Road Boundary Estimation Using Sparse Automotive Radar Inputs

TL;DR

This paper introduces a novel method for road boundary detection using sparse automotive radar data, combining probabilistic modeling with RANSAC to achieve accurate lane boundary estimates with less than 11 cm error.

Contribution

The paper develops a new probabilistic framework integrating Dirichlet Process Mixture Models and a custom RANSAC variant for robust road boundary estimation from sparse radar signals.

Findings

Mean lane boundary estimation error is under 11 cm.

The algorithm performs satisfactorily in tests.

The approach effectively combines probabilistic modeling with RANSAC.

Abstract

This paper presents a new approach to detecting road boundaries based on sparse radar signals. We model the roadway using a homogeneous model and derive its conditional predictive model under known radar motion. Using the conditional predictive model and model radar points using a Dirichlet Process Mixture Model (DPMM), we employ Mean Field Variational Inference (MFVI) to derive an unconditional road boundary model distribution. In order to generate initial candidate solutions for the MFVI, we develop a custom Random Sample and Consensus (RANSAC) variant to propose unseen model instances as candidate road boundaries. For each radar point cloud we alternate the MFVI and RANSAC proposal steps until convergence to generate the best estimate of all candidate models. We select the candidate model with the minimum lateral distance to the radar on each side as the estimates of the left and right boundaries. We have implemented the proposed algorithm in C++. We have tested the algorithm and it has shown satisfactory results. More specifically, the mean lane boundary estimation error is not more than 11.0 cm.