Renderable neural radiance map for visual navigation

O Kwon, J Park, S Oh - … of the IEEE/CVF Conference on …, 2023‏ - openaccess.thecvf.com
We propose a novel type of map for visual navigation, a renderable neural radiance map
(RNR-Map), which is designed to contain the overall visual information of a 3D environment …

Nerf in the palm of your hand: Corrective augmentation for robotics via novel-view synthesis

A Zhou, MJ Kim, L Wang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Expert demonstrations are a rich source of supervision for training visual robotic
manipulation policies, but imitation learning methods often require either a large number of …

Rgbgrasp: Image-based object gras** by capturing multiple views during robot arm movement with neural radiance fields

C Liu, K Shi, K Zhou, H Wang, J Zhang… - IEEE Robotics and …, 2024‏ - ieeexplore.ieee.org
Robotic research encounters a significant hurdle when it comes to the intricate task of
gras** objects that come in various shapes, materials, and textures. Unlike many prior …

Diva-360: The dynamic visual dataset for immersive neural fields

CY Lu, P Zhou, A **ng, C Pokhariya… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Advances in neural fields are enabling high-fidelity capture of the shape and appearance of
dynamic 3D scenes. However their capabilities lag behind those offered by conventional …

Neural Fields in Robotics: A Survey

MZ Irshad, M Comi, YC Lin, N Heppert… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Neural Fields have emerged as a transformative approach for 3D scene representation in
computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and …

FuncGrasp: Learning Object-Centric Neural Grasp Functions from Single Annotated Example Object

H Chen, B Xu, S Leutenegger - 2024 IEEE International …, 2024‏ - ieeexplore.ieee.org
We present FuncGrasp, a framework that can infer dense yet reliable grasp configurations
for unseen objects using one annotated object and single-view RGB-D observation via …

Dreamup3d: Object-centric generative models for single-view 3d scene understanding and real-to-sim transfer

Y Wu, HS de Ocáriz Borde, J Collins… - IEEE Robotics and …, 2024‏ - ieeexplore.ieee.org
3D scene understanding for robotic applications exhibits a unique set of requirements
including real-time inference, object-centric latent representation learning, accurate 6D pose …

Diffusion meets dagger: Supercharging eye-in-hand imitation learning

X Zhang, M Chang, P Kumar, S Gupta - arxiv preprint arxiv:2402.17768, 2024‏ - arxiv.org
A common failure mode for policies trained with imitation is compounding execution errors at
test time. When the learned policy encounters states that are not present in the expert …

[PDF][PDF] Implicit neural representation for 3d shape reconstruction using vision-based tactile sensing

M Comi, A Church, K Li, L Aitchison, NF Lepora - 2023‏ - shanluo.github.io
Humans rely on their senses of vision and touch to build a 3D understanding of their
physical surroundings. This understanding is critical in various fields of robotics, including …

[PDF][PDF] Robotics: An Idiosyncratic Snapshot in the Age of LLMs

A Majumdar - IRoM Lab, 2023‏ - irom-lab.princeton.edu
Robotics: An Idiosyncratic Snapshot in the Age of LLMs Page 1 Robotics: An Idiosyncratic
Snapshot in the Age of LLMs Anirudha Majumdar August 2, 2023 1 Introduction The goal of …