Does Unpredictability Influence Driving Behavior?

TL;DR

This paper explores how the unpredictability of surrounding vehicles affects driving behavior by incorporating a new unpredictability feature into reward models, showing improved alignment with human driving data.

Contribution

It introduces a novel unpredictability feature into reward functions for autonomous driving and demonstrates its effectiveness using inverse reinforcement learning.

Findings

Incorporating unpredictability improves model fit to human driving data.

The unpredictability feature enhances the realism of simulated driving behavior.

Results suggest unpredictability significantly influences driving decisions.

Abstract

In this paper we investigate the effect of the unpredictability of surrounding cars on an ego-car performing a driving maneuver. We use Maximum Entropy Inverse Reinforcement Learning to model reward functions for an ego-car conducting a lane change in a highway setting. We define a new feature based on the unpredictability of surrounding cars and use it in the reward function. We learn two reward functions from human data: a baseline and one that incorporates our defined unpredictability feature, then compare their performance with a quantitative and qualitative evaluation. Our evaluation demonstrates that incorporating the unpredictability feature leads to a better fit of human-generated test data. These results encourage further investigation of the effect of unpredictability on driving behavior.