Obstacle Avoidance Path Planning Strategy for Industrial Robotic Arm

Koh, Jing Sheng (2026) Obstacle Avoidance Path Planning Strategy for Industrial Robotic Arm. Final Year Project (Bachelor), Tunku Abdul Rahman University of Management and Technology.

Text KOH_JING_SHENG_Full Text.pdf Restricted to Registered users only Download (6MB)

Abstract

This project presents the design and analysis of a hybrid Rapidly-Exploring Random Tree and Proximal Policy Optimization (RRT-PPO) path planning strategy for a six-degree-of-freedom (6DOF) industrial robotic arm. Its primary goal is to generate collision-free trajectories in the presence of static obstacles while reducing path length and decreasing computation time. The study is conducted entirely in a simulated environment using Microsoft Visual Studio Code and PyBullet, as hardware implementation is limited by time and resource constraints. In the proposed framework, RRT provides effective global exploration and waypoint generation, while PPO enhances local motion execution and obstacle avoidance between waypoints. The hybrid method is evaluated in terms of computation time, path length, and obstacle avoidance success rate, and is compared against the baseline goal-biased RRT algorithm across three static obstacle scenarios. This study is expected to contribute to safer, more efficient, and more adaptive robotic motion planning in industry, while also supporting broader goals of innovation, workplace safety, and sustainable industrial development