This paper describes how the performance of motion primitive-based planning algorithms can be improved using reinforcement learning. Specifically, we describe and evaluate a framework that autonomously improves the performance of a primitive-based motion planner. The improvement process consists of three phases: exploration, extraction, and reward updates. This process can be iterated continuously to provide successive improvement. The exploration step generates new trajectories, and the extraction step identifies new primitives from these trajectories. These primitives are then used to update rewards for continued exploration. This framework required novel shaping rewards, development of a primitive extraction algorithm, and modification of the Hybrid A* algorithm. The framework is tested on a navigation task using a nonlinear F-16 model. The framework autonomously added 91 motion primitives to the primitive library and reduced average path cost by 21.6 s, or 35.75% of the original cost. The learned primitives are applied to an obstacle field navigation task, which was not used in training, and reduced path cost by 16.3 s, or 24.1%. Additionally, two heuristics for the modified Hybrid A* algorithm are designed to improve effective branching factor.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Utilizing Reinforcement Learning to Continuously Improve a Primitive-Based Motion Planner


    Contributors:

    Published in:

    Publication date :

    2022-03-07


    Size :

    12 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Utilizing Reinforcement Learning to Continuously Improve a Primitive-Based Motion Planner

    Goddard, Zachary C. / Wardlaw, Kenneth / Krishnan, Rohith et al. | AIAA | 2021


    UTILIZING REINFORCEMENT LEARNING TO CONTINUOUSLY IMPROVE A PRIMITIVE-BASED MOTION PLANNER

    Goddard, Zachary C. / Wardlaw, Kenneth / Krishnan, Rohith et al. | TIBKAT | 2021



    Motion-Primitive based Deep Reinforcement Learning for High Speed Aerospace Vehicle Missions

    Levin, Winston C. / Nolan, Sean M. / Raz, Ali K. et al. | AIAA | 2023


    VEHICLE MOTION PLANNER

    CHOI JIWUNG | European Patent Office | 2024

    Free access