Brain-Inspired Deep Imitation Learning for Autonomous Driving Systems

TL;DR

This paper introduces a brain-inspired deep imitation learning approach for autonomous driving, leveraging neural asymmetry to enhance generalisation across different driving scenarios and outperform existing methods.

Contribution

It proposes a novel dual neural circuit policy architecture inspired by human brain asymmetry to improve generalisation in deep imitation learning for autonomous driving.

Findings

Outperforms existing methods in generalisation to unseen data

Demonstrates effectiveness of brain-inspired asymmetry in neural networks

Provides source code and pretrained models for reproducibility

Abstract

Autonomous driving has attracted great attention from both academics and industries. To realise autonomous driving, Deep Imitation Learning (DIL) is treated as one of the most promising solutions, because it improves autonomous driving systems by automatically learning a complex mapping from human driving data, compared to manually designing the driving policy. However, existing DIL methods cannot generalise well across domains, that is, a network trained on the data of source domain gives rise to poor generalisation on the data of target domain. In the present study, we propose a novel brain-inspired deep imitation method that builds on the evidence from human brain functions, to improve the generalisation ability of deep neural networks so that autonomous driving systems can perform well in various scenarios. Specifically, humans have a strong generalisation ability which is beneficial from the structural and functional asymmetry of the two sides of the brain. Here, we design dual Neural Circuit Policy (NCP) architectures in deep neural networks based on the asymmetry of human neural networks. Experimental results demonstrate that our brain-inspired method outperforms existing methods regarding generalisation when dealing with unseen data. Our source codes and pretrained models are available at https://github.com/Intenzo21/Brain-Inspired-Deep-Imitation-Learning-for-Autonomous-Driving-Systems}{https://github.com/Intenzo21/Brain-Inspired-Deep-Imitation-Learning-for-Autonomous-Driving-Systems.