Learning Latent Traits for Simulated Cooperative Driving Tasks

TL;DR

This paper introduces a framework for modeling human driver preferences and behaviors using latent traits, enabling personalized intervention policies in simulated cooperative driving scenarios.

Contribution

It presents a novel latent trait-based approach to capture individual driver differences and a new simulation environment for distracted driving to evaluate intervention strategies.

Findings

Effective discrimination of driver types achieved

Intervention policies improved safety in simulations

Framework adapts to individual driver preferences

Abstract

To construct effective teaming strategies between humans and AI systems in complex, risky situations requires an understanding of individual preferences and behaviors of humans. Previously this problem has been treated in case-specific or data-agnostic ways. In this paper, we build a framework capable of capturing a compact latent representation of the human in terms of their behavior and preferences based on data from a simulated population of drivers. Our framework leverages, to the extent available, knowledge of individual preferences and types from samples within the population to deploy interaction policies appropriate for specific drivers. We then build a lightweight simulation environment, HMIway-env, for modelling one form of distracted driving behavior, and use it to generate data for different driver types and train intervention policies. We finally use this environment to quantify both the ability to discriminate drivers and the effectiveness of intervention policies.