Where Should We Place LiDARs on the Autonomous Vehicle? - An Optimal Design Approach

TL;DR

This paper presents an optimal design approach for placing LiDAR sensors on autonomous vehicles, using a novel volume-to-surface-area ratio measure and bio-inspired algorithms to maximize detection capabilities efficiently.

Contribution

It introduces a VSR-based cost function and a cuboid-based method for optimal LiDAR placement, improving detection performance and cost-effectiveness in AV systems.

Findings

VSR measure effectively proxies object detection rate

Artificial Bee Colony algorithm efficiently computes cost functions

Optimized configurations enhance detection and reduce costs

Abstract

Autonomous vehicle manufacturers recognize that LiDAR provides accurate 3D views and precise distance measures under highly uncertain driving conditions. Its practical implementation, however, remains costly. This paper investigates the optimal LiDAR configuration problem to achieve utility maximization. We use the perception area and non-detectable subspace to construct the design procedure as solving a min-max optimization problem and propose a bio-inspired measure -- volume to surface area ratio (VSR) -- as an easy-to-evaluate cost function representing the notion of the size of the non-detectable subspaces of a given configuration. We then adopt a cuboid-based approach to show that the proposed VSR-based measure is a well-suited proxy for object detection rate. It is found that the Artificial Bee Colony evolutionary algorithm yields a tractable cost function computation. Our experiments highlight the effectiveness of our proposed VSR measure in terms of cost-effectiveness configuration as well as providing insightful analyses that can improve the design of AV systems.