Paper Image

Using language models to guide robotic grasping

Published on:

30 August 2023

Primary Category:


Paper Authors:

Tianyu Wang,

Yifan Li,

Haitao Lin,

Xiangyang Xue,

Yanwei Fu


Key Details

Proposes a system integrating language models with robotic grasping

Uses conversational model to summarize user preferences

Performs visual grounding on instructions for grasp pose estimation

Deploys system on physical robot and validates in real-world tests

AI generated summary

Using language models to guide robotic grasping

This paper explores integrating large language models with existing robotic systems to allow more natural human-robot interaction for grasping tasks. The approach has a conversational model summarize user preferences, then uses visual grounding to identify objects from instructions and estimate pose/size for robotic grasping.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up