Transfer of learning or leveraging a pre-trained network and fine-tuning it to perform new tasks has been successfully applied in a variety of machine intelligence fields, including computer vision, natural language processing and audio/speech recognition. Drawing inspiration from neuroscience research that suggests that both visual and tactile stimuli rouse similar neural networks in the human brain, in this work, we explore the idea of transferring learning from vision to touch in the context of 3D object recognition. In particular, deep convolutional neural networks (CNN) pre-trained on visual images are adapted and evaluated for the classification of tactile data sets. To do so, we ran experiments with five different pre-trained CNN architectures and on five different datasets acquired with different technologies of tactile sensors including BathTip, Gelsight, force-sensing resistor (FSR) array, a high-resolution virtual FSR sensor, and tactile sensors on the Barrett robotic hand. The results obtained confirm the transferability of learning from vision to touch to interpret 3D models. Due to its higher resolution, tactile data from optical tactile sensors was demonstrated to achieve higher classification rates based on visual features compared to other technologies relying on pressure measurements. Further analysis of the weight updates in the convolutional layer is performed to measure the similarity between visual and tactile features for each technology of tactile sensing. Comparing the weight updates in different convolutional layers suggests that by updating a few convolutional layers of a pre-trained CNN on visual data, it can be efficiently used to classify tactile data. Accordingly, we propose a hybrid architecture performing both visual and tactile 3D object recognition with a MobileNetV2 backbone. MobileNetV2 is chosen due to its smaller size and thus its capability to be implemented on mobile devices, such that the network can classify both visual and tactile data. An accuracy of 100% for visual and 77.63% for tactile data are achieved by the proposed architecture.

No abstract

Drawing inspiration from haptic exploration of objects by humans, the current work proposes a novel framework for robotic tactile object recognition, where visual information in the form of a set of visually interesting points is employed to guide the process of tactile data acquisition. Neuroscience research confirms the integration of cutaneous data as a response to surface changes sensed by humans with data from joints, muscles, and bones (kinesthetic cues) for object recognition. On the other hand, psychological studies demonstrate that humans tend to follow object contours to perceive their global shape, which leads to object recognition. In compliance with these findings, a series of contours are determined around a set of 24 virtual objects from which bimodal tactile data (kinesthetic and cutaneous) are obtained sequentially and by adaptively changing the size of the sensor surface according to the object geometry for each object. A virtual Force Sensing Resistor array (FSR) is employed to capture cutaneous cues. Two different methods for sequential data classification are then implemented using Convolutional Neural Networks (CNN) and conventional classifiers, including support vector machines and k-nearest neighbors. In the case of conventional classifiers, we exploit contourlet transformation to extract features from tactile images. In the case of CNN, two networks are trained for cutaneous and kinesthetic data and a novel hybrid decision-making strategy is proposed for object recognition. The proposed framework is tested both for contours determined blindly (randomly determined contours of objects) and contours determined using a model of visual attention. Trained classifiers are tested on 4560 new sequential tactile data and the CNN trained over tactile data from object contours selected by the model of visual attention yields an accuracy of 98.97% which is the highest accuracy among other implemented approaches.

No abstract

No abstract