Language-driven physics-based scene synthesis and editing via feature splatting

RZ Qiu, G Yang, W Zeng, X Wang - European Conference on Computer …, 2025 - Springer
Scene representations using 3D Gaussian primitives have produced excellent results in
modeling the appearance of static and dynamic 3D scenes. Many graphics applications …

Sim-to-real transfer via 3d feature fields for vision-and-language navigation

Z Wang, X Li, J Yang, Y Liu, S Jiang - arXiv preprint arXiv:2406.09798, 2024 - arxiv.org
Vision-and-language navigation (VLN) enables the agent to navigate to a remote location in
3D environments following the natural language instruction. In this field, the agent is usually …

Graspsplats: Efficient manipulation with 3d feature splatting

M Ji, RZ Qiu, X Zou, X Wang - arXiv preprint arXiv:2409.02084, 2024 - arxiv.org
The ability for robots to perform efficient and zero-shot grasping of object parts is crucial for
practical applications and is becoming prevalent with recent advances in Vision-Language …

[PDF][PDF] Gendp: 3d semantic fields for category-level generalizable diffusion policy

Y Wang, G Yin, B Huang, T Kelestemur… - … Annual Conference on …, 2024 - robopil.github.io
• Generalizable Representation: Some existing semantic fields or representations are
trained on small-scale datasets and are challenging to transfer to novel scenes or object …

Nl-slam for oc-vln: Natural language grounded slam for object-centric vln

S Raychaudhuri, D Ta, K Ashton, AX Chang… - arXiv preprint arXiv …, 2024 - arxiv.org
Landmark-based navigation (eg go to the wooden desk) and relative positional navigation
(eg move 5 meters forward) are distinct navigation challenges solved very differently in …

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 …

Challenges and Opportunities for Large-Scale Exploration with Air-Ground Teams using Semantics

F Cladera, ID Miller, Z Ravichandran, V Murali… - arXiv preprint arXiv …, 2024 - arxiv.org
One common and desirable application of robots is exploring potentially hazardous and
unstructured environments. Air-ground collaboration offers a synergistic approach to …

From Words to Poses: Enhancing Novel Object Pose Estimation with Vision Language Models

T Pulli, S Thalhammer, S Schwaiger… - arXiv preprint arXiv …, 2024 - arxiv.org
Robots are increasingly envisioned to interact in real-world scenarios, where they must
continuously adapt to new situations. To detect and grasp novel objects, zero-shot pose …

TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning

J Wu, W Chong, R Holmberg, A Prasad, Y Gao… - arXiv preprint arXiv …, 2024 - arxiv.org
Exploiting the promise of recent advances in imitation learning for mobile manipulation will
require the collection of large numbers of human-guided demonstrations. This paper …

WildLMa: Long Horizon Loco-Manipulation in the Wild

RZ Qiu, Y Song, X Peng, SA Suryadevara… - arXiv preprint arXiv …, 2024 - arxiv.org
In-the-wild'mobile manipulation aims to deploy robots in diverse real-world environments,
which requires the robot to (1) have skills that generalize across object configurations;(2) be …