One-Shot

A key challenge in robotic manipulation in open domains is how to acquir...

Please sign up or login with your details

Forgot password? Click here to reset