Flexible piezoelectric tactile system improves robotic object recognition accuracy
Flexible Piezoelectric Tactile Sensing System for Intelligent Object Recognition
Robotics
Summary
Recognizing objects by touch quickly and accurately is hard for robots, especially right when they first grab something. The authors created a flexible touch sensor system made of piezoelectric sensors that can sense pressures and vibrations across many points. They tested several ways to teach a computer to recognize six common objects using this sensor data and found that using heatmaps and deep learning worked best. Their best setup could quickly and accurately identify objects in about 100 milliseconds with low energy use, showing promise for helping robots handle things better in real time.
What this means in practice
- •For roboticists: Improve robotic grasping by integrating a flexible piezoelectric sensor array to quickly recognize objects during early contact.
- •For wearable device developers: Design wearable devices with distributed tactile sensors enabling fast and energy-efficient object recognition through touch feedback.
Authors
Razan Khalifeh, Mohamad Yaacoub, Christian Gianoglio, Moustafa Saleh, Maurizio Valle, Yahya Abbass
Abstract
Tactile sensing provides information about object properties that can improve robotic grasping and manipulation. However, accurate object recognition during the early stages of grasping remains challenging, particularly under strict real-time constraints. This study presents a flexible, distributed piezoelectric tactile sensing system for early-stage object recognition. The system was experimentally evaluated using six everyday objects and three recognition approaches: feature-based classification using support vector machines (SVMs), raw-signal classification using 1D convolutional neural networks (1D-CNNs) and convolutional recurrent neural networks (C-RNNs), and spatiotemporal heatmap classification using a 2D-CNN. The effects of sensor count and temporal window size on recognition accuracy and real-time feasibility were systematically investigated. Increasing the number of sensing elements improved recognition performance across all approaches. The best-performing method, based on spatiotemporal heatmaps and a 2D-CNN, achieved F1-scores of 0.9796, 0.9846, and 0.9903 using 16, 24, and 32 sensors, respectively. The optimal configuration, comprising 32 sensors and a 100-ms temporal window (50 samples), was deployed on an embedded edge platform, achieving an end-to-end recognition latency of approximately 101 ms from contact onset and an energy consumption of 63.8 microjoules per inference. These results demonstrate the potential of distributed piezoelectric tactile sensing for accurate, energy-efficient, and real-time object recognition during robotic grasping.