Optimized and Trusted Collision Avoidance for Unmanned Aerial Vehicles using Approximate Dynamic Programming (Technical Report)
This work addresses safety integration of UAVs into civil airspace, but it is incremental as it builds on existing trusted logic with dynamic parameter adaptation.
The paper tackles the problem of conservative collision avoidance for UAVs by proposing an online adaptive tuning of trusted resolution logic parameters using approximate dynamic programming, resulting in improved safety and operational performance compared to a static baseline.
Safely integrating unmanned aerial vehicles into civil airspace is contingent upon development of a trustworthy collision avoidance system. This paper proposes an approach whereby a parameterized resolution logic that is considered trusted for a given range of its parameters is adaptively tuned online. Specifically, to address the potential conservatism of the resolution logic with static parameters, we present a dynamic programming approach for adapting the parameters dynamically based on the encounter state. We compute the adaptation policy offline using a simulation-based approximate dynamic programming method that accommodates the high dimensionality of the problem. Numerical experiments show that this approach improves safety and operational performance compared to the baseline resolution logic, while retaining trustworthiness.