Map Prediction and Generative Entropy for Multi-Agent Exploration
This addresses the problem of efficient autonomous reconnaissance for robotics by introducing a new paradigm for task ranking, though it is incremental as it builds on existing generative technologies and inpainting methods.
The paper tackled the problem of multi-agent exploration by enabling robot teams to infer distributions of scene interpretations beyond known observations, using a fine-tuned latent diffusion model for map inpainting. The result showed that prioritizing tasks based on generative entropy allowed predicting a correct scene significantly faster than traditional information-guided methods in simulated urban environments with three vehicles.
Traditionally, autonomous reconnaissance applications have acted on explicit sets of historical observations. Aided by recent breakthroughs in generative technologies, this work enables robot teams to act beyond what is currently known about the environment by inferring a distribution of reasonable interpretations of the scene. We developed a map predictor that inpaints the unknown space in a multi-agent 2D occupancy map during an exploration mission. From a comparison of several inpainting methods, we found that a fine-tuned latent diffusion inpainting model could provide rich and coherent interpretations of simulated urban environments with relatively little computation time. By iteratively inferring interpretations of the scene throughout an exploration run, we are able to identify areas that exhibit high uncertainty in the prediction, which we formalize with the concept of generative entropy. We prioritize tasks in regions of high generative entropy, hypothesizing that this will expedite convergence on an accurate predicted map of the scene. In our study we juxtapose this new paradigm of task ranking with the state of the art, which ranks regions to explore by those which maximize expected information recovery. We compare both of these methods in a simulated urban environment with three vehicles. Our results demonstrate that by using our new task ranking method, we can predict a correct scene significantly faster than with a traditional information-guided method.