Game Theory-Based Parameter-Tuning for Path Planning of UAVs

Modern UAV s are incredibly complex systems with numerous tunable knobs such as the battery capacity, camera settings, sampling rate, constraints on the route, etc. The area of theoretical exploration of the optimization problems that arise in such settings is dominated by traditional approaches that use regular nonlinear optimization often enhanced with AI-based techniques such as genetic algorithms. These techniques are sadly rather slow, have convergence issues, and are typically not suitable for use at runtime. In this paper, we leverage recent and promising research results that propose to convert the optimization problem into a game and then find the set of equilibrium strategies of different players. The strategies can then be mapped to the optimal values of the tunable parameters. With simulation studies in virtual worlds, we show that our solutions are 5–21% better than those produced by traditional methods, and our approach is 10–100 times faster.