Planning Efficiency

Enchance planners efficiency.

Efficient computation of robot motion trajectories is crucial for deploying robots in time-constrained applications. Simple tasks like picking an object from a deep shelf remain challenging due to narrow navigation areas, often requiring minutes of computation. Leveraging past experiences can significantly reduce planning time, but effectively combining planning and learning is complex. ELPIS lab conducts research in this area aiming to advance the efficiency of motion planners in realistic scenarios. Additionally, the Lab is also interested in creating community accepted datasets to help evaluated objectively the progress in the field.

Relevant Publications

  1. Expansion-GRR: Efficient Generation of Smooth Global Redundancy Resolution Roadmaps
    Z. Zhong, Z. Li, and C Chamzas
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024
  2. AR
    Sampling-Based Motion Planning: A Comparative Review
    A. Orthey, C. Chamzas, and L. Kavraki
    Annual Review of Control, Robotics, and Autonomous Systems, 2024
  3. RAL
    Adaptive Experience Sampling for Motion Planning using the Generator-Critic Framework
    Y. Lee, C. Chamzas, and L. E. Kavraki
    IEEE Robotics and Automation Letters, 2022
  4. Learning to Retrieve Relevant Experiences for Motion Planning
    C. Chamzas, A. Cullen, A. Shrivastava, and L. E. Kavraki
    In IEEE International Conference on Robotics and Automation, 2022
  5. RAL
    MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets
    C. Chamzas, C. Quintero-Peña, Z. Kingston, A. Orthey, D. Rakita, M. Gleicher, M. Toussaint, and L. E. Kavraki
    IEEE Robotics and Automation Letters, 2022
  6. Using Experience to Improve Constrained Planning on Foliations for Multi-Modal Problems
    Z. Kingston, C. Chamzas, and L. E. Kavraki
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021
  7. HyperPlan: A Framework for Motion Planning Algorithm Selection and Parameter Optimization
    M. Moll, C. Chamzas, Z. Kingston, and L. E. Kavraki
    In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021
  8. Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions
    C. Chamzas, Z. Kingston, C. Quintero-Peña, A. Shrivastava, and L. E. Kavraki
    In IEEE International Conference on Robotics and Automation, 2021
    (Top-4 finalist for best paper in Cognitive Robotics)
  9. RAL
    Path Planning for Manipulation Using Experience-Driven Random Trees
    È. Pairet, C. Chamzas, Y. Petillot, and L. E. Kavraki
    IEEE Robotics and Automation Letters, 2021
  10. Using Local Experiences for Global Motion Planning
    C. Chamzas, A. Shrivastava, and L. E. Kavraki
    In IEEE International Conference on Robotics and Automation, 2019