Skip to content
@CognitiveAISystems

CognitiveAISystems

Popular repositories Loading

  1. 3DGraphLLM 3DGraphLLM Public

    3DGraphLLM is a model that uses a 3D scene graph and an LLM to perform 3D vision-language tasks.

    Python 55 6

  2. MAPF-GPT MAPF-GPT Public

    [AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on trajectories produced by LaCAM, it generates actions under p…

    Python 52 7

  3. pogema pogema Public

    POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored…

    Python 31 9

  4. Dynamic-Neural-Potential-Field Dynamic-Neural-Potential-Field Public

    Approach where the repulsive potential in an MPC pipeline is estimated by a neural model.

    Python 14

  5. MIKASA-Robo MIKASA-Robo Public

    Benchmark for robotic tabletop manipulation memory-intensive tasks

    Jupyter Notebook 11 1

  6. RATE RATE Public

    Official implementation of Recurrent Action Transformer with Memory, an offline RL agent with memory mechanisms. https://sites.google.com/view/rate-model/

    Shell 8 2

Repositories

Showing 10 of 11 repositories
  • MIKASA-Robo Public

    Benchmark for robotic tabletop manipulation memory-intensive tasks

    CognitiveAISystems/MIKASA-Robo’s past year of commit activity
    Jupyter Notebook 11 MIT 1 0 0 Updated Apr 10, 2025
  • RATE Public

    Official implementation of Recurrent Action Transformer with Memory, an offline RL agent with memory mechanisms. https://sites.google.com/view/rate-model/

    CognitiveAISystems/RATE’s past year of commit activity
    Shell 8 MIT 2 0 0 Updated Apr 9, 2025
  • pogema-toolbox Public

    The POGEMA Toolbox is a comprehensive framework designed to facilitate the testing of learning-based approaches within the POGEMA environment. This toolbox offers a unified interface that enables the seamless execution of any learnable MAPF algorithm in POGEMA.

    CognitiveAISystems/pogema-toolbox’s past year of commit activity
    Python 4 Apache-2.0 0 0 0 Updated Mar 30, 2025
  • pogema Public

    POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF settings.

    CognitiveAISystems/pogema’s past year of commit activity
    Python 31 MIT 9 1 0 Updated Mar 15, 2025
  • pogema-benchmark Public

    This is an umbrella repository that contains links and information about all the tools and algorithms related to the POGEMA Benchmark.

    CognitiveAISystems/pogema-benchmark’s past year of commit activity
    Python 2 Apache-2.0 1 1 0 Updated Mar 11, 2025
  • MIKASA-Base Public

    Unified Benchmark for Memory-Intensive Tasks

    CognitiveAISystems/MIKASA-Base’s past year of commit activity
    Python 3 MIT 0 0 0 Updated Feb 24, 2025
  • Dynamic-Neural-Potential-Field Public

    Approach where the repulsive potential in an MPC pipeline is estimated by a neural model.

    CognitiveAISystems/Dynamic-Neural-Potential-Field’s past year of commit activity
    Python 14 Apache-2.0 0 0 0 Updated Feb 7, 2025
  • 3DGraphLLM Public

    3DGraphLLM is a model that uses a 3D scene graph and an LLM to perform 3D vision-language tasks.

    CognitiveAISystems/3DGraphLLM’s past year of commit activity
    Python 55 MIT 6 1 1 Updated Jan 7, 2025
  • MAPF-GPT Public

    [AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on trajectories produced by LaCAM, it generates actions under partial observability without heuristics or agent communication. MAPF-GPT excels on unseen instances and outperforms learnable state-of-the-art solvers

    CognitiveAISystems/MAPF-GPT’s past year of commit activity
    Python 52 MIT 7 0 0 Updated Dec 26, 2024
  • learn-to-follow Public

    [AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a combination of a planning algorithm for constructing a long-term plan and reinforcement learning for resolving local conflicts.

    CognitiveAISystems/learn-to-follow’s past year of commit activity
    C++ 7 MIT 0 0 0 Updated Nov 25, 2024
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…