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

Collaborative robots working on a common task are necessary for many applications. One of the challenges for achieving collaboration in a team of robots is mutual tracking and identification. We present a novel pipeline for online…

Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games…

The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed…

Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of…

The widespread success of artificial intelligence in fields like natural language processing and computer vision has not yet fully transferred to robotics, where progress is hindered by the lack of large-scale training data and the…

In ground-view object change detection, the recently emerging mapless navigation has great potential to navigate a robot to objects distantly detected (e.g., books, cups, clothes) and acquire high-resolution object images, to identify their…

We propose to take a novel approach to robot system design where each building block of a larger system is represented as a differentiable program, i.e. a deep neural network. This representation allows for integrating algorithmic planning…

Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection,…

In this paper, we address the multi-robot collaborative perception problem, specifically in the context of multi-view infilling for distributed semantic segmentation. This setting entails several real-world challenges, especially those…

Image segmentation is a vital task for providing human assistance and enhancing autonomy in our daily lives. In particular, RGB-D segmentation-leveraging both visual and depth cues-has attracted increasing attention as it promises richer…

The advent of the Microsoft Kinect three years ago stimulated not only the computer vision community for new algorithms and setups to tackle well-known problems in the community but also sparked the launch of several new benchmark datasets…

Dynamic objects have a significant impact on the robot's perception of the environment which degrades the performance of essential tasks such as localization and mapping. In this work, we address this problem by synthesizing plausible…

In the RGB-D vision community, extensive research has been focused on designing multi-modal learning strategies and fusion structures. However, the complementary and fusion mechanisms in RGB-D models remain a black box. In this paper, we…

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…

Scene recognition is one of the basic problems in computer vision research with extensive applications in robotics. When available, depth images provide helpful geometric cues that complement the RGB texture information and help to identify…

Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence. It has great fundamental importance and strong industrial…

Robots have to face challenging perceptual settings, including changes in viewpoint, lighting, and background. Current simulated reinforcement learning (RL) benchmarks such as DM Control provide visual input without such complexity, which…

The ability to visually recognize objects is a fundamental skill for robotics systems. Indeed, a large variety of tasks involving manipulation, navigation or interaction with other agents, deeply depends on the accurate understanding of the…

Deep Reinforcement Learning has been successfully applied in various computer games [8]. However, it is still rarely used in real-world applications, especially for the navigation and continuous control of real mobile robots [13]. Previous…

Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with…