Indirect and Direct Training of Spiking Neural Networks for End-to-End Control of a Lane-Keeping Vehicle
This work addresses the problem of enabling energy-efficient SNN-based control for mobile robotics, though it appears incremental as it builds on existing training methods like DQN and STDP.
The paper tackled the lack of practical training methods for spiking neural networks (SNNs) in robotics by introducing indirect and direct end-to-end training approaches for lane-keeping vehicle control, demonstrating that the R-STDP method achieved advantages in lateral localization accuracy and training time steps compared to other algorithms.
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 \textcolor{black}{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.