MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents
This work addresses domain adaptation for embodied agents in noisy environments, which is incremental as it builds on existing map-based methods with a novel self-supervised approach.
The paper tackles the problem of adapting pretrained embodied agents to noisy environments without ground-truth supervision, using a map style transfer method that improves performance in tasks like localization and navigation, with results showing quick enhancement in downstream tasks.
We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision. Map-based memory provides important contextual information for visual navigation, and exhibits unique spatial structure mainly composed of flat walls and rectangular obstacles. Our adaptation approach encourages the inherent regularities on the estimated maps to guide the agent to overcome the prevalent domain discrepancy in a novel environment. Specifically, we propose an efficient learning curriculum to handle the visual and dynamics corruptions in an online manner, self-supervised with pseudo clean maps generated by style transfer networks. Because the map-based representation provides spatial knowledge for the agent's policy, our formulation can deploy the pretrained policy networks from simulators in a new setting. We evaluate MoDA in various practical scenarios and show that our proposed method quickly enhances the agent's performance in downstream tasks including localization, mapping, exploration, and point-goal navigation.