TalkWithMachines

Enhancing Human-Robot Interaction Through Large/Vision Language Models

Ammar N. Abbas, Csaba Beleznai
Technological University Dublin, AIT Austrian Institute of Technology
ammar.abbas@tudublin.ie, csaba.beleznai@ait.ac.at

Paper

Paper

Code

Code

Demo

Demo

Obstacle Avoidance Stacking Sorting

Project Overview

This project investigates how Large Language Models (LLMs) and Vision Language Models (VLMs) can enhance robotic control, perception, and situational awareness in human-robot interaction.

Methodology

Framework Overview:

Framework Diagram

Experiment Results

Baseline Control

Goal: Test low-level grasping and obstacle avoidance.

Result: High success rate with low error in task execution.

Supplementary Materials

Appendix