No abstract

In this paper, we present a novel tactile-based method for detecting slippage in robotic manipulation, using a single piezoelectric sensor. The method combines spectral analysis (FFT) and deep learning (GRU) for improved efficiency and adaptability. We implement an automated data-collection process with accurate and unbiased labels of slip events. The proposed method is evaluated through an ablation study characterizing the influence of model hyperparameters and interaction settings. The results show a high classification accuracy of 98.70% at 100Hz and detection delays of 8.5 ± 23.7ms, demonstrating the relevance of our spectro-temporal pipeline. The proposed method has the potential to enhance the performance of robotic systems and increase their reliability in robotic grasping applications.

Training deep learning models for accurate spatiotemporal recognition of facial expressions in videos requires significant computational resources. For practical reasons, 3D Convolutional Neural Networks (3D CNNs) are usually trained with relatively short clips randomly extracted from videos. However, such uniform sampling is generally sub-optimal because equal importance is assigned to each temporal clip. In this paper, we present a strategy for efficient video-based training of 3D CNNs. It relies on softmax temporal pooling and a weighted sampling mechanism to select the most relevant training clips. The proposed softmax strategy provides several advantages -a reduced computational complexity due to efficient clip sampling, and an improved accuracy since temporal weighting focuses on more relevant clips during both training and inference. Experimental results obtained with the proposed method on several facial expression recognition benchmarks show the benefits of focusing on more informative clips in training videos. In particular, our approach improves performance and computational cost by reducing the impact of inaccurate trimming and coarse annotation of videos, and heterogeneous distribution of visual information across time.