SignificanceWe present a framework that integrates social psychology tools into controller design for autonomous vehicles. Our key insight utilizes Social Value Orientation (SVO), quantifying an agent’s degree of selfishness or altruism, which allows us to better predict driver behavior. We model interactions between human and autonomous agents with game theory and the principle of best response. Our unified algorithm estimates driver SVOs and incorporates their predicted trajectories into the autonomous vehicle’s control while respecting safety constraints. We study common-yet-difficult traffic scenarios: highway merging and unprotected left turns. Incorporating SVO reduces error in predictions by 25%, validated on 92 human driving merges. Furthermore, we find that merging drivers are more competitive than nonmerging drivers.

No abstract

No abstract

No abstract

This article considers the problem of multi-robot coverage control, where a group of robots has to spread out over an environment to provide coverage. We propose a new approach for a group of robots carrying out this collaborative task that will adapt online to performance variations among the robots. Two types of performance variations are considered: variations in sensing performance (e.g. differences in sensor types, calibration, or noise), and variations in actuation (e.g. differences in terrain, vehicle types, or lossy motors). The robots have no prior knowledge of the relative strengths of their performance compared to the others in the team. We present an algorithm that learns the relative performance variations among the robots online, in a distributed fashion, and automatically compensates by assigning the weak robots a smaller portion of the environment and the strong robots a larger portion. Using a Lyapunov-type proof, we show that the robots converge to a locally optimal coverage configuration. The algorithm is also demonstrated in both MATLAB simulations and experiments with Pololu m3pi ground robots.