Learning an Urban Air Mobility Encounter Model from Expert Preferences
This addresses the problem of data scarcity for UAM safety modeling, offering a practical solution for developers, though it is incremental as it extends existing preference-based learning methods to a new domain.
The paper tackles the challenge of developing realistic encounter models for Urban Air Mobility (UAM) systems in the absence of large datasets by using expert preferences to tune a stochastic policy, resulting in a method that generates realistic trajectories with only a few minutes of expert time.
Airspace models have played an important role in the development and evaluation of aircraft collision avoidance systems for both manned and unmanned aircraft. As Urban Air Mobility (UAM) systems are being developed, we need new encounter models that are representative of their operational environment. Developing such models is challenging due to the lack of data on UAM behavior in the airspace. While previous encounter models for other aircraft types rely on large datasets to produce realistic trajectories, this paper presents an approach to encounter modeling that instead relies on expert knowledge. In particular, recent advances in preference-based learning are extended to tune an encounter model from expert preferences. The model takes the form of a stochastic policy for a Markov decision process (MDP) in which the reward function is learned from pairwise queries of a domain expert. We evaluate the performance of two querying methods that seek to maximize the information obtained from each query. Ultimately, we demonstrate a method for generating realistic encounter trajectories with only a few minutes of an expert's time.