Aleksandr I. Panov

Principal researcher at AIRI and FRC CSC RAS
Head of the Center for Cognitive Modeling at MIPT

photo-042024.png

Moscow, Russia

Currently, I lead a group for neuro-symbolic integration at the Artificial Intelligence Institute (AIRI), engage in embodied artificial intelligence at the Cognitive Modeling Center of the Moscow Institute of Physics and Technology (MIPT), and work on deep reinforcement learning at the Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences (FRC CSC RAS). My current scientific interests are related to transformer models and structured world models in reinforcement learning, applying language models for behavior planning (including robotics platforms), multi-agent planning and learning, and indoor visual navigation.

At AIRI, my primary focus is on fundamental research for creating new neurosymbolic architectures for planning and learning. At MIPT, I lead applied activities and oversee commissioned research in robotics and control systems. Since 2019, I have been leading applied research in developing computer vision and planning systems for mobile robotics and unmanned vehicles commissioned by companies such as NKB VS, Integrant, Huawei, Sber. Additionally, at MIPT, I am the head of the master’s program in artificial intelligence, which is one of the most sought-after non-industrial programs in the Phystech School of Applied Mathematics and Computer Science (FPMI). At FRC CSC RAS, I lead the department of Dynamic Intelligent Systems and Cognitive Research and develop various approaches in the field of reinforcement learning.

Brief Biography: In 2005, I graduated from the physics and mathematics school at Novosibirsk State University (NSU), and later pursued a bachelor’s degree in the Faculty of Physics at the same university, specializing in physical-technical informatics. I completed my master’s degree in applied mathematics and physics at MIPT, Department of Intelligent Systems (basic department of the Computing Center of RAS). I conducted my doctoral dissertation at the Institute for System Analysis of RAS under the guidance of G.S. Osipov (topic Research of methods, development of models, and algorithms for forming elements of the sign representation of the subject’s world model). Since 2019, I have been leading the scientific and educational Center for Cognitive Modeling at MIPT and the master’s program Methods and Technologies of Artificial Intelligence at FPMI.

Honors and Awards: In 2017, I became a laureate of the Russian Academy of Sciences Medal for Young Scientists. In 2019, I led the CDS team, which took first place in the NeurIPS MineRL competition. In 2023, I led the SkillFusion team, which secured first place in the CVPR Habitat competition. I have also led completed grants from the Russian Foundation for Basic Research (RFBR) and the Russian Science Foundation (RSF). Winner of the Yandex ML Prize 2024 in the Scientific Supervisors category.

Academic Service: Since 2019, I have been an editor of the journal Cognitive Systems Research (Elsevier). From 2015 to 2022, I was a member of the Scientific Council of the Russian Association for Artificial Intelligence (RAAI). Since 2017, I have been organizing annual summer schools for RAAI and AIRI. In 2021 and 2022, I organized the NeurIPS IGLU competition. Science 2022, I am a reviewer for AAAI 2023, 2024, 2025, ECAI 2023, 2024, IROS 2023, 2024, ICRA 2024, CVPR 2024, 2025, IJCAI 2024, NeurIPS 2024, ICLR 2025, ICAPS 2025, AISTATS 2025 conferences and in ACL Rolling Review cycles.

news

selected publications

2024

  1. RAL
    FFStreams: Fast Search with Streams for Autonomous Maneuver Planning
    Mais Jamal, and Aleksandr Panov
    IEEE Robotics and Automation Letters, 2024
  2. ICRA
    Neural Potential Field for Obstacle-Aware Local Motion Planning
    Muhammad Alhaddad, Konstantin Mironov, Aleksey Staroverov, and 1 more author
    In 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024
  3. AAAI
    Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding
    Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, and 1 more author
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2024
  4. AAAI
    Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning
    Alexey Skrynnik, Anton Andreychuk, Maria Nesterova, and 2 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2024
  5. ICLR
    Object-Centric Learning with Slot Mixture Module
    Daniil Kirilenko, Vitaliy Vorobyov, Alexey Kovalev, and 1 more author
    In The Twelfth International Conference on Learning Representations, 2024
  6. ICLR
    Gradual Optimization Learning for Conformational Energy Minimization
    Artem Tsypin, Leonid Ugadiarov, Kuzma Khrabrov, and 7 more authors
    In The Twelfth International Conference on Learning Representations, 2024
  7. EAAI
    Hierarchical waste detection with weakly supervised segmentation in images from recycling plants
    Dmitry Yudin, Nikita Zakharenko, Artem Smetanin, and 7 more authors
    Engineering Applications of Artificial Intelligence, 2024
  8. Interactive Semantic Map Representation for Skill-Based Visual Object Navigation
    Tatiana Zemskova, Aleksei Staroverov, Kirill Muravyev, and 2 more authors
    IEEE Access, 2024

2023

  1. Fine-tuning Multimodal Transformer Models for Generating Actions in Virtual and Real Environments
    Aleksei Staroverov, Andrey S Gorodetsky, Andrei S Krishtopik, and 3 more authors
    IEEE Access, 2023
  2. AAAI
    TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
    Daniil Kirilenko, Anton Andreychuk, Aleksandr Panov, and 1 more author
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2023
  3. TNNLS
    When to Switch: Planning and Learning For Partially Observable Multi-Agent Pathfinding
    Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, and 1 more author
    IEEE Transactions on Neural Networks and Learning Systems, 2023
  4. RAL
    Policy Optimization to Learn Adaptive Motion Primitives in Path Planning With Dynamic Obstacles
    Brian Angulo, Aleksandr Panov, and Konstantin Yakovlev
    IEEE Robotics and Automation Letters, 2023
  5. Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation
    Aleksei Staroverov, Kirill Muravyev, Konstantin Yakovlev, and 1 more author
    Robotics, 2023

2022

  1. CSR
    Vector Semiotic Model for Visual Question Answering
    Alexey K. Kovalev, Makhmud Shaban, Evgeny Osipov, and 1 more author
    Cognitive Systems Research, 2022
  2. BrainInf
    Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments
    Evgenii Dzhivelikian, Artem Latyshev, Petr Kuderov, and 1 more author
    Brain Informatics, 2022
  3. Hierarchical Landmark Policy Optimization for Visual Indoor Navigation
    Aleksei Staroverov, and Aleksandr Panov
    IEEE Access, 2022

2021

  1. KBS
    Forgetful experience replay in hierarchical reinforcement learning from expert demonstrations
    Alexey Skrynnik, Aleksey Staroverov, Ermek Aitygulov, and 3 more authors
    Knowledge-Based Systems, 2021
  2. CSR
    Hierarchical Deep Q-Network from imperfect demonstrations in Minecraft
    Alexey Skrynnik, Aleksey Staroverov, Ermek Aitygulov, and 3 more authors
    Cognitive Systems Research, 2021
  3. Hybrid Policy Learning for Multi-Agent Pathfinding
    Alexey Skrynnik, Alexandra Yakovleva, Vasilii Davydov, and 2 more authors
    IEEE Access, 2021

2020

  1. Real-Time Object Navigation with Deep Neural Networks and Hierarchical Reinforcement Learning
    Aleksey Staroverov, Dmitry A. Yudin, Ilya Belkin, and 3 more authors
    IEEE Access, 2020

2016

  1. CSR
    Multilayer cognitive architecture for UAV control
    Stanislav Emel’yanov, Dmitry Makarov, Aleksandr I. Panov, and 1 more author
    Cognitive Systems Research, 2016