SpikiLi: A Spiking Simulation of LiDAR based Real-time Object Detection for Autonomous Driving

TL;DR

This paper demonstrates the application of spiking neural networks to complex 3D object detection from LiDAR data for autonomous driving, showing comparable accuracy to traditional models while promising enhanced power efficiency on neuromorphic hardware.

Contribution

It is the first to apply spiking neural networks to LiDAR-based 3D object detection and demonstrates simulation of spiking behavior with existing CNNs.

Findings

Achieved equivalent accuracy and runtime on GPU

Successfully simulated spiking neural behavior from CNNs

Indicates potential for improved power efficiency on neuromorphic hardware

Abstract

Spiking Neural Networks are a recent and new neural network design approach that promises tremendous improvements in power efficiency, computation efficiency, and processing latency. They do so by using asynchronous spike-based data flow, event-based signal generation, processing, and modifying the neuron model to resemble biological neurons closely. While some initial works have shown significant initial evidence of applicability to common deep learning tasks, their applications in complex real-world tasks has been relatively low. In this work, we first illustrate the applicability of spiking neural networks to a complex deep learning task namely Lidar based 3D object detection for automated driving. Secondly, we make a step-by-step demonstration of simulating spiking behavior using a pre-trained convolutional neural network. We closely model essential aspects of spiking neural networks in simulation and achieve equivalent run-time and accuracy on a GPU. When the model is realized on a neuromorphic hardware, we expect to have significantly improved power efficiency.