Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Blum, Hermann"'
Despite increasing research efforts on household robotics, robots intended for deployment in domestic settings still struggle with more complex tasks such as interacting with functional elements like drawers or light switches, largely due to limited
Externí odkaz:
http://arxiv.org/abs/2409.11870
Autor:
Di Giammarino, Luca, Sun, Boyang, Grisetti, Giorgio, Pollefeys, Marc, Blum, Hermann, Barath, Daniel
Accurate localization in diverse environments is a fundamental challenge in computer vision and robotics. The task involves determining a sensor's precise position and orientation, typically a camera, within a given space. Traditional localization me
Externí odkaz:
http://arxiv.org/abs/2407.15593
State-of-the-art approaches for 6D object pose estimation assume the availability of CAD models and require the user to manually set up physically-based rendering (PBR) pipelines for synthetic training data generation. Both factors limit the applicat
Externí odkaz:
http://arxiv.org/abs/2407.12207
Recently, Vision-Language Models (VLMs) have advanced segmentation techniques by shifting from the traditional segmentation of a closed-set of predefined object classes to open-vocabulary segmentation (OVS), allowing users to segment novel classes an
Externí odkaz:
http://arxiv.org/abs/2405.20141
Natural language interfaces to embodied AI are becoming more ubiquitous in our daily lives. This opens further opportunities for language-based interaction with embodied agents, such as a user instructing an agent to execute some task in a specific l
Externí odkaz:
http://arxiv.org/abs/2404.14565
Autor:
Lemke, Oliver, Bauer, Zuria, Zurbrügg, René, Pollefeys, Marc, Engelmann, Francis, Blum, Hermann
In recent years, modern techniques in deep learning and large-scale datasets have led to impressive progress in 3D instance segmentation, grasp pose estimation, and robotics. This allows for accurate detection directly in 3D scenes, object- and envir
Externí odkaz:
http://arxiv.org/abs/2404.12440
Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generate labels for RGB-D scans at eq
Externí odkaz:
http://arxiv.org/abs/2311.12174
Autor:
Zhu, Siting, Wang, Guangming, Blum, Hermann, Liu, Jiuming, Song, Liang, Pollefeys, Marc, Wang, Hesheng
We propose SNI-SLAM, a semantic SLAM system utilizing neural implicit representation, that simultaneously performs accurate semantic mapping, high-quality surface reconstruction, and robust camera tracking. In this system, we introduce hierarchical s
Externí odkaz:
http://arxiv.org/abs/2311.11016
Rather than having each newly deployed robot create its own map of its surroundings, the growing availability of SLAM-enabled devices provides the option of simply localizing in a map of another robot or device. In cases such as multi-robot or human-
Externí odkaz:
http://arxiv.org/abs/2310.02650
This paper presents a mixed-reality human-robot teaming system. It allows human operators to see in real-time where robots are located, even if they are not in line of sight. The operator can also visualize the map that the robots create of their env
Externí odkaz:
http://arxiv.org/abs/2310.02392