Precision object handling and manipulation require the accurate positioning of industrial robots. A common practice for performing end effector positioning is to read joint angles and use industrial robot forward kinematics (FKs). However, industrial robot FKs rely on the robot Denavit–Hartenberg (DH) parameter values, which include uncertainties. Sources of uncertainty associated with industrial robot FKs include mechanical wear, manufacturing and assembly tolerances, and robot calibration errors. It is therefore necessary to increase the accuracy of DH parameter values to reduce the impact of uncertainties on industrial robot FKs. In this paper, we use differential evolution, particle swarm optimization, an artificial bee colony, and a gravitational search algorithm to calibrate industrial robot DH parameters. A laser tracker system, Leica AT960-MR, is utilized to register accurate positional measurements. The nominal accuracy of this non-contact metrology equipment is less than 3 μm/m. Metaheuristic optimization approaches such as differential evolution, particle swarm optimization, an artificial bee colony and a gravitational search algorithm are used as optimization methods to perform the calibration using laser tracker position data. It is observed that, using the proposed approach with an artificial bee colony optimization algorithm, the accuracy of industrial robot FKs in terms of mean absolute errors of static and near-static motion over all three dimensions for the test data decreases from its measured value of 75.4 μm to 60.1 μm (a 20.3% improvement).

This literature review investigates the integration of machine learning (ML) into optical metrology, unveiling enhancements in both efficiency and effectiveness of measurement processes. With a focus on phase demodulation, unwrapping, and phase-to-height conversion, the review highlights how ML algorithms have transformed traditional optical metrology techniques, offering improved speed, accuracy, and data processing capabilities. Efficiency improvements are underscored by advancements in data generation, intelligent sampling, and processing strategies, where ML algorithms have accelerated the metrological evaluations. Effectiveness is enhanced in measurement precision, with ML providing robust solutions to complex pattern recognition and noise reduction challenges. Additionally, the role of parallel computing using graphics processing units and field programmable gate arrays is emphasised, showcasing their importance in supporting the computationally intensive ML algorithms for real-time processing. This review culminates in identifying future research directions, emphasising the potential of advanced ML models and broader applications within optical metrology. Through this investigation, the review articulates a future where optical metrology, empowered by ML, achieves improved levels of operational efficiency and effectiveness.