Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Memetic algorithms (MAs) are population-based meta-heuristic search algorithms that combine the composite benefits of natural and cultural evolutions. An adaptive MA (AMA) incorporates an adaptive selection of memes (units of cultural transmission) from a meme pool to improve the cultural characteristics of the individual member of a population-based search algorithm. This paper presents a novel approach to design an AMA by utilizing the composite benefits of differential evolution (DE) for global search and Q-learning for local refinement. Four variants of DE, including the currently best self-adaptive DE algorithm, have been used here to study the relative performance of the proposed AMA with respect to runtime, cost function evaluation, and accuracy (offset in cost function from the theoretical optimum after termination of the algorithm). Computer simulations performed on a well-known set of 25 benchmark functions reveal that incorporation of Q-learning in one popular and one outstanding variants of DE makes the corresponding algorithm more efficient in both runtime and accuracy. The performance of the proposed AMA has been studied on a real-time multirobot path-planning problem. Experimental results obtained for both simulation and real frameworks indicate that the proposed algorithm-based path-planning scheme outperforms the real-coded genetic algorithm, particle swarm optimization, and DE, particularly its currently best version with respect two standard metrics defined in the literature.

Realization of an Adaptive Memetic Algorithm Using Differential Evolution and Q-Learning: A Case Study in Multirobot Path Planning

In J Robot Syst 13(3):177---185 (1996), Ma proposed an efficient technique to stabilize local torque optimization solution of redundant manipulators, which prevents occurrence of high joint-velocity and guarantees the final joint-velocity to be near zero. To prevent the same problems, a different-level simultaneous minimization scheme is proposed in this paper for robotic redundancy resolution, which combines the minimum two-norm joint-velocity and joint-torque solutions via two weighting factors. Physical constraints such as joint-angle limits, joint-velocity limits and joint-acceleration limits are also taken into consideration in such a scheme-formulation. Moreover, the proposed different-level simultaneous minimization scheme is resolved at the joint-acceleration level and reformulated as a general quadratic program (QP). Computer-simulation results based on the PUMA560 robot manipulator performing different types of end-effector path-tracking tasks demonstrate the validity and advantage of the proposed different-level simultaneous minimization scheme. Furthermore, experimental verification conducted on a practical six-link planar robot manipulator substantiates the effectiveness and the physical realizability of the proposed scheme.

Different-Level Simultaneous Minimization of Joint-Velocity and Joint-Torque for Redundant Robot Manipulators

Quantum-like mutation-induced dragonfly-inspired optimization approach

Equivalence of Different-level Schemes for Repetitive Motion Planning of Redundant Robots

Inverse Kinematic Solution for Robot Manipulator Based on Electromagnetism-like and Modified DFP Algorithms

Inverse Kinematic Solution for Robot Manipulator Based on Electromagnetism-like and Modified DFP Algorithms: Inverse Kinematic Solution for Robot Manipulator Based on Electromagnetism-like and Modified DFP Algorithms

Ice coating in power networks could result in power-tower collapse and power interruption. This paper introduces a preliminary design of deicing robot, which travels on transmission lines and automatically remove ices. Inevitably, the deicing robot will encounter some obstacles. To cross an obstacle, the deicing robot needs to control its arms to grasp transmission line over the obstacle. In this paper, Q-learning, one of reinforcement learning algorithms is applied to study the line-grasping control strategies for deicing robot. We implement a graphical simulation environment and use it to evaluate the Q-learning based line-grasping control policy study algorithm. Simulation results show that the proposed algorithm is promising for the line-grasping control of deicing robot.

Applying Q-Learning Algorithm to Study Line-Grasping Control Policy for Transmission Line Deicing Robot

Purpose – This paper aims to develop a new real‐time effective method for solving the inverse kinematics (IK) problem, especially for those manipulators with high‐dimensional nonlinear kinematic equations.Design/methodology/approach – The paper transforms the IKs problem into a minimization problem. Then, a novel meta‐heuristic algorithm, called the electromagnetism‐like method (EM), is used to solve this equivalent problem. Moreover, in order to further improve the computational efficiency and accuracy of EM, a hybrid method which combines EM with the Davidon‐Fletcher‐Powell (DFP) method is proposed.Findings – The results showed that EM is a powerful yet easy algorithm for solving the IKs problem of robot manipulators. Its complexity is independent on the characteristics of the kinematic equations involving dimensionality and the degree of nonlinearity. Moreover, EM can be used as an accompanying algorithm for DFP method to get better precision at a lower iteration number.Originality/value – The method d...

A novel hybrid electromagnetism‐like algorithm for solving the inverse kinematics of robot

In view of the current situation that the traditional climbing robot of stay cable machine still needs manual clamping and is challenging to adapt to cables with different diameters, a new robot had been designed. Firstly, its structure and control design scheme were introduced. The robot adopted a mechanical clamping structure and can adapt to cables with different diameters. The new single motor double drive design can avoid complex multi-motor synchronous control, and a simple automatic control system was designed with high degree of automation. Then the diameter range of the cable was calculated and analyzed. Finally, the prototype experiment was tested. The results show that the designed cable climbing robot has the advantages of automatic clamping and good climbing stability.

Feng Yin

Papers

Inverse Kinematic Solution for Robot Manipulator Based on Electromagnetism-like and Modified DFP Algorithms

Inverse Kinematic Solution for Robot Manipulator Based on Electromagnetism-like and Modified DFP Algorithms: Inverse Kinematic Solution for Robot Manipulator Based on Electromagnetism-like and Modified DFP Algorithms

Applying Q-Learning Algorithm to Study Line-Grasping Control Policy for Transmission Line Deicing Robot

A novel hybrid electromagnetism‐like algorithm for solving the inverse kinematics of robot

Structural Design of a Cable Climbing Robot