Rapid Exploration for Open-World Navigation with Latent Goal Models
This addresses the problem of robust robotic navigation in diverse, real-world settings for applications like autonomous robots, though it appears incremental as it builds on existing latent variable and memory-based methods.
The paper tackles autonomous exploration and navigation in open-world environments by developing a robotic learning system with a latent goal model and topological memory, achieving the ability to discover goals up to 80 meters away in under 20 minutes amidst unseen obstacles and weather conditions.
We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory of images. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration. Trained on a large offline dataset of prior experience, the model acquires a representation of visual goals that is robust to task-irrelevant distractors. We demonstrate our method on a mobile ground robot in open-world exploration scenarios. Given an image of a goal that is up to 80 meters away, our method leverages its representation to explore and discover the goal in under 20 minutes, even amidst previously-unseen obstacles and weather conditions. Please check out the project website for videos of our experiments and information about the real-world dataset used at https://sites.google.com/view/recon-robot.