Zobrazeno 1 - 10
of 224
pro vyhledávání: '"Roberson, Matthew"'
Constructing 3D representations of object geometry is critical for many downstream robotics tasks, particularly tabletop manipulation problems. These representations must be built from potentially noisy partial observations. In this work, we focus on
Externí odkaz:
http://arxiv.org/abs/2411.19461
Many recent developments for robots to represent environments have focused on photorealistic reconstructions. This paper particularly focuses on generating sequences of images from the photorealistic Gaussian Splatting models, that match instructions
Externí odkaz:
http://arxiv.org/abs/2410.06014
Building accurate representations of the environment is critical for intelligent robots to make decisions during deployment. Advances in photorealistic environment models have enabled robots to develop hyper-realistic reconstructions, which can be us
Externí odkaz:
http://arxiv.org/abs/2410.05044
Autor:
Xie, Quanting, Min, So Yeon, Zhang, Tianyi, Xu, Kedi, Bajaj, Aarav, Salakhutdinov, Ruslan, Johnson-Roberson, Matthew, Bisk, Yonatan
There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhouse of large-scale non-parametric know
Externí odkaz:
http://arxiv.org/abs/2409.18313
Humans have the remarkable ability to use held objects as tools to interact with their environment. For this to occur, humans internally estimate how hand movements affect the object's movement. We wish to endow robots with this capability. We contri
Externí odkaz:
http://arxiv.org/abs/2407.10331
Autor:
Zhang, Tianyi, Zhi, Weiming, Huang, Kaining, Mangelson, Joshua, Barbalata, Corina, Johnson-Roberson, Matthew
Water caustics are commonly observed in seafloor imaging data from shallow-water areas. Traditional methods that remove caustic patterns from images often rely on 2D filtering or pre-training on an annotated dataset, hindering the performance when ge
Externí odkaz:
http://arxiv.org/abs/2407.10318
Autor:
Xu, Xiaohao, Zhang, Tianyi, Wang, Sibo, Li, Xiang, Chen, Yongqi, Li, Ye, Raj, Bhiksha, Johnson-Roberson, Matthew, Huang, Xiaonan
Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy. While real-world datasets are invaluable, sim
Externí odkaz:
http://arxiv.org/abs/2406.16850
Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges. This has motivated the development of self-supervised pretraining strategies. However, existing pretraining met
Externí odkaz:
http://arxiv.org/abs/2405.17942
Representing the environment is a central challenge in robotics, and is essential for effective decision-making. Traditionally, before capturing images with a manipulator-mounted camera, users need to calibrate the camera using a specific external ma
Externí odkaz:
http://arxiv.org/abs/2404.11683
Teaching Robots Where To Go And How To Act With Human Sketches via Spatial Diagrammatic Instructions
This paper introduces Spatial Diagrammatic Instructions (SDIs), an approach for human operators to specify objectives and constraints that are related to spatial regions in the working environment. Human operators are enabled to sketch out regions di
Externí odkaz:
http://arxiv.org/abs/2403.12465