Enhancing Robotic Arm Activity Recognition with Vision Transformers and Wavelet-Transformed Channel State Information

TL;DR

This paper introduces a novel machine learning approach combining wavelet transforms and vision transformers to improve robotic arm activity recognition using Wi-Fi CSI data, especially when line-of-sight is blocked.

Contribution

The paper presents a new method that outperforms CNN and LSTM models in recognizing robotic arm activities from Wi-Fi CSI data without relying on visual sensors.

Findings

Wavelet transform enhances transformer network accuracy.

Method outperforms CNN and LSTM models.

Effective in obstructed line-of-sight scenarios.

Abstract

Vision-based methods are commonly used in robotic arm activity recognition. These approaches typically rely on line-of-sight (LoS) and raise privacy concerns, particularly in smart home applications. Passive Wi-Fi sensing represents a new paradigm for recognizing human and robotic arm activities, utilizing channel state information (CSI) measurements to identify activities in indoor environments. In this paper, a novel machine learning approach based on discrete wavelet transform and vision transformers for robotic arm activity recognition from CSI measurements in indoor settings is proposed. This method outperforms convolutional neural network (CNN) and long short-term memory (LSTM) models in robotic arm activity recognition, particularly when LoS is obstructed by barriers, without relying on external or internal sensors or visual aids. Experiments are conducted using four different data collection scenarios and four different robotic arm activities. Performance results demonstrate that wavelet transform can significantly enhance the accuracy of visual transformer networks in robotic arms activity recognition.