Semantic Property Maps for Driving Applications

TL;DR

This paper introduces a novel probabilistic mapping method that combines vehicle dynamics parameters with semantic information from cameras, enhancing predictive control in driving applications.

Contribution

It presents a new map representation using conjugate priors and Bayesian moment matching, enabling online spatial adaptation of vehicle parameters for improved control.

Findings

The map provides a smooth spatial distribution of vehicle parameters.

The approach integrates camera data with vehicle signals for better parameter estimation.

Theoretical guarantees ensure the map's suitability for predictive control.

Abstract

We consider the problem of estimating the parameters of a vehicle dynamics model for predictive control in driving applications. Instead of solely using the instantaneous parameters estimated from the vehicle signals, we combine this with cameras and update a probabilistic map with parameter estimates and semantic information using Bayesian moment matching. Key to this approach is the map representation, which is constructed with conjugate priors to the measurement likelihoods and defined in the same path coordinates as the vehicle controller, such that the map can be externalized to provide a local representation of the parameter likelihoods that vary in space. The result is a spatial map of vehicle parameters adapted online to enhance the driving control system. We provide theoretical guarantees on the smoothness of relevant parameter likelihood statistics as a function of space, which is critical for their use in predictive control.