Multi-Rotor Aircraft Collision Avoidance using Partially Observable Markov Decision Processes

This paper presents an extension to the ACAS X collision avoidance algorithm to multirotor aircraft capable of using speed changes to avoid close encounters with neighboring aircraft. The ACAS X family of algorithms currently use either turns or vertical maneuvers to avoid collision. We present a formulation of the algorithm in two dimensions that uses horizontal plane accelerations for resolution maneuvers and propose a set of metrics that directly specify aircraft behavior in terms of separation from other aircraft and minimizing deviation from the desired trajectory. The maneuver strategy is optimized with respect to a partially observable Markov decision process model using dynamic programming. The parameters of the model strongly influence the performance tradeoff between metrics such as alert rate and safety. Finding the parameters that provide the appropriate tradeoff was aided by a Gaussian process-based surrogate model. The algorithm is shown to successfully achieve the competing goals of maintaining a minimum separation standard and closely tracking the mission trajectory in simulations involving thousands of collision encounters. Further, sets of algorithm parameters were generated that provide a tradeoff between the two goals. These parameter sets allow a user of the collision avoidance algorithm to select a desired separation minimum appropriate for their application that also minimizes trajectory deviations.