Related papers: SenseNet: 3D Objects Database and Tactile Simulato…
Tactile sensing is critical for robotic grasping and manipulation of objects under visual occlusion. However, in contrast to simulations of robot arms and cameras, current simulations of tactile sensors have limited accuracy, speed, and…
Rapid deployment of new tactile sensors is essential for scalable robotic manipulation, especially in multi-fingered hands equipped with vision-based tactile sensors. However, current methods for inferring contact properties rely heavily on…
The integration of visual-tactile stimulus is common while humans performing daily tasks. In contrast, using unimodal visual or tactile perception limits the perceivable dimensionality of a subject. However, it remains a challenge to…
The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is…
The use of deep learning techniques has exploded during the last few years, resulting in a direct contribution to the field of artificial intelligence. This work aims to be a review of the state-of-the-art in scene recognition with deep…
Knowledge creation occurs in the process of social interaction. As our service-based society is evolving into a knowledge-based society there is an acute need for more effective collaboration and knowledge-sharing systems to be used by…
Sensor-based activity recognition seeks the profound high-level knowledge about human activities from multitudes of low-level sensor readings. Conventional pattern recognition approaches have made tremendous progress in the past years.…
We propose SplitNet, a method for decoupling visual perception and policy learning. By incorporating auxiliary tasks and selective learning of portions of the model, we explicitly decompose the learning objectives for visual navigation into…
Selection of appropriate tools and use of them when performing daily tasks is a critical function for introducing robots for domestic applications. In previous studies, however, adaptability to target objects was limited, making it…
The smart textile and wearables sector is looking towards advancing technologies to meet both industry, consumer and new emerging innovative textile application demands, within a fast paced textile industry. In parallel inspiration based on…
Interactive lenses are useful tools for supporting the analysis of data in different ways. Most existing lenses are designed for 2D visualization and are operated using standard mouse and keyboard interaction. On the other hand, research on…
Active perception has been employed in many domains, particularly in the field of robotics. The idea of active perception is to utilize the input data to predict the next action that can help robots to improve their performance. The main…
The current state-of-the-art object recognition algorithms, deep convolutional neural networks (DCNNs), are inspired by the architecture of the mammalian visual system, and are capable of human-level performance on many tasks. However, even…
Human is able to conduct 3D recognition by a limited number of haptic contacts between the target object and his/her fingers without seeing the object. This capability is defined as `haptic glance' in cognitive neuroscience. Most of the…
Tactile sensors are believed to be essential in robotic manipulation, and prior works often rely on experts to reason the sensor feedback and design a controller. With the recent advancement in data-driven approaches, complicated…
Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet, which connects each layer to every other layer…
Deep neural networks (DNNs) have recently achieved great success in a multitude of classification tasks. Ensembles of DNNs have been shown to improve the performance. In this paper, we explore the recent state-of-the-art DNNs used for image…
There has been increasing interest in deploying IoT devices to study human behaviour in locations such as homes and offices. Such devices can be deployed in a laboratory or `in the wild' in natural environments. The latter allows one to…
We present Megaverse, a new 3D simulation platform for reinforcement learning and embodied AI research. The efficient design of our engine enables physics-based simulation with high-dimensional egocentric observations at more than 1,000,000…
Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…