Probabilistic Spiking Neural Network for Robotic Tactile Continual Learning
Senlin Fang, Yiwen Liu, Chengliang Liu, Jingnan Wang, Yuanzhe Su, Yupo Zhang, Hoiio Kong, Zhengkun Yi
Abstract
The sense of touch is essential for robots to perform various daily tasks. Artificial Neural Networks have shown significant promise in advancing robotic tactile learning. However, due to the changing of tactile data distribution as robots encounter new tasks, ANN-based robotic tactile learning suffers from catastrophic forgetting. To solve this problem, we introduce a novel continual learning (CL) framework called the Probabilistic Spiking Neural Network with Variational Continual Learning (PSNN-VCL). In this framework, PSNN introduces uncertainty during spike emission and can apply fast Variational Inference by optimizing the uncertainty through backpropagation, which significantly reduces the required model parameters for VCL. We establish a robotic tactile CL benchmark using publicly available datasets to evaluate our method. Experimental results demonstrated that, compared to other CL methods, PSNN-VCL not only achieves superior performance in terms of widely used CL metrics but also achieves at least a 50% reduction in model parameters on the robotic tactile CL benchmark.
BibTeX
@inproceedings{icra2024_probabilisticspi,
title = {Probabilistic Spiking Neural Network for Robotic Tactile Continual Learning},
author = {Senlin Fang and Yiwen Liu and Chengliang Liu and Jingnan Wang and Yuanzhe Su and Yupo Zhang and Hoiio Kong and Zhengkun Yi and Xinyu Wu},
booktitle = {ICRA 2024},
year = {2024}
}