Publications

Current imitation learning approaches, predominantly based on deep neural networks (DNNs), offer efficient mechanisms for learning driving policies from real-world datasets. However, they suffer from inherent limitations in interpretability and generalizability—issues of critical importance in safety-critical domains such as autonomous driving. In this paper, we introduce Symbolic Imitation Learning (SIL), a novel framework that leverages Inductive Logic Programming (ILP) to derive explainable and generalizable driving policies from synthetic datasets. We evaluate SIL on real-world HighD and NGSim datasets, comparing its performance with state-of-the-art neural imitation learning methods using metrics such as collision rate, lane change efficiency, and average speed. The results indicate that SIL significantly enhances policy transparency while maintaining strong performance across varied driving conditions. These findings highlight the potential of integrating ILP into imitation learning to promote safer and more reliable autonomous systems.

I. Sharifi, M. Yildirim, and S. Fallah. (2025). "Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies." Applied Sciences, 15(23), 12464.

@article{sharifi2025symbolic,
  title     = {Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies},
  author    = {Sharifi, Iman and Yildirim, Mustafa and Fallah, Saber},
  journal   = {Applied Sciences},
  volume    = {15},
  number    = {23},
  pages     = {12464},
  year      = {2025},
  doi       = {10.3390/app152312464}
}

The dynamic nature of driving environments and the presence of diverse road users pose significant challenges for decision-making in autonomous driving. Deep reinforcement learning (DRL) has emerged as a popular approach to tackle this problem. However, the application of existing DRL solutions is mainly confined to simulated environments because of safety concerns, impeding their deployment in real-world environments. To overcome this limitation, this paper introduces a novel neuro-symbolic model-free DRL approach, called DRL with symbolic logic (DRLSL) that combines the strengths of DRL (learning from experience) and symbolic first-order logic (knowledge-driven reasoning) to enable safe learning in real-time interactions of autonomous driving within real environments. This innovative approach provides a means to learn autonomous driving policies by actively engaging with the physical environment while ensuring safety. We have implemented the DRLSL framework in a highway driving scenario using the HighD dataset and demonstrated that our method successfully avoids unsafe actions during both the training and testing phases. Furthermore, our results indicate that DRLSL achieves faster convergence during training and exhibits better generalizability to new highway driving scenarios compared to traditional DRL methods.

I. Sharifi, M. Yildirim, and S. Fallah. (2025). "Toward Safe Autonomous Highway Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach." Transportation Research Record, 2680(1), 416–431.

@article{sharifi2025toward,
  title     = {Toward Safe Autonomous Highway Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach},
  author    = {Sharifi, Iman and Yildirim, Mustafa and Fallah, Saber},
  journal   = {Transportation Research Record},
  volume    = {2680},
  number    = {1},
  pages     = {416--431},
  year      = {2025},
  doi       = {10.1177/03611981251357006}
}

A. Talaeizadeh, I. Sharifi, A. Alasty, and S. Ghatrehsamani. (2025). "Agricultural Spraying Drones: A Comprehensive Review." Smart Agricultural Technology, 12, 101519.

@article{talaeizadeh2025agricultural,
  title     = {Agricultural Spraying Drones: A Comprehensive Review},
  author    = {Talaeizadeh, Amin and Sharifi, Iman and Alasty, Aria and Ghatrehsamani, Shirin},
  journal   = {Smart Agricultural Technology},
  volume    = {12},
  pages     = {101519},
  year      = {2025},
  doi       = {10.1016/j.atech.2025.101519}
}

Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings. Classical ILP relies on discrete combinatorial rule search and is brittle under uncertainty, while differentiable ILP methods typically depend on predefined rule templates or inaccurate fuzzy operators that suffer from vanishing gradients or poor approximation of logical structure when reasoning over probabilistic predicate valuations. This paper proposes an Attention-based Neuro-symbolic Differentiable Rule Extractor (ANDRE), a novel ILP framework that learns first-order logic programs by optimizing over a continuous rule space with attention-based logical operators. ANDRE replaces both rule templates and logical operators with fully differentiable, attention-driven conjunction and disjunction operators that approximate logical min-max semantics, enabling accurate, stable, and interpretable reasoning over probabilistic data. By softly selecting, negating, or excluding predicates within each rule, ANDRE supports flexible rule induction while preserving symbolic structure. Extensive experiments on classical ILP benchmarks, large-scale knowledge bases, and synthetic datasets with probabilistic predicates and noisy supervision demonstrate that ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability.

I. Sharifi, P. Wei, and S. Fallah. (2026). "ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming." International Conference on Neurosymbolic Learning and Reasoning (NeSy), 2026.

@inproceedings{sharifi2026andre,
  title     = {ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming},
  author    = {Sharifi, Iman and Wei, Peng and Fallah, Saber},
  booktitle = {International Conference on Neurosymbolic Learning and Reasoning (NeSy)},
  year      = {2026},
  eprint    = {2605.04193},
  archivePrefix = {arXiv},
  url       = {https://openreview.net/forum?id=Kqd1zKe3Go}
}

The growing deployment of small Unmanned Aerial Systems (sUASs) in low-altitude airspaces has increased the need for reliable tactical deconfliction under safety-critical constraints. Tactical deconfliction involves short-horizon decision-making in dense, partially observable, and heterogeneous multi-agent environments, where both cooperative separation assurance and operational efficiency must be maintained. While Large Language Models (LLMs) exhibit strong reasoning capabilities, their direct application to air traffic control remains limited by insufficient domain grounding and unpredictable output inconsistency. This paper investigates LLMs as decision-makers in cooperative multi-agent tactical deconfliction using fine-tuning strategies that align model outputs to human operator heuristics. We propose a simulation-to-language data generation pipeline based on the BlueSky air traffic simulator that produces rule-consistent deconfliction datasets reflecting established safety practices. A pretrained Qwen-Math-7B model is fine-tuned using two parameter-efficient strategies: supervised fine-tuning with Low-Rank Adaptation (LoRA) and preference-based fine-tuning combining LoRA with Group-Relative Policy Optimization (GRPO). Experimental results on validation datasets and closed-loop simulations demonstrate that supervised LoRA fine-tuning substantially improves decision accuracy, consistency, and separation performance compared to the pretrained LLM, with significant reductions in near mid-air collisions. GRPO provides additional coordination benefits but exhibits reduced robustness when interacting with heterogeneous agent policies.

I. Sharifi, A. Zongo, and P. Wei. (2026). "Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems." CVPR Workshops, 2026.

@inproceedings{sharifi2026finetuning,
  title     = {Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems},
  author    = {Sharifi, Iman and Zongo, Alex and Wei, Peng},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  year      = {2026},
  eprint    = {2603.28561},
  archivePrefix = {arXiv}
}

In the envisioned future dense urban airspace, multiple companies will operate heterogeneous fleets of small unmanned aerial systems (sUASs), where each fleet includes several homogeneous aircraft with identical policies and configurations, e.g., equipage, sensing, and communication ranges, making tactical deconfliction highly complex for the aircraft. This paper aims to address two core questions: (1) Can tactical deconfliction policies converge or reach an equilibrium to ensure a conflict-free airspace when companies operate heterogeneous fleets of homogeneous aircraft? (2) If so, will the converged policies discriminate against companies operating sUASs with weaker configurations? We investigate a multi-agent reinforcement learning paradigm in which homogeneous aircraft within heterogeneous fleets operate concurrently to perform package delivery missions over Dallas, Texas, USA. An attention-enhanced Proximal Policy Optimization-based Advantage Actor-Critic (PPOA2C) framework is employed to resolve intra- and inter-fleet conflicts, with each fleet independently training its own policy while preserving privacy. Experimental results show that two fleets with distinct, shared PPOA2C policies can reach an equilibrium to maintain safe separation. While two PPOA2C policies outperform two strong rule-based baselines in terms of conflict resolution, a PPOA2C policy exhibits safer interaction with a rule-based policy, indicating adaptive capabilities of PPOA2C policies. Furthermore, we conducted extensive policy-configuration evaluations, which reveal that equilibria between similar policy types tend to favor fleets with stronger configurations. Even under similar configurations but different policy types, the equilibrium favors one of the heterogeneous policies, underscoring the need for fairness-aware conflict management in heterogeneous sUAS operations.

I. Sharifi, H. T. Kim, M. H. Ahmed, M. Ghasemi, and P. Wei. (2026). "Separation Assurance between Heterogeneous Fleets of Small Unmanned Aerial Systems via Multi-Agent Reinforcement Learning." IEEE ITSC, 2026.

@inproceedings{sharifi2026separation,
  title     = {Separation Assurance between Heterogeneous Fleets of Small Unmanned Aerial Systems via Multi-Agent Reinforcement Learning},
  author    = {Sharifi, Iman and Kim, Hyeong Tae and Ahmed, Maheed Hatem and Ghasemi, Mahsa and Wei, Peng},
  booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)},
  year      = {2026},
  eprint    = {2605.01041},
  archivePrefix = {arXiv}
}

The rapid growth of small Unmanned Aerial Systems (sUAS) for civil and commercial missions has intensified concerns about their resilience to cyber-security threats. Operating within the emerging UAS Traffic Management (UTM) framework, these lightweight and highly networked platforms depend on secure communication, navigation, and surveillance (CNS) subsystems that are vulnerable to spoofing, jamming, hijacking, and data manipulation. While prior reviews of UAS security addressed these challenges at a conceptual level, a detailed, system-oriented analysis for resource-constrained sUAS remains lacking. This paper presents a comprehensive survey of cyber-security vulnerabilities and defenses tailored to the sUAS and UTM ecosystem. We organize existing research across the full cyber-physical stack, encompassing CNS, data links, sensing and perception, UTM cloud access, and software integrity layers, and classify attack vectors according to their technical targets and operational impacts. Correspondingly, we review defense mechanisms ranging from classical encryption and authentication to adaptive intrusion detection, lightweight cryptography, and secure firmware management. By mapping threats to mitigation strategies and evaluating their scalability and practical effectiveness, this work establishes a unified taxonomy and identifies open challenges for achieving safe, secure, and scalable sUAS operations within future UTM environments.

I. Sharifi, M. Ghazanfari, A. Taye, P. Wei, M. Ahmed, H. T. Kim, M. Ghasemi, V. Gupta, et al. (2026). "A Survey of Security Challenges and Solutions for UAS Traffic Management (UTM) and Small Unmanned Aerial Systems (sUAS)." AIAA SciTech Forum, 2026.

@inproceedings{sharifi2026survey,
  title     = {A Survey of Security Challenges and Solutions for UAS Traffic Management (UTM) and Small Unmanned Aerial Systems (sUAS)},
  author    = {Sharifi, Iman and Ghazanfari, Mahyar and Taye, Abenezer and Wei, Peng and Ahmed, Maheed and Kim, Hyeong Tae and Ghasemi, Mahsa and Gupta, Vijay and Dahle, Noah W. and Canady, Robert and Diaz-Gonzalez, Abel and Coursey, Austin and Bjorkman, Bryce and Lemieux-Mack, Cailani and Ward, Bryan and Koutsoukos, Xenofon and Biswas, Gautam and Herencia-Zapana, Heber and Hasan, Saqib and Amundson, Isaac and Fotiadis, Filippos and Topcu, Ufuk and Lu, Junchi and Chen, Alfred and Aryal, Nischal and Ibrahim, Amer and Ras, Abdul Kareem and Shirkhodaie, Amir},
  booktitle = {AIAA SciTech 2026 Forum},
  year      = {2026},
  doi       = {10.2514/6.2026-2892}
}

This survey reviews the existing and envisioned security vulnerabilities and defense mechanisms relevant to Advanced Air Mobility (AAM) systems, with a focus on electric vertical takeoff and landing (eVTOL) aircraft. Drawing from vulnerabilities in the avionics in commercial aviation and the automated unmanned aerial systems (UAS), the paper presents a taxonomy of attacks, analyzes mitigation strategies, and proposes a secure system architecture tailored to the future AAM ecosystem. The paper also highlights key threat vectors, including Global Positioning System (GPS) jamming/spoofing, ATC radio frequency misuse, attacks on TCAS and ADS-B, possible backdoor via Electronic Flight Bag (EFB), new vulnerabilities introduced by aircraft automation and connectivity, and risks from flight management system (FMS) software, database and cloud services. Finally, this paper describes emerging defense techniques against these attacks, and open technical problems to address toward better defense mechanisms.

M. Ghazanfari, I. Sharifi, P. Wei, A. Taye, B. Ward, X. Koutsoukos, G. Biswas, M. Ghasemi, V. Gupta, et al. (2026). "A Survey of Security Challenges and Solutions for Advanced Air Mobility and eVTOL Aircraft." AIAA SciTech Forum, 2026.

@inproceedings{ghazanfari2026survey,
  title     = {A Survey of Security Challenges and Solutions for Advanced Air Mobility and eVTOL Aircraft},
  author    = {Ghazanfari, Mahyar and Sharifi, Iman and Wei, Peng and Taye, Abenezer and Ward, Bryan and Koutsoukos, Xenofon and Biswas, Gautam and Ghasemi, Mahsa and Gupta, Vijay and Kim, Hyeong Tae and Ahmed, Maheed and Topcu, Ufuk and Fotiadis, Filippos and Chen, Alfred and Lu, Junchi and Amundson, Isaac and Hasan, Saqib and Shirkhodaie, Amir and Aryal, Nischal and Ibrahim, Amer and Ras, Abdul Kareem and Herencia-Zapana, Heber and Dahle, Noah W. and Diaz-Gonzalez, Abel and Coursey, Austin and Bjorkman, Bryce and Lemieux-Mack, Cailani and Canady, Robert E.},
  booktitle = {AIAA SciTech 2026 Forum},
  year      = {2026},
  doi       = {10.2514/6.2026-2891}
}

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.

K. Acharya, I. Sharifi, M. Lad, L. Sun, and H. H. Song. (2025). "Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Survey." IJCAI, 2025.

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

Proportional-Integrator-Derivative (PID) controller is used in a wide range of industrial and experimental processes. There are a couple of offline methods for tuning PID gains. However, due to the uncertainty of model parameters and external disturbances, real systems such as Quadrotors need more robust and reliable PID controllers. In this research, a self-tuning PID controller using a Reinforcement-Learning-based Neural Network for attitude and altitude control of a Quadrotor has been investigated. An Incremental PID, which contains static and dynamic gains, has been considered and only the variable gains have been tuned. To tune dynamic gains, a model-free actor-critic-based hybrid neural structure was used that was able to properly tune PID gains, and also has done the best as an identifier. In both tunning and identification tasks, a Neural Network with two hidden layers and sigmoid activation functions has been learned using Adaptive Momentum (ADAM) optimizer and Back-Propagation (BP) algorithm. This method is online, able to tackle disturbance, and fast in training. In addition to robustness to mass uncertainty and wind gust disturbance, results showed that the proposed method had a better performance when compared to a PID controller with constant gains.

I. Sharifi and A. Alasty. (2022). "Self-Tuning PID Control via a Hybrid Actor-Critic-Based Neural Structure for Quadcopter Control." ISME Conference, 2022.

@inproceedings{sharifi2022selftuning,
  title     = {Self-Tuning PID Control via a Hybrid Actor-Critic-Based Neural Structure for Quadcopter Control},
  author    = {Sharifi, Iman and Alasty, Aria},
  booktitle = {30th Annual International Conference of the Iranian Society of Mechanical Engineers (ISME)},
  year      = {2022},
  eprint    = {2307.01312},
  archivePrefix = {arXiv}
}

The problem with existing camera-based Deep Reinforcement Learning approaches is twofold: they rarely integrate high-level scene context into the feature representation, and they rely on rigid, fixed reward functions. To address these challenges, this paper proposes a novel pipeline that produces a neuro-symbolic feature representation that encompasses semantic, spatial, and shape information, as well as spatially boosted features of dynamic entities in the scene, with an emphasis on safety-critical road users. It also proposes a Soft First-Order Logic (SFOL) reward function that balances human values via a symbolic reasoning module. Here, semantic and spatial predicates are extracted from segmentation maps and applied to linguistic rules to obtain reward weights. Quantitative experiments in the CARLA simulation environment show that the proposed neuro-symbolic representation and SFOL reward function improved policy robustness and safety-related performance metrics compared to baseline representations and reward formulations across varying traffic densities and occlusion levels. The findings demonstrate that integrating holistic representations and soft reasoning into Reinforcement Learning can support more context-aware and value-aligned decision-making for autonomous driving.

V. Asodia, I. Sharifi, and S. Fallah. (2026). "Reinforcement Learning Enhancement Using Vector Semantic Representation and Symbolic Reasoning for Human-Centered Autonomous Emergency Braking." arXiv preprint arXiv:2602.05079.

@article{asodia2026reinforcement,
  title     = {Reinforcement Learning Enhancement Using Vector Semantic Representation and Symbolic Reasoning for Human-Centered Autonomous Emergency Braking},
  author    = {Asodia, Vinal and Sharifi, Iman and Fallah, Saber},
  journal   = {arXiv preprint arXiv:2602.05079},
  year      = {2026},
  eprint    = {2602.05079},
  archivePrefix = {arXiv}
}