Vehicle Type Specific Waypoint Generation

TL;DR

This paper presents a method to generate vehicle-type specific waypoint sequences by conditioning a generic probabilistic behavior model with reinforcement learning byproducts, improving physical plausibility for planning applications.

Contribution

It introduces a novel approach to specialize generic behavior models to specific vehicle types using reinforcement learning byproducts, enhancing their practical utility.

Findings

Generated waypoints are more physically plausible for specific vehicle types.

Method effectively specializes generic models without retraining from scratch.

Improves downstream planning accuracy for different vehicle classes.

Abstract

We develop a generic mechanism for generating vehicle-type specific sequences of waypoints from a probabilistic foundation model of driving behavior. Many foundation behavior models are trained on data that does not include vehicle information, which limits their utility in downstream applications such as planning. Our novel methodology conditionally specializes such a behavior predictive model to a vehicle-type by utilizing byproducts of the reinforcement learning algorithms used to produce vehicle specific controllers. We show how to compose a vehicle specific value function estimate with a generic probabilistic behavior model to generate vehicle-type specific waypoint sequences that are more likely to be physically plausible then their vehicle-agnostic counterparts.