Environment Predictive Coding for Embodied Agents
This work addresses the problem of learning robust environment representations for embodied agents to improve navigation performance, which is significant for robotics and AI.
This paper introduces environment predictive coding, a self-supervised method that learns environment-level representations for embodied agents by predicting masked portions of an agent's trajectory from unmasked parts, conditioned on camera poses. The learned representations successfully transfer to multiple downstream navigation tasks, outperforming state-of-the-art methods on Gibson and Matterport3D environments with limited experience.
We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly encode a series of images gathered by an agent as it moves about in 3D environments. We learn these representations via a zone prediction task, where we intelligently mask out portions of an agent's trajectory and predict them from the unmasked portions, conditioned on the agent's camera poses. By learning such representations on a collection of videos, we demonstrate successful transfer to multiple downstream navigation-oriented tasks. Our experiments on the photorealistic 3D environments of Gibson and Matterport3D show that our method outperforms the state-of-the-art on challenging tasks with only a limited budget of experience.