A review of tactile information: Perception and action through touch

Q Li, O Kroemer, Z Su, FF Veiga… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Tactile sensing is a key sensor modality for robots interacting with their surroundings. These
sensors provide a rich and diverse set of data signals that contain detailed information …

Deep learning in robotics: Survey on model structures and training strategies

AI Károly, P Galambos, J Kuti… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
The ever-increasing complexity of robot applications induces the need for methods to
approach problems with no (viable) analytical solution. Deep learning (DL) provides a set of …

Self-supervised visual terrain classification from unsupervised acoustic feature learning

J Zürn, W Burgard, A Valada - IEEE Transactions on Robotics, 2020 - ieeexplore.ieee.org
Mobile robots operating in unknown urban environments encounter a wide range of
complex terrains to which they must adapt their planned trajectory for safe and efficient …

Sound source localization in a multipath environment using convolutional neural networks

EL Ferguson, SB Williams, CT ** - 2018 IEEE International …, 2018 - ieeexplore.ieee.org
The propagation of sound in a shallow water environment is characterized by boundary
reflections from the sea surface and sea floor. These reflections result in multiple (indirect) …

A deep convolution neural network method for land cover map**: A case study of Qinhuangdao, China

Y Hu, Q Zhang, Y Zhang, H Yan - Remote Sensing, 2018 - mdpi.com
Land cover and its dynamic information is the basis for characterizing surface conditions,
supporting land resource management and optimization, and assessing the impacts of …

Deep recurrent neural networks for audio classification in construction sites

M Scarpiniti, D Comminiello, A Uncini… - 2020 28th European …, 2021 - ieeexplore.ieee.org
In this paper, we propose a Deep Recurrent Neural Network (DRNN) approach based on
Long-Short Term Memory (LSTM) units for the classification of audio signals recorded in …

Feature learning for fault detection in high-dimensional condition monitoring signals

G Michau, Y Hu, T Palmé… - … Part O: Journal of Risk and …, 2020 - journals.sagepub.com
Complex industrial systems are continuously monitored by a large number of
heterogeneous sensors. The diversity of their operating conditions and the possible fault …

Deep spatiotemporal models for robust proprioceptive terrain classification

A Valada, W Burgard - The International Journal of Robotics …, 2017 - journals.sagepub.com
Terrain classification is a critical component of any autonomous mobile robot system
operating in unknown real-world environments. Over the years, several proprioceptive …

Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning

HH Chieng, N Wahid, P Ong, SRK Perla - arxiv preprint arxiv:1812.06247, 2018 - arxiv.org
Activation functions are essential for deep learning methods to learn and perform complex
tasks such as image classification. Rectified Linear Unit (ReLU) has been widely used and …

Convolutional neural networks for passive monitoring of a shallow water environment using a single sensor

EL Ferguson, R Ramakrishnan… - … on Acoustics, Speech …, 2017 - ieeexplore.ieee.org
A cost effective approach to remote monitoring of protected areas such as marine reserves
and restricted naval waters is to use passive sonar to detect, classify, localize, and track …