Saved in:
Bibliographic Details
Main Authors: Ekpo, Daniel, Levy, Mara, Suri, Saksham, Huynh, Chuong, Swaminathan, Archana, Shrivastava, Abhinav
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.10446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911599375155200
author Ekpo, Daniel
Levy, Mara
Suri, Saksham
Huynh, Chuong
Swaminathan, Archana
Shrivastava, Abhinav
author_facet Ekpo, Daniel
Levy, Mara
Suri, Saksham
Huynh, Chuong
Swaminathan, Archana
Shrivastava, Abhinav
contents Recent progress in vision-language models (VLMs) has opened new possibilities for robot task planning, but these models often produce incorrect action sequences. To address these limitations, we propose VeriGraph, a novel framework that integrates VLMs for robotic planning while verifying action feasibility. VeriGraph uses scene graphs as an intermediate representation to capture key objects and spatial relationships, enabling more reliable plan verification and refinement. The system generates a scene graph from input images and uses it to iteratively check and correct action sequences generated by an LLM-based task planner, ensuring constraints are respected and actions are executable. Our approach significantly enhances task completion rates across diverse manipulation scenarios, outperforming baseline methods by 58% on language-based tasks, 56% on tangram puzzle tasks, and 30% on image-based tasks. Qualitative results and code can be found at https://verigraph-agent.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10446
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VeriGraph: Scene Graphs for Execution Verifiable Robot Planning
Ekpo, Daniel
Levy, Mara
Suri, Saksham
Huynh, Chuong
Swaminathan, Archana
Shrivastava, Abhinav
Robotics
Artificial Intelligence
Recent progress in vision-language models (VLMs) has opened new possibilities for robot task planning, but these models often produce incorrect action sequences. To address these limitations, we propose VeriGraph, a novel framework that integrates VLMs for robotic planning while verifying action feasibility. VeriGraph uses scene graphs as an intermediate representation to capture key objects and spatial relationships, enabling more reliable plan verification and refinement. The system generates a scene graph from input images and uses it to iteratively check and correct action sequences generated by an LLM-based task planner, ensuring constraints are respected and actions are executable. Our approach significantly enhances task completion rates across diverse manipulation scenarios, outperforming baseline methods by 58% on language-based tasks, 56% on tangram puzzle tasks, and 30% on image-based tasks. Qualitative results and code can be found at https://verigraph-agent.github.io.
title VeriGraph: Scene Graphs for Execution Verifiable Robot Planning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2411.10446