Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets

by   Frederik Ebert, et al.

Robot learning holds the promise of learning policies that generalize broadly. However, such generalization requires sufficiently diverse datasets of the task of interest, which can be prohibitively expensive to collect. In other fields, such as computer vision, it is common to utilize shared, reusable datasets, such as ImageNet, to overcome this challenge, but this has proven difficult in robotics. In this paper, we ask: what would it take to enable practical data reuse in robotics for end-to-end skill learning? We hypothesize that the key is to use datasets with multiple tasks and multiple domains, such that a new user that wants to train their robot to perform a new task in a new domain can include this dataset in their training process and benefit from cross-task and cross-domain generalization. To evaluate this hypothesis, we collect a large multi-domain and multi-task dataset, with 7,200 demonstrations constituting 71 tasks across 10 environments, and empirically study how this data can improve the learning of new tasks in new environments. We find that jointly training with the proposed dataset and 50 demonstrations of a never-before-seen task in a new domain on average leads to a 2x improvement in success rate compared to using target domain data alone. We also find that data for only a few tasks in a new domain can bridge the domain gap and make it possible for a robot to perform a variety of prior tasks that were only seen in other domains. These results suggest that reusing diverse multi-task and multi-domain datasets, including our open-source dataset, may pave the way for broader robot generalization, eliminating the need to re-collect data for each new robot learning project.


page 1

page 3

page 5


Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation

In recent years, we have seen an emergence of data-driven approaches in ...

Robot Skill Learning Via Classical Robotics-Based Generated Datasets: Advantages, Disadvantages, and Future Improvement

Why do we not profit from our long-existing classical robotics knowledge...

Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials

Recent progress in deep learning highlights the tremendous potential of ...

Unsupervised Domain Generalization by Learning a Bridge Across Domains

The ability to generalize learned representations across significantly d...

ASC me to Do Anything: Multi-task Training for Embodied AI

Embodied AI has seen steady progress across a diverse set of independent...

UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training

We present UnifiedQA-v2, a QA model built with the same process as Unifi...

Multi-Task Generative Adversarial Nets with Shared Memory for Cross-Domain Coordination Control

Generating sequential decision process from huge amounts of measured pro...

Please sign up or login with your details

Forgot password? Click here to reset