Search Results for author: Aleksandr Panov

Found 14 papers, 8 papers with code

Neural Potential Field for Obstacle-Aware Local Motion Planning

2 code implementations25 Oct 2023 Muhammad Alhaddad, Konstantin Mironov, Aleksey Staroverov, Aleksandr Panov

Experiment on Husky UGV mobile robot showed that our approach allows real-time and safe local planning.

Motion Planning

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

no code implementations2 Oct 2023 Alexey Skrynnik, Anton Andreychuk, Maria Nesterova, Konstantin Yakovlev, Aleksandr Panov

Multi-agent Pathfinding (MAPF) problem generally asks to find a set of conflict-free paths for a set of agents confined to a graph and is typically solved in a centralized fashion.

Collision Avoidance

Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning

no code implementations27 Jul 2023 Brian Angulo, Gregory Gorbov, Aleksandr Panov, Konstantin Yakovlev

While reinforcement learning algorithms have had great success in the field of autonomous navigation, they cannot be straightforwardly applied to the real autonomous systems without considering the safety constraints.

Autonomous Navigation reinforcement-learning

Reinforcement Learning with Success Induced Task Prioritization

1 code implementation30 Dec 2022 Maria Nesterova, Alexey Skrynnik, Aleksandr Panov

Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies.

reinforcement-learning Reinforcement Learning (RL)

TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers

1 code implementation22 Dec 2022 Daniil Kirilenko, Anton Andreychuk, Aleksandr Panov, Konstantin Yakovlev

To this end, we suggest learning the instance-dependent heuristic proxies that are supposed to notably increase the efficiency of the search.

Pathfinding in stochastic environments: learning vs planning

1 code implementation PeerJ Computer Science 2022 Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, Aleksandr Panov

Within planning, an agent constantly re-plans and updates the path based on the history of the observations using a search-based planner.

Cannot find the paper you are looking for? You can Submit a new open access paper.