3 papers
cs.RO2025
GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
Ali Abouzeid, Malak Mansour, Qinbo Sun +2
Vision-Language-Action (VLA) models often fail to generalize to unseen camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images…
cs.RO2025
A Point Cloud Completion Approach for the Grasping of Partially Occluded Objects and Its Applications in Robotic Strawberry Harvesting
Ali Abouzeid, Malak Mansour, Chengsong Hu +1
In robotic fruit picking applications, managing object occlusion in unstructured settings poses a substantial challenge for designing grasping algorithms. Using strawberry harvesti…
cs.CL2025
Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models
Malak Mansour, Ahmed Aly, Bahey Tharwat +3
Large Language Models (LLMs) such as GPT-4, trained on huge amount of datasets spanning multiple domains, exhibit significant reasoning, understanding, and planning capabilities ac…