Jacobus Janse Van Vuuren

Citation

Thesis Title
Learning-based robotic manipulation for dynamic object handling

Read article at Massey Research Online:

The autonomous robotic grasping of previously unseen objects is a difficult task, confounded by object geometry, weight-distribution, friction coefficients, and deformation characteristics. Sensing and actuation accuracy can also significantly impact manipulation quality. Mr Janse van Vuuren employed convolutional neural networks, regression, and machine vision to address this issue. He constructed a physical prototype system consisting of a robotic manipulator, vision enclosure, imaging system, conveyor, sensing unit, and control system for testing. Over 4,000 trials were conducted utilising 100 objects. Experimentation showed that robotic manipulation quality could be improved by 10.3% when selecting to optimise for the proposed metrics, quantified by a metric related to translational error. Trials further demonstrated a grasp success rate of 99.3% for known objects and 98.9% for objects for which a priori information is unavailable. For unknown objects, this equated to an improvement of approximately 10% relative to similar methodologies deployed in the literature.

Supervisors
Dr Liqiong Tang
Associate Professor Ibrahim Al-Bahadly
Associate Professor Khalid Arif