MoMo: Mouse-Based Motion Planning for Optimized Grasping to Declutter Objects Using a Mobile Robotic Manipulator

Abstract

The aim of this study is to develop a cost-effective and efficient mobile robotic manipulator designed for decluttering objects in both domestic and industrial settings. To accomplish this objective, we implemented a deep learning approach utilizing YOLO for accurate object detection. In addition, we incorporated inverse kinematics to facilitate the precise positioning, placing, and movement of the robotic arms toward the desired object location. To enhance the robot’s navigational capabilities within the environment, we devised an innovative algorithm named “MoMo”, which effectively utilizes odometry data. Through careful integration of these algorithms, our goal is to optimize grasp planning for object decluttering while simultaneously reducing the computational burden and associated costs of such systems. During the experimentation phase, the developed mobile robotic manipulator, following the MoMo path planning strategy, exhibited an impressive average path length coverage of 421.04 cm after completing 10 navigation trials. This performance surpassed that of other state-of-the-art path planning algorithms in reaching the target. Additionally, the MoMo strategy demonstrated superior efficiency, achieving an average coverage time of just 16.84 s, outperforming alternative methods.