Object recognition for robotics from tactile time series data utilising different neural network architectures
This work addresses object recognition for robots by enhancing tactile sensing, but it is incremental as it builds on existing neural network methods.
The paper tackled object classification for robotics using tactile time-series data by comparing CNN and LSTM architectures and augmenting training data, achieving improved accuracies of about 94% for both BioTac SP and WTS-FT sensors.
Robots need to exploit high-quality information on grasped objects to interact with the physical environment. Haptic data can therefore be used for supplementing the visual modality. This paper investigates the use of Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) neural network architectures for object classification on Spatio-temporal tactile grasping data. Furthermore, we compared these methods using data from two different fingertip sensors (namely the BioTac SP and WTS-FT) in the same physical setup, allowing for a realistic comparison across methods and sensors for the same tactile object classification dataset. Additionally, we propose a way to create more training examples from the recorded data. The results show that the proposed method improves the maximum accuracy from 82.4% (BioTac SP fingertips) and 90.7% (WTS-FT fingertips) with complete time-series data to about 94% for both sensor types.