Learning-Based Approaches for Robot Motion Planning in Dynamic Environments

EasyChair Preprint no. 11781

Abstract

This research explores the integration of learning-based techniques into robot motion planning to enhance adaptability in dynamic environments. Traditional motion planning methods face challenges in scenarios with unpredictable changes, such as moving obstacles or dynamic landscapes. The proposed approaches leverage machine learning and reinforcement learning to enable robots to adaptively plan and execute motions in response to real-time environmental dynamics. The study investigates various learning models, training methodologies, and validation strategies, aiming to improve the agility and responsiveness of robots operating in dynamic and uncertain surroundings. The findings contribute to advancing the field of robotics by providing insights into effective learning-based approaches for enhanced motion planning capabilities in dynamic environments.

Keyphrases: motion, planning, robot

@Booklet{EasyChair:11781,
  author = {Kurez Oroy and Jack Jhon},
  title = {Learning-Based Approaches for Robot Motion Planning in Dynamic Environments},
  howpublished = {EasyChair Preprint no. 11781},

  year = {EasyChair, 2024}}