Paper Info
Title
Indirect and direct training of spiking neural networks for end-to-end control of a lane-keeping vehicle.
Abstract
Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications. However, the implementations of SNNs in robotic fields are limited due to the lack of practical training methods. In this paper, we therefore introduce both indirect and direct end-to-end training methods of SNNs for a lane-keeping vehicle. First, we adopt a policy learned using the Deep Q-Learning (DQN) algorithm and then subsequently transfer it to an SNN using supervised learning. Second, we adopt the reward-modulated spike-timing-dependent plasticity (R-STDP) for training SNNs directly, since it combines the advantages of both reinforcement learning and the well-known spike-timing-dependent plasticity (STDP). We examine the proposed approaches in three scenarios in which a robot is controlled to keep within lane markings by using an event-based neuromorphic vision sensor. We further demonstrate the advantages of the R-STDP approach in terms of the lateral localization accuracy and training time steps by comparing them with other three algorithms presented in this paper.
Year
DOI
Venue
2020
10.1016/j.neunet.2019.05.019
Neural Networks
Keywords
Field
DocType
Spiking neural network,End-to-end learning,R-STDP,Lane keeping
End-to-end principle,Neuromorphic engineering,Supervised learning,Implementation,Artificial intelligence,Robot,Vision sensor,Spiking neural network,Machine learning,Mathematics,Reinforcement learning
Journal
Volume
Issue
ISSN
121
1
0893-6080
Citations 
PageRank 
References 
1
0.35
0
Authors
5
Name
Order
Citations
PageRank
Zhenshan Bing1175.51
Claus Meschede210.35
Guang Chen3205.71
Alois Knoll Knoll41700271.32
Kai Huang546845.69