ChipNet: Real-Time LiDAR Processing for Drivable Region Segmentation on an FPGA

TL;DR

This paper introduces ChipNet, an FPGA-based CNN model for real-time LiDAR data segmentation to identify drivable regions, offering high accuracy and speed suitable for autonomous vehicle navigation.

Contribution

The paper presents a novel FPGA hardware architecture for CNN-based LiDAR segmentation that significantly improves processing speed while maintaining high accuracy.

Findings

Processes each LiDAR scan in 17.59 ms

Achieves high accuracy on Ford and KITTI benchmarks

Outperforms previous real-time LiDAR segmentation methods

Abstract

This paper presents a field-programmable gate array (FPGA) design of a segmentation algorithm based on convolutional neural network (CNN) that can process light detection and ranging (LiDAR) data in real-time. For autonomous vehicles, drivable region segmentation is an essential step that sets up the static constraints for planning tasks. Traditional drivable region segmentation algorithms are mostly developed on camera data, so their performance is susceptible to the light conditions and the qualities of road markings. LiDAR sensors can obtain the 3D geometry information of the vehicle surroundings with high precision. However, it is a computational challenge to process a large amount of LiDAR data in real-time. In this paper, a convolutional neural network model is proposed and trained to perform semantic segmentation using data from the LiDAR sensor. An efficient hardware architecture is proposed and implemented on an FPGA that can process each LiDAR scan in 17.59 ms, which is much faster than the previous works. Evaluated using Ford and KITTI road detection benchmarks, the proposed solution achieves both high accuracy in performance and real-time processing in speed.