Hanz Cuevas Velasquez

Ph.D. Student - The University of Edinburgh


BC-1.12, Bayes Centre, School of Informatics 

University of Edinburgh

47 Potterrow, Edinburgh EH8 9BT

Research


Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Segmentation


An innovative two-headed attention layer that combines geometric and latent features to segment a 3D scene into semantically meaningful subsets. Each head combines local and global information, using either the geometric or latent features, of a neighborhood of points and uses this information to learn better local relationships.

Real-time Stereo Visual Servoing for Rose Pruning with Robotic Arm


Visual servoing to find and cut rose branches in real-time in a real garden using a robotic arm and eye-in-hand stereo camera. 

ICRA 2020

Segmentation and 3D Reconstruction of Rose Plants from Stereoscopic Images


Part of the vision module of a garden robot capable of navigating towards rose bushes and clip them according to a set of pruning rules. The method is responsible for performing the segmentation of the branches and recovering their morphology in 3D. 

Computers and Electronics in Agriculture 2020

Hybrid Multi-camera Visual Servoing to Moving Target


A novel hybrid multi-camera eye-to-hand (EtoH) / eye-in-hand (EinH) approach to guide a robotarm in different tasks. The target point is assumed to bedynamic, which makes the problem more complex in termsof the switching between EtoH and EinH servoing as thespatial relationship between the robot and target changes.

IROS 2018

Short CV


- (2017 - Now) Ph.D. in Informatic - Computer Vision

   The University of Edinburgh

- (2017- 2016) MSc. Artificial Intelligence 

   The University of Edinburgh

- (2011- 2015) BSc. Mechatronics Engineering

   Universidad Catolica Boliviana "San Pablo"