Evaluation and Testing System for Automotive LiDAR Sensors

Abstract

The world is facing a great technological transformation towards fully autonomous vehicles, where optimists predict that by 2030 autonomous vehicles will be sufficiently reliable, affordable, and common to displace most human driving. To cope with these trends, reliable perception systems must enable vehicles to hear and see all their surroundings, with light detection and ranging (LiDAR) sensors being a key instrument for recreating a 3D visualization of the world in real time. However, perception systems must rely on accurate measurements of the environment. Thus, these intelligent sensors must be calibrated and benchmarked before being placed on the market or assembled in a car. This article presents an Evaluation and Testing Platform for Automotive LiDAR sensors, with the main goal of testing both commercially available sensors and new sensor prototypes currently under development in Bosch Car Multimedia Portugal. The testing system can benchmark any LiDAR sensor under different conditions, recreating the expected driving environment in which such devices normally operate. To characterize and validate the sensor under test, the platform evaluates several parameters, such as the field of view (FoV), angular resolution, sensor’s range, etc., based only on the point cloud output. This project is the result of a partnership between the University of Minho and Bosch Car Multimedia Portugal.

A Survey on Data Compression Techniques for Automotive LiDAR Point Clouds

“…For instance, LIBRE, considered the first benchmarking and reference LiDAR dataset, tested ten sensors in three different environments and configurations such as static targets, adverse weather, and dynamic traffic [29,30]. Gomes et al also proposed a testing platform to rapidly test and validate LiDAR sensors by analyzing only their point cloud output [31]. The testing system is able to benchmark a LiDAR sensor in a controlled environment to recreate the expected driving conditions to which such devices are normally subjected.…”

A freight yard train and commercial vehicle based on DGPS/radar ranging/laser ranging combination application

“…A positioning module is arranged on the locomotive and on the target personnel to detect the position of the target personnel and generate positioning signals; The GPS differential station is communicated with the positioning module to receive the positioning signal, perform differential correction on the positioning signal to obtain the positioning signal after differential correction, and re-upload the positioning signal after differential correction to the positioning module [10];The microcomputer is communicated with the positioning module and the early warning module respectively, and is used to display the position of the target person on the electronic map according to the positioning signal after difference correction, and when the target person enters the limit of the electronic map, the control early warning module issues an alarm. In practical application, when the staff enters the demarcated danger limit (such as entering within 1.7m from the line center, as redundancy, it is necessary to take ≥1.7m, and it can also be set to 1.8m or higher), and there is no rolling stock working on the line temporarily (the microcomputer can judge whether the line has vehicles according to whether the current time is working time), The device indicates by voice that the staff has entered the limit; If the microcomputer determines that the locomotive and vehicle will enter the line, or has been in the line but there is a certain distance, the microcomputer control speaker will alarm the personnel and the train driver who enter the limit -danger!…”

An Automotive LiDAR Performance Test Method in Dynamic Driving Conditions

“…Range accuracy and precision measures the quality of range detection in scanning of LiDAR sensors. In the literature and in field guidance [1,33], accuracy is calculated as a difference between a reference measurement of the distance of a specified object and the distance measured by the DUT. For this, a high-precision rangefinder is required to obtain reference range data against the DUT.…”