Related papers: Hypernom: Mapping VR Headset Orientation to S^3
Depth perception is fundamental for robots to understand the surrounding environment. As the view of cognitive neuroscience, visual depth perception methods are divided into three categories, namely binocular, active, and pictorial. The…
Probabilistic 3D map has been applied to object segmentation with multiple camera viewpoints, however, conventional methods lack of real-time efficiency and functionality of multilabel object mapping. In this paper, we propose a method to…
Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely…
Sequential manipulation tasks require a robot to perceive the state of an environment and plan a sequence of actions leading to a desired goal state. In such tasks, the ability to reason about spatial relations among object entities from…
Robot manipulation of unknown objects in unstructured environments is a challenging problem due to the variety of shapes, materials, arrangements and lighting conditions. Even with large-scale real-world data collection, robust perception…
In primate brains, tactile and proprioceptive inputs are relayed to the somatosensory cortex which is known for somatotopic representations, or, "homunculi". Our research centers on understanding the mechanisms of the formation of these and…
To catch a thrown object, a robot must be able to perceive the object's motion and generate control actions in a timely manner. Rather than explicitly estimating the object's 3D position, this work focuses on a novel approach that…
Being able to perceive the semantics and the spatial structure of the environment is essential for visual navigation of a household robot. However, most existing works only employ visual backbones pre-trained either with independent images…
For robot manipulation, a complete and accurate object shape is desirable. Here, we present a method that combines visual and haptic reconstruction in a closed-loop pipeline. From an initial viewpoint, the object shape is reconstructed…
What is Virtual Reality? A professional tool, made to facilitate our everyday tasks? A conceptual mistake, accompanied by cybersickness and unsolved locomotion issues since the very beginning? Or just another source of entertainment that…
The double orthogonal projection of the 4-space onto two mutually perpendicular 3-spaces is a method of visualization of four-dimensional objects in a three-dimensional space. We present an interactive animation of the stereographic…
A three-dimensional orthoscheme is defined as a tetrahedron whose base is a right-angled triangle and an edge joining the apex and a non-right-angled vertex is perpendicular to the base. A generalization, called complete orthoschemes, of…
We propose Hand-Eye Autonomous Delivery (HEAD), a framework that learns navigation, locomotion, and reaching skills for humanoids, directly from human motion and vision perception data. We take a modular approach where the high-level…
A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from challenges related to…
Video-to-video synthesis is a challenging problem aiming at learning a translation function between a sequence of semantic maps and a photo-realistic video depicting the characteristics of a driving video. We propose a head-to-head system…
Visual object navigation using learning methods is one of the key tasks in mobile robotics. This paper introduces a new representation of a scene semantic map formed during the embodied agent interaction with the indoor environment. It is…
Visual Place Recognition (VPR) enables coarse localization by comparing query images to a reference database of geo-tagged images. Recent breakthroughs in deep learning architectures and training regimes have led to methods with improved…
The discovery of place cells and other spatially modulated neurons in the hippocampal complex of rodents has been crucial to elucidating the neural basis of spatial cognition. More recently, the replay of neural sequences encoding…
Motivated by the human way of memorizing images we introduce their functional representation, where an image is represented by a neural network. For this purpose, we construct a hypernetwork which takes an image and returns weights to the…
The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision…