PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning

@article{Sartoretti2019PRIMALPV,
  title={PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning},
  author={Guillaume Sartoretti and Justin Kerr and Yunfei Shi and Glenn Wagner and T. K. Satish Kumar and Sven Koenig and Howie Choset},
  journal={IEEE Robotics and Automation Letters},
  year={2019},
  volume={4},
  pages={2378-2385}
}
  • Guillaume Sartoretti, Justin Kerr, +4 authors Howie Choset
  • Published 2019
  • Computer Science, Engineering
  • IEEE Robotics and Automation Letters
  • Multi-agent path finding (MAPF) is an essential component of many large-scale, real-world robot deployments, from aerial swarms to warehouse automation. However, despite the community's continued efforts, most state-of-the-art MAPF planners still rely on centralized planning and scale poorly past a few hundred agents. Such planning approaches are maladapted to real-world deployments, where noise and uncertainty often require paths be recomputed online, which is impossible when planning times… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 19 CITATIONS

    Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Graph Neural Networks for Decentralized Path Planning

    VIEW 1 EXCERPT
    CITES METHODS

    Multi Agent Reinforcement Learning

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Clone Swarms: Learning to Predict and Control Multi-Robot Systems by Imitation

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES

    Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning

    VIEW 3 EXCERPTS

    Overcoming Exploration in Reinforcement Learning with Demonstrations

    VIEW 2 EXCERPTS

    ODrM* optimal multirobot path planning in low dimensional search spaces

    VIEW 1 EXCERPT

    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

    VIEW 3 EXCERPTS