- Aleksandr
PanovHead of laboratory
PhD, Associate Professor
Email: panov.ai@mipt.ru
Homepage - https://grafft.github.io/Scientific interests:
Reinforcement learning
Semiotics
Cognitive robotics
Multi-agent systems
Behavior planning
Recent publications
1. Staroverov A. et al. Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation // Robotics. 2023. Vol. 12.
2. Skrynnik A. et al. When to Switch: Planning and Learning For Partially Observable Multi-Agent Pathfinding // TNNLS. 2023.
3. Sarkisyan C., Kovalev A.K., Panov A.I. Evaluation of Pretrained Large Language Models in Embodied Planning Tasks // Artificial General Intelligence. AGI 2023. Lecture Notes in Computer Science. Springer Cham, 2023. Vol. 13921. P. 222–232.
4. Pitanov Y. et al. Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results // Hybrid Artificial Intelligent Systems. HAIS 2023. Lecture Notes in Computer Science. Springer Cham, 2023. Vol. 14001. P. 649–660.
5. Kirilenko D. et al. Quantized Disentangled Representations for Object-Centric Visual Tasks // PReMI Proceedings. 2023.
6. Angulo B., Panov A., Yakovlev K. Policy Optimization to Learn Adaptive Motion Primitives in Path Planning With Dynamic Obstacles // IEEE Robotics and Automation Letters. 2023. Vol. 8, № 2. P. 824–831.
7. Yakovlev K.S. et al. Planning and Learning in Multi-Agent Path Finding // Doklady Mathematics. 2022. Vol. 106, № S1. P. S79–S84.
8. Staroverov A., Panov A. Hierarchical Landmark Policy Optimization for Visual Indoor Navigation // IEEE Access. 2022. Vol. 10. P. 70447–70455.
9. Skrynnik A. et al. Pathfinding in stochastic environments: learning vs planning // PeerJ Computer Science. 2022. Vol. 8. P. e1056.
10. Panov A.I. Simultaneous Learning and Planning in a Hierarchical Control System for a Cognitive Agent // Automation and Remote Control. 2022. Vol. 83, № 6. P. 869–883.
11. Kovalev A.K. et al. Vector Semiotic Model for Visual Question Answering // Cognitive Systems Research. 2022. Vol. 71. P. 52–63.
12. Kovalev A.K., Panov A.I. Application of Pretrained Large Language Models in Embodied Artificial Intelligence // Doklady Mathematics. 2022. Vol. 106, № S1. P. S85–S90.
13. Dzhivelikian E. et al. Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments // Brain Informatics. 2022. Vol. 9, № 1. P. 8.
1. Staroverov A. et al. Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation // Robotics. 2023. Vol. 12.
2. Skrynnik A. et al. When to Switch: Planning and Learning For Partially Observable Multi-Agent Pathfinding // TNNLS. 2023.
3. Sarkisyan C., Kovalev A.K., Panov A.I. Evaluation of Pretrained Large Language Models in Embodied Planning Tasks // Artificial General Intelligence. AGI 2023. Lecture Notes in Computer Science. Springer Cham, 2023. Vol. 13921. P. 222–232.
4. Pitanov Y. et al. Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results // Hybrid Artificial Intelligent Systems. HAIS 2023. Lecture Notes in Computer Science. Springer Cham, 2023. Vol. 14001. P. 649–660.
5. Kirilenko D. et al. Quantized Disentangled Representations for Object-Centric Visual Tasks // PReMI Proceedings. 2023.
6. Angulo B., Panov A., Yakovlev K. Policy Optimization to Learn Adaptive Motion Primitives in Path Planning With Dynamic Obstacles // IEEE Robotics and Automation Letters. 2023. Vol. 8, № 2. P. 824–831.
7. Yakovlev K.S. et al. Planning and Learning in Multi-Agent Path Finding // Doklady Mathematics. 2022. Vol. 106, № S1. P. S79–S84.
8. Staroverov A., Panov A. Hierarchical Landmark Policy Optimization for Visual Indoor Navigation // IEEE Access. 2022. Vol. 10. P. 70447–70455.
9. Skrynnik A. et al. Pathfinding in stochastic environments: learning vs planning // PeerJ Computer Science. 2022. Vol. 8. P. e1056.
10. Panov A.I. Simultaneous Learning and Planning in a Hierarchical Control System for a Cognitive Agent // Automation and Remote Control. 2022. Vol. 83, № 6. P. 869–883.
11. Kovalev A.K. et al. Vector Semiotic Model for Visual Question Answering // Cognitive Systems Research. 2022. Vol. 71. P. 52–63.
12. Kovalev A.K., Panov A.I. Application of Pretrained Large Language Models in Embodied Artificial Intelligence // Doklady Mathematics. 2022. Vol. 106, № S1. P. S85–S90.
13. Dzhivelikian E. et al. Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments // Brain Informatics. 2022. Vol. 9, № 1. P. 8.
2011–2015 PhD in Computer Science in the direction "05.13.17 - Theoretical Foundations of Informatics", Institute for Systems Analysis of the Russian Academy of Sciences, Moscow. Thesis topic "Research of methods, development of models and algorithms for the formation of elements of the symbolic world model of the subject of activity", scientific. head - G.S. Osipov
2009–2011 Master of Applied Mathematics and Physics in Applied Mathematics and Physics, Moscow Institute of Physics and Technology, Moscow. Thesis topic "Research and modeling of the behavior of a collective of intelligent agents with different functionality", scientific. head - G.S. Osipov
2005-2009 Bachelor of Physics in Physics, Novosibirsk State University, Novosibirsk.
2009–2011 Master of Applied Mathematics and Physics in Applied Mathematics and Physics, Moscow Institute of Physics and Technology, Moscow. Thesis topic "Research and modeling of the behavior of a collective of intelligent agents with different functionality", scientific. head - G.S. Osipov
2005-2009 Bachelor of Physics in Physics, Novosibirsk State University, Novosibirsk.
- 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 the first place in the CVPR Habitat competition.
- I have also led successfully completed grants from the Russian Foundation for Basic Research (RFBR) and the Russian Science Foundation (RSF).
2015 – 2019 Research Fellow, Higher School of Economics, Laboratory of Process-Oriented Information Systems, Moscow.
Computer cognitive modeling: a study of teaching methods in the task of planning behavior based on a sign world picture.
2010 – present Senior Researcher, Federal Research Center "Informatics and Control" of the Russian Academy of Sciences, Laboratory "Dynamic Intelligent Systems".
Computer cognitive modeling: research and modeling of the processes of perception, planning of behavior, goal-setting and other higher cognitive functions of a person.
Machine learning: development of algorithms for logical and hybrid methods of data analysis, development of biologically plausible algorithms for machine learning.
Multi-agent systems and management systems: study of the distribution of roles in a team of agents, development of multi-level architectures for managing teams of complex technical objects.
Computer cognitive modeling: a study of teaching methods in the task of planning behavior based on a sign world picture.
2010 – present Senior Researcher, Federal Research Center "Informatics and Control" of the Russian Academy of Sciences, Laboratory "Dynamic Intelligent Systems".
Computer cognitive modeling: research and modeling of the processes of perception, planning of behavior, goal-setting and other higher cognitive functions of a person.
Machine learning: development of algorithms for logical and hybrid methods of data analysis, development of biologically plausible algorithms for machine learning.
Multi-agent systems and management systems: study of the distribution of roles in a team of agents, development of multi-level architectures for managing teams of complex technical objects.