Domain-adapting Visual Policies with A Single Demonstration

Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor policies that utilize high-dimensional images as input. A common method to tackle this issue is through domain randomization, which aims to broaden the span of the training distribution to cover the test-time distribution. However, this approach is only effective when the domain randomizations encompass the actual shifts in the test-time distribution. We instead take a different approach, where we make use of a single demonstration (a prompt) to learn policy that adapts to the testing target environment. Our proposed framework, PromptAdapt, leverages the Transformer architecture's capacity to model sequential data to learn demonstration-conditioned visual policies, allowing for in-context adaptation to a target domain that is distinct from training. Our experiments in both simulation and real-world settings show that PromptAdapt is a strong domain-adapting policy that outperforms baseline methods by a large margin under a range of domain shifts, including variations in lighting, color, texture, and camera pose.

Real-world experiment rollouts under sim-to-real settings: