Kamal Acharya

Postdoctoral Research Associate at Baylor University

Back to Publications

Conference Paper

Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Survey

By Kamal Acharya Iman Sharifi Mehul Lad Liang Sun Houbing Herbert Song

An IJCAI 2025 Survey Track paper on how neurosymbolic AI can support reliable, transparent, and regulation-aware Advanced Air Mobility systems.

2025 IJCAI 2025 DOI: 10.24963/ijcai.2025/1151

Neurosymbolic AI Advanced Air Mobility Survey

DOI Publisher Page Cite

Abstract

Neurosymbolic AI combines neural network adaptability with symbolic reasoning, promising an approach to address the complex regulatory, operational, and safety challenges in Advanced Air Mobility (AAM). This survey reviews its applications across key AAM domains such as demand forecasting, aircraft design, and real-time air traffic management. Our analysis reveals a fragmented research landscape where methodologies, including Neurosymbolic Reinforcement Learning, have shown potential for dynamic optimization but still face hurdles in scalability, robustness, and compliance with aviation standards. We classify current advancements, present relevant case studies, and outline future research directions aimed at integrating these approaches into reliable, transparent AAM systems. By linking advanced AI techniques with AAM’s operational demands, this work provides a concise roadmap for researchers and practitioners developing next-generation air mobility solutions.

In brief

What This Work Does

The paper explains how AI systems that combine data learning with rule-based reasoning could help make future air mobility safer, more transparent, easier to certify, and better aligned with aviation regulations.

Research impact

Why It Matters

AAM depends on autonomous and AI-assisted decisions in safety-critical, regulated environments. This survey frames neurosymbolic AI as a practical path toward systems that can learn from complex data while still exposing rule-grounded, auditable, and certifiable reasoning.

Paper at a glance

Research Scope

4Research stages
6Methods or application areas
8Future research directions

Neurosymbolic AI and AAM Survey Framework

1

Background

Introduces neurosymbolic AI as a hybrid of neural learning and symbolic reasoning, and positions AAM as a safety-critical transportation transformation.

2

Application Mapping

Maps neurosymbolic AI to AAM domains such as electrification, aircraft design, training, maintenance, safety, autonomy, cybersecurity, and demand modeling.

3

Case Studies

Uses FAA and EASA AI roadmaps to examine aviation AI safety assurance, certification, human oversight, and regulatory alignment.

4

Risks and Directions

Organizes future work around technological, ethical, regulatory, governance, scalability, and lifecycle challenges.

Key Contributions

  • Provides a comprehensive survey of neurosymbolic AI integration across Advanced Air Mobility domains.
  • Classifies application areas including electrification, aircraft design, training and simulation, predictive maintenance, safety, autonomy, cybersecurity, and demand modeling.
  • Discusses FAA and EASA AI roadmaps as aviation safety assurance case studies.
  • Identifies technological, ethical, regulatory, governance, and lifecycle challenges for deploying neurosymbolic AI in AAM.
  • Outlines future research directions for reliable, transparent, and certifiable AAM AI systems.

AAM Application Areas

Electrification

Uses neurosymbolic methods for energy management, battery lifecycle optimization, smart-grid integration, and fault detection in electric AAM systems.

Aircraft Design

Connects learned design exploration with symbolic constraints around certification, vehicle performance, payload, flight range, noise, and urban integration.

Training and Simulation

Supports adaptive simulation, digital twins, natural-language interaction, failure reasoning, route planning, and multi-agent scenario analysis.

Safety and Autonomy

Uses symbolic shields, logic constraints, and rule-guided learning to keep autonomous AAM decisions aligned with safety protocols and air traffic rules.

Cybersecurity

Combines anomaly detection with security policies, knowledge graphs, and cross-validation of navigation inputs to address cyber-physical threats.

Demand Modeling

Combines neural pattern recognition with structured regulatory and operational reasoning for interpretable AAM demand forecasting.

Research Gaps

  1. Scalability
  2. Robustness
  3. Certification
  4. Data interoperability
  5. Cybersecurity
  6. Accountability
  7. Public trust
  8. Data governance

Publication Details

Type
Conference Paper
Venue
IJCAI 2025
Year
2025
Pages
10362-10370

Research Topics

Neurosymbolic AI Advanced Air Mobility Survey AI Safety Aviation Governance

Citation

@inproceedings{acharya2025integrating,
  author={Acharya, Kamal and Sharifi, Iman and Lad, Mehul and Sun, Liang and Song, Houbing},
  title={Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Survey},
  booktitle={Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence},
  year={2025},
  pages={10362--10370},
  doi={10.24963/ijcai.2025/1151}
}