Improving the Resilience of Quadrotors in Underground Environments by Combining Learning-based and Safety Controllers
This work addresses the challenge of autonomous quadrotor navigation in subterranean settings for applications like search and rescue, though it is incremental as it builds on existing learning and safety control methods.
The paper tackled the problem of quadrotor control in underground environments by combining a learning-based controller with a safety controller, using a normalizing flow-based prior to detect out-of-distribution conditions and switch between them, resulting in a system that completes tasks quickly while avoiding collisions in simulated cave environments.
Autonomously controlling quadrotors in large-scale subterranean environments is applicable to many areas such as environmental surveying, mining operations, and search and rescue. Learning-based controllers represent an appealing approach to autonomy, but are known to not generalize well to `out-of-distribution' environments not encountered during training. In this work, we train a normalizing flow-based prior over the environment, which provides a measure of how far out-of-distribution the quadrotor is at any given time. We use this measure as a runtime monitor, allowing us to switch between a learning-based controller and a safe controller when we are sufficiently out-of-distribution. Our methods are benchmarked on a point-to-point navigation task in a simulated 3D cave environment based on real-world point cloud data from the DARPA Subterranean Challenge Final Event Dataset. Our experimental results show that our combined controller simultaneously possesses the liveness of the learning-based controller (completing the task quickly) and the safety of the safety controller (avoiding collision).