Bayesian deep learning for affordance segmentation in images
Affordances are a fundamental concept in robotics since they relate available actions for an
agent depending on its sensory-motor capabilities and the environment. We present a novel …
agent depending on its sensory-motor capabilities and the environment. We present a novel …
Introspective perception for mobile robots
Perception algorithms that provide estimates of their uncertainty are crucial to the
development of autonomous robots that can operate in challenging and uncontrolled …
development of autonomous robots that can operate in challenging and uncontrolled …
On the uncertain single-view depths in colonoscopies
Estimating depth information from endoscopic images is a prerequisite for a wide set of AI-
assisted technologies, such as accurate localization and measurement of tumors, or …
assisted technologies, such as accurate localization and measurement of tumors, or …
LightDepth: Single-View Depth Self-Supervision from Illumination Decline
Single-view depth estimation can be remarkably effective if there is enough ground-truth
depth data for supervised training. However, there are scenarios, especially in medicine in …
depth data for supervised training. However, there are scenarios, especially in medicine in …
LightDepth: Single-View Depth Self-Supervision from Illumination Decline
Résumé Single-view depth estimation can be remarkably effective if there is enough ground-
truth depth data for supervised training. However, there are scenarios, especially in …
truth depth data for supervised training. However, there are scenarios, especially in …
ProbNet: Bayesian deep neural network for point cloud analysis
Deep neural networks exhibit extreme superiority in natural language processing and
computer vision. With the fast development of 3D sensing technology, point cloud has been …
computer vision. With the fast development of 3D sensing technology, point cloud has been …
Uncertainty and Self-Supervision in Single-View Depth
J Rodriguez-Puigvert - arxiv preprint arxiv:2406.14226, 2024 - arxiv.org
Single-view depth estimation refers to the ability to derive three-dimensional information per
pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed …
pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed …
On Performance and Calibration of Natural Gradient Langevin Dynamics
Producing deep neural network (DNN) models with calibrated confidence is essential for
applications in many fields, such as medical image analysis, natural language processing …
applications in many fields, such as medical image analysis, natural language processing …
Model-Based Policy Optimization for Legged Locomotion
J Garcia-Barcos, R Martinez-Cantin… - 2024 7th Iberian …, 2024 - ieeexplore.ieee.org
In this paper, we explore model-based reinforcement learning (MBRL) for legged locomotion
in robotics, employing state-of-the-art techniques to evaluate the performance and stability of …
in robotics, employing state-of-the-art techniques to evaluate the performance and stability of …
Analysis of linearization methods for Bayesian Deep Learning.
C Plou Izquierdo, R Martínez Cantín, AC Murillo Arnal - zaguan.unizar.es
Deep learning has revolutionized the field of machine learning, outperforming traditional
methods in a wide range of areas such as computer vision, robotics or natural language …
methods in a wide range of areas such as computer vision, robotics or natural language …