Alert button
Picture for Aleksandr Panov

Aleksandr Panov

Alert button

Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding

Dec 26, 2023
Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, Aleksandr Panov

Viaarxiv icon

Interactive Semantic Map Representation for Skill-based Visual Object Navigation

Nov 07, 2023
Tatiana Zemskova, Aleksei Staroverov, Kirill Muravyev, Dmitry Yudin, Aleksandr Panov

Viaarxiv icon

Neural Potential Field for Obstacle-Aware Local Motion Planning

Oct 25, 2023
Muhammad Alhaddad, Konstantin Mironov, Aleksey Staroverov, Aleksandr Panov

Figure 1 for Neural Potential Field for Obstacle-Aware Local Motion Planning
Figure 2 for Neural Potential Field for Obstacle-Aware Local Motion Planning
Figure 3 for Neural Potential Field for Obstacle-Aware Local Motion Planning
Figure 4 for Neural Potential Field for Obstacle-Aware Local Motion Planning
Viaarxiv icon

SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment

Oct 18, 2023
Tatiana Zemskova, Margarita Kichik, Dmitry Yudin, Aleksei Staroverov, Aleksandr Panov

Viaarxiv icon

Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learning

Oct 02, 2023
Alexey Skrynnik, Anton Andreychuk, Maria Nesterova, Konstantin Yakovlev, Aleksandr Panov

Viaarxiv icon

Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning

Jul 27, 2023
Brian Angulo, Gregory Gorbov, Aleksandr Panov, Konstantin Yakovlev

Figure 1 for Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning
Figure 2 for Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning
Viaarxiv icon

Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results

Jul 25, 2023
Yelisey Pitanov, Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, Aleksandr Panov

Figure 1 for Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results
Figure 2 for Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results
Figure 3 for Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results
Figure 4 for Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results
Viaarxiv icon

Reinforcement Learning with Success Induced Task Prioritization

Dec 30, 2022
Maria Nesterova, Alexey Skrynnik, Aleksandr Panov

Viaarxiv icon

Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles

Dec 29, 2022
Brian Angulo, Aleksandr Panov, Konstantin Yakovlev

Figure 1 for Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles
Figure 2 for Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles
Figure 3 for Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles
Figure 4 for Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles
Viaarxiv icon

TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers

Dec 22, 2022
Daniil Kirilenko, Anton Andreychuk, Aleksandr Panov, Konstantin Yakovlev

Figure 1 for TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
Figure 2 for TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
Figure 3 for TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
Figure 4 for TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
Viaarxiv icon