Risk-Aware Planning and Assignment for Ground Vehicles using Uncertain Perception from Aerial Vehicles
This addresses the challenge of safe ground vehicle navigation in search-and-rescue scenarios, but it is incremental as it builds on existing risk-aware and perception methods.
The paper tackles the problem of multi-robot assignment and planning in unknown disaster response environments by developing a risk-aware framework that uses Bayesian deep learning and CVaR to handle noisy perception from aerial images, resulting in quantifiably safer paths and assignments.
We propose a risk-aware framework for multi-robot, multi-demand assignment and planning in unknown environments. Our motivation is disaster response and search-and-rescue scenarios where ground vehicles must reach demand locations as soon as possible. We consider a setting where the terrain information is available only in the form of an aerial, georeferenced image. Deep learning techniques can be used for semantic segmentation of the aerial image to create a cost map for safe ground robot navigation. Such segmentation may still be noisy. Hence, we present a joint planning and perception framework that accounts for the risk introduced due to noisy perception. Our contributions are two-fold: (i) we show how to use Bayesian deep learning techniques to extract risk at the perception level; and (ii) use a risk-theoretical measure, CVaR, for risk-aware planning and assignment. The pipeline is theoretically established, then empirically analyzed through two datasets. We find that accounting for risk at both levels produces quantifiably safer paths and assignments.