neusis

NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions

https://github.com/controlnet/neusis

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (11.8%) to scientific vocabulary

Keywords

airsim drone uav unreal-engine
Last synced: 6 months ago · JSON representation ·

Repository

NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions

Basic Info
Statistics
  • Stars: 2
  • Watchers: 2
  • Forks: 0
  • Open Issues: 1
  • Releases: 0
Topics
airsim drone uav unreal-engine
Created 12 months ago · Last pushed 12 months ago
Metadata Files
Readme Citation

README.md

NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions

This repo is the official repository for the paper NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions.

Abstract

This paper addresses the problem of autonomous UAV search missions, where a UAV must locate specific Entities of Interest (EOIs) within a time limit, based on brief descriptions in large, hazard-prone environments with keep-out zones. The UAV must perceive, reason, and make decisions with limited and uncertain information. We propose NEUSIS, a compositional neuro-symbolic system designed for interpretable UAV search and navigation in realistic scenarios. NEUSIS integrates neuro-symbolic visual perception, reasoning, and grounding (GRiD) to process raw sensory inputs, maintains a probabilistic world model for environment representation, and uses a hierarchical planning component (SNaC) for efficient path planning. Experimental results from simulated urban search missions using AirSim and Unreal Engine show that NEUSIS outperforms a state-of-the-art (SOTA) vision-language model and a SOTA search planning model in success rate, search efficiency, and 3D localization. These results demonstrate the effectiveness of our compositional neuro-symbolic approach in handling complex, real-world scenarios, making it a promising solution for autonomous UAV systems in search missions.

Video Demo

https://github.com/user-attachments/assets/8f1b0b7c-ab10-42a3-b63f-1acf975ca5fd

References

If you find this work useful for your research, please consider citing it.

bibtex @article{cai2024neusis, title={NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions}, author={Cai, Zhixi and Cardenas, Cristian Rojas and Leo, Kevin and Zhang, Chenyuan and Backman, Kal and Li, Hanbing and Li, Boying and Ghorbanali, Mahsa and Datta, Stavya and Qu, Lizhen and Santiago, Julian Gutierrez and Ignatiev, Alexey and Li, Yuan-Fang and Vered, Mor and Stuckey, Peter J. and Garcia de la Banda, Maria and Rezatofighi, Hamid}, journal={arXiv preprint arXiv:2409.10196}, year={2024} }

Owner

  • Name: ControlNet
  • Login: ControlNet
  • Kind: user

Study on: Computer Vision | Artificial Intelligence

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you find this work useful for your research, please consider citing it."
preferred-citation:
  type: article
  authors:
  - family-names: "Cai"
    given-names: "Zhixi"
  - family-names: "Cardenas"
    given-names: "Cristian Rojas"
  - family-names: "Leo"
    given-names: "Kevin"
  - family-names: "Zhang"
    given-names: "Chenyuan"
  - family-names: "Backman"
    given-names: "Kal"
  - family-names: "Li"
    given-names: "Hanbing"
  - family-names: "Li"
    given-names: "Boying"
  - family-names: "Ghorbanali"
    given-names: "Mahsa"
  - family-names: "Datta"
    given-names: "Stavya"
  - family-names: "Qu"
    given-names: "Lizhen"
  - family-names: "Santiago"
    given-names: "Julian Gutierrez"
  - family-names: "Ignatiev"
    given-names: "Alexey"
  - family-names: "Li"
    given-names: "Yuan-Fang"
  - family-names: "Vered"
    given-names: "Mor"
  - family-names: "Stuckey"
    given-names: "Peter J."
  - family-names: "Garcia de la Banda"
    given-names: "Maria"
  - family-names: "Rezatofighi"
    given-names: "Hamid"
  journal: "arXiv preprint arXiv:2409.10196"
  title: "NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions"
  year: 2024

GitHub Events

Total
  • Issues event: 1
  • Watch event: 4
  • Member event: 4
  • Push event: 4
  • Create event: 2
Last Year
  • Issues event: 1
  • Watch event: 4
  • Member event: 4
  • Push event: 4
  • Create event: 2