Spiking Reinforcement Learning with Memory Ability for Mapless Navigation
Bo Yang, Mengwen Yuan, Chengjun Zhang, Chaofei Hong, Gang Pan, Huajin Tang
Abstract
Our study focuses on mapless navigation in robotics, which involves navigating without an established obstacle map of the environment. Spiking Neural Networks (SNNs) have recently been applied to this task using Deep Reinforcement Learning (DRL), but face challenges in dynamic and partially observable environments, as well as inaccuracies in transmitted data. To overcome these issues, we propose a Multi-Critic DDPG with Spiking Memory (MC-DDPGSM) framework. Our approach introduces a spiking Gate Recurrent Unit layer (Spiking-GRU) to provide memory function and evaluates the state-action value with multi-critic networks. The experimental results demonstrate that our method achieves better performance (success rate, navigation distance, navigation time spent, and power consumption) in complex navigation tasks compared to the state-of-the-art approaches. Furthermore, our model can be transferred to unseen environments without the need for fine-tuning.
BibTeX
@inproceedings{iros2023_spikingreinforce,
title = {Spiking Reinforcement Learning with Memory Ability for Mapless Navigation},
author = {Bo Yang and Mengwen Yuan and Chengjun Zhang and Chaofei Hong and Gang Pan and Huajin Tang},
booktitle = {IROS 2023},
year = {2023}
}