Related papers: The RGB-D Triathlon: Towards Agile Visual Toolboxe…

We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

Visual quality inspection in high performance manufacturing can benefit from automation, due to cost savings and improved rigor. Deep learning techniques are the current state of the art for generic computer vision tasks like classification…

State-of-the-art 3D models, which excel in recognition tasks, typically depend on large-scale datasets and well-defined category sets. Recent advances in multi-modal pre-training have demonstrated potential in learning 3D representations by…

We consider learning representations (features) in the setting in which we have access to multiple unlabeled views of the data for learning while only one view is available for downstream tasks. Previous work on this problem has proposed…

Transparent object perception is a rapidly developing research problem in artificial intelligence. The ability to perceive transparent objects enables robots to achieve higher levels of autonomy, unlocking new applications in various…

Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments. To achieve this, we are exploring and evaluating a…

Creating a vision pipeline for different datasets to solve a computer vision task is a complex and time consuming process. Currently, these pipelines are developed with the help of domain experts. Moreover, there is no systematic structure…

Intelligent robots require object-level scene understanding to reason about possible tasks and interactions with the environment. Moreover, many perception tasks such as scene reconstruction, image retrieval, or place recognition can…

Traditional visual servoing methods suffer from serving between scenes from multiple perspectives, which humans can complete with visual signals alone. In this paper, we investigated how multi-perspective visual servoing could be solved…

Object transportation could be a challenging problem for a single robot due to the oversize and/or overweight issues. A multi-robot system can take the advantage of increased driving power and more flexible configuration to solve such a…

Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition. However, most of the existing action…

The ability to classify objects is fundamental for robots. Besides knowledge about their visual appearance, captured by the RGB channel, robots heavily need also depth information to make sense of the world. While the use of deep networks…

Representation learning, i.e. the generation of representations useful for downstream applications, is a task of fundamental importance that underlies much of the success of deep neural networks (DNNs). Recently, robustness to adversarial…

Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but…

Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area…

Robot learning is a very promising topic for the future of automation and machine intelligence. Future robots should be able to autonomously acquire skills, learn to represent their environment, and interact with it. While these topics have…

Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high…

This paper introduces a novel deep learning-based multimodal fusion architecture aimed at enhancing the perception capabilities of autonomous navigation robots in complex environments. By utilizing innovative feature extraction modules,…

Deep reinforcement learning (DRL) has been proven to be a powerful paradigm for learning complex control policy autonomously. Numerous recent applications of DRL in robotic grasping have successfully trained DRL robotic agents end-to-end,…