Digital twin-based industrial cloud robotics: Framework, control approach and implementation

Industrial robots can be mechanical intelligent agents by integrating programs, intelligent algorithms and facilitating intelligent manufacturing models from cyber world into physical entities. After introducing the concept of cloud, their storage, computing, knowledge sharing and evolution capabilities are further strengthened. Digital twin is an effective means to achieve the fusion of physics and information. Therefore, it is feasible to introduce the digital twin to the industrial cloud robotics (ICR), in order to facilitate the control optimization of robots’ running state. The traditional manufacturing task-oriented service composition is limited to execution in the cloud, and it is separated from the underlying robot equipment control, which greatly reduces the real-time performance and accuracy of the underlying service response, such as Robotic Control as a Cloud Service (RCaaCS). Therefore, this paper proposes a digital twin-based control approach for ICR. At the manufacturing cell level, robots’ control instruction service modeling is conducted, and then the control service in the digital world is mapped to the robot action control in the physical world through the concept of digital twin. The accumulated operational data in the physical world can be fed back to the digital world as a reference for simulation and control strategy adjustment, finally achieving the integration of cloud services and robot control. A case study based on workpiece disassembly is presented to verify the availability and effectiveness of the proposed control approach.

In order to realize the collaborative operation between the physical prototype and the virtual prototype of industrial robot, a digital twin model of a six-degree-of-freedom industrial robot was established. The structure and motion parameters of the 6-DOF industrial robot are introduced. The virtual prototype model of the industrial robot was established based on Visual One; the digital twin modeling of the industrial robot was completed by the three methods communication between the virtual prototype of the industrial robot and the physical prototype was realized, and the virtual and real collaborative operation of the twin robot and the physical robot was realized. Experiments show that when manipulating the movement of the robot on the physical terminal, the digital twin was consistent with its behavior. The research results provide references for the application of digital twin technology in the field of industrial robots.

In human–robot collaboration (HRC), safe and efficient robotic control requires a deep understanding and realistic modeling of human motion behavior. However, current human motion data collection is inefficient in real HRC and constrained by safety considerations, resulting in limited data coverage of HRC processes. This paper proposes a method for generating human trajectories in collaborative assembly based on a digital human model and reinforcement learning. A muscle‐driven musculoskeletal dynamic model of the digital human is developed, and reinforcement learning is employed to generate synthetic human motion trajectories that conform to biomechanical constraints. Furthermore, these trajectories are used to train collaborative robot control policies by reinforcement learning, enabling adaptive trajectory planning and real‐time obstacle avoidance. The synthetic trajectories are evaluated using Fitts’ law and compared with experimental data. The experimental results show that the synthetic trajectories exhibit consistency with real human motion. The proposed robotic control method can effectively improve the efficiency and safety of human–robot collaborative assembly.

At the present time automatic welding machines are used for welding operations in the production of electric-welded pipes. However, industrial robots are used when welding complex structures consist of pipes of different diameters and bending radius. Unlike welding machines, robots move according to a set coordinate, thus making it possible to obtain welding constructions that “classical” welding machines are not able to perform or require considerable time for their readjustment. Moreover, welding robots-manipulators can perform additional operations: pre-cleaning of the joint, weld preparation and cleaning from dirt. Methods of setting (setting coordinates) of welding robots-manipulators are considered. It was noted that when making settings on the robot's panel it is necessary to stop the technological process, therefore a more rational way is the preliminary imitation of the welding process by using a digital twin of an industrial robot. Using of digital twins of robots-manipulators is often connected with serious financial expenses, therefore development on the basis of the simplified mathematical model of the digital twin is actual, that allows fulfilling the technological process of welding of new kinds of difficult designs by virtual way. Here is a description of a digital twin of an industrial robot-manipulator Yaskawa Motoman MH50-35, developed in Matlab Simulink environment. The main task of developing the digital twin was to create a system of automatic control of the rotation angle on the basis of the position regulator. The elaborated digital twin was tested; the accuracy of processing the wrist rotation assignment is +-0.0001 rad, there is no position overshoot, and the time of a full wrist revolution reaches 1.07 s. The possibility has been shown to use the developed twin as a digital twin of an industrial welding robot taking into account the accepted assumptions.

In the control of complex systems, we observe two diametrical trends: model-based control derived from digital twins, and model-free control through AI. There are also attempts to bridge the gap between the two by incorporating learning-based AI algorithms into digital twins to mitigate mismatches between the digital twin model and the physical system. One of the most straightforward approaches to this is direct input adaptation. In this paper, we ask whether it is useful to employ a generic learning algorithm in such a setting, and our conclusion is “not very”. We denote an algorithm to be more useful than another algorithm based on three aspects: 1) it requires fewer data samples to reach a desired minimal performance, 2) it achieves better performance for a reasonable number of data samples, and 3) it accumulates less regret. In our evaluation, we randomly sample problems from an industrially relevant geometry assurance context and measure the aforementioned performance indicators of 16 different algorithms. Our conclusion is that blackbox optimization algorithms, designed to leverage specific properties of the problem, generally perform better than generic learning algorithms, once again finding that “there is no free lunch”. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Digital twins have the potential to improve productivity and quality in complex systems such as manufacturing systems. Their impact on system performance hinges on the accuracy of their digital models around the system’s operating points. Difficult to measure phenomena, such as wear and tear of equipment, however, may cause a mismatch between the digital twin model and the physical system. In this paper, we formalize this problem and compare 16 potential solution strategies under practical aspects. We argue that readily available off-the-shelf blackbox optimization algorithms may prove more useful for this problem, than more recent learning-based approaches. Specifically, gradient-based algorithms will perform best in systems with high-dimensional, continuous, and non-linear performance functions – even in the presence of white measurement noise.

Industrial robots are a crucial technology for developing smart factories. These smart factories will require more efficient robot control strategies. Hence, researchers and practitioners are putting significant efforts into enhancing this field. One can find in the literature remarkable developments that go from the control of articulated arms, routing, planning, decision-making, self-decision-making, object recognition, and human-robot interface. This manuscript aims to summarize the literature on artificial intelligence in robotic control systems. Moreover, these strategies are analyzed, and the most promising techniques are discussed. This manuscript is intended to guide future directions in this field.

Mitigating collision is a fundamental issue in contact problems, and is required to ensure the safety of a robotic cell. Research into the contact problem between robots and their environment is divided into two parts: one uses the environmental contact model and parameter estimation, the other uses the robot force control method. There are two main problems with this research method. One is that the two research levels are not effectively combined to form a complete solution for force control in practice. The other problem is that research on excessive contact force in the collision phase has not been studied in depth for force control. In this paper, a sensing-executing bionic system is proposed that combines environmental detection and robotic force control based on the way an ant functions. The bionic system clearly explains the process from environment detection to robot control, which can provide guidance when designing a new robot control system. An adaptive switching control algorithm is proposed to mitigate the collision force in the collision phase. From the simulation results, the collision force is significantly reduced due to the implementation of adaptive switching control. Finally, a new self-sensing device is designed which can be integrated into the robot control device. However, as there are no additional sensors or computational complexity in the system, the effectiveness of the circuit and superiority of the adaptive parameter update must be verified by experimentation.

Modern industrial robotic systems are highly interconnected. They operate in a distributed environment and communicate with sensors, computer vision systems, mechatronic devices, and computational components. On the fundamental level, communication and coordination between all parties in such distributed system are characterized by discrete event behavior. The latter is largely attributed to the specifics of communication over the network, which, in terms, facilitates asynchronous programming and explicit event handling. In addition, on the conceptual level, events are an important building block for realizing reactivity and coordination. Event-driven architecture has manifested its effectiveness for building loosely-coupled systems based on publish-subscribe middleware, either general-purpose or robotic-oriented. Despite all the advances in middleware, industrial robots remain difficult to program in context of distributed systems, to a large extent due to the limitation of the native robot platforms. This paper proposes an architecture for flexible event-based control of industrial robots based on the Adept V+ platform. The architecture is based on the robot controller providing a TCP/IP server and a collection of robot skills, and a high-level control module deployed to a dedicated computing device. The control module possesses bidirectional communication with the robot controller and publish/subscribe messaging with external systems. It is programmed in asynchronous style using pyadept, a Python library based on Python coroutines, AsyncIO event loop and ZeroMQ middleware. The proposed solution facilitates integration of Adept robots into distributed environments and building more flexible robotic solutions with event-based logic.

As an innovative information technology, Digital Twin has greatly promoted the development of intelligent manufacturing in the industry. However, in the field of geotechnical engineering, there are still few researches on this aspect, which is still a “new territory” and “no man's land”. The concept of digital twin coincides with the needs of geotechnical engineering informatization, so the introduction of digital twin technology into the field of geotechnical engineering will help to promote the development process of geotechnical engineering informatization and digitization. This paper puts forward and defines the digital twin model of geotechnical engineering, describes the connotation of the digital twin model, and studies the architecture of the digital twin model of geotechnical engineering. On this basis, the integration and sharing mechanism of geotechnical engineering digital twin data based on BIM technology is proposed. In order to break through the defect that the geotechnical engineering information model has not fully played its role for a long time, an integrated model of geological body and structural body is constructed based on the construction and integration module of geotechnical digital twin model. Furthermore, the geotechnical engineering digital twin simulation analysis module is developed to initially form the geotechnical engineering digital twin model, so as to realize the geotechnical engineering digital design, collaborative construction, visual decision-making and transparent management.

Precision component displacement, processing, and manipulation in an industrial environment require the high-precision positioning and orientation of industrial robots. However, industrial robots’ positioning includes uncertainties due to assembly and manufacturing tolerances. It is therefore required to use calibration techniques for industrial robot parameters. One of the major sources of uncertainty is the one associated with industrial robot geometrical parameter values. In this paper, using multi-objective meta-heuristic optimization approaches and optical metrology measurements, more accurate Denavit–Hartenberg (DH) geometrical parameters of an industrial robot are estimated. The sensor data used to perform this calibration are the absolute 3D position readings using a highly accurate laser tracker (LT) and industrial robot joint angle readings. Other than position accuracy, the mean absolute deviation of the DH parameters from the manufacturer’s given parameters is considered as the second objective function. Therefore, the optimization problem investigated in this paper is a multi-objective one. The solution to the multi-objective optimization problem is obtained using different evolutionary and swarm optimization approaches. The evolutionary optimization approaches are nondominated sorting genetic algorithms and a multi-objective evolutionary algorithm based on decomposition. The swarm optimization approach considered in this paper is multi-objective particle swarm optimization. It is observed that NSGAII outperforms the other two optimization algorithms in terms of a more diverse Pareto front and the function corresponding to the positional accuracy. It is further observed that through using NSGAII for calibration purposes, the root mean squared for positional error has been improved significantly compared with nominal values.

With the advancement of the motion control of industrial robots in recent years, a method that can easily measure the accuracy of the synchronous control of a two-axis dual-arm robot is desired. Therefore, in this study, we propose a new measurement method that creates a ball rolling motion in a circular orbit on a work plate and uses the rolling motion error with respect to the reference circle. In addition, industrial robots in the field are always forced to operate continuously for a long period of time, and they work with all kinds of loads overlapping and applying non-uniform loads. In this study, we propose a new measurement method that creates a rolling motion of a ball on a circular track on a work plate and uses the error of the rolling motion relative to a reference circle. In particular, in order to elucidate the motion error during long-time continuous operation under high load, we approached the problem from the viewpoint of joint temperature and power consumption. As a result, we found that the ball trajectory error was caused by an increase in the temperature of the elbow and wrist motors, which increased the joint load and caused an angular error in the plate. Even when non-uniform loads were applied, the circular trajectory could be corrected by making corrections according to the temperature at each arm. The tendency of the angle error due to the temperature rise and the increase in joint load of each joint was found, and it was found that it was possible to correct the angle error by FF control.

Biopharma Is Going Digital … Bit by Bit

Most industrial robots are still controlled with motor-side feedback. To increase the accuracy of industrial robots, controllers with joint-side feedback and explicit consideration of the joint elasticity, such as linearization-based controllers, are needed. The key issue for the performance of linearization-based controllers is a high-fidelity model. Today, the drivetrains installed in the joints of industrial robots of the high payload class usually consist of a permanent magnet synchronous machine and a cycloidal drive. Such robot joints are highly nonlinear due to effects like hysteresis, torque ripples and friction. Therefore, the drivetrain dynamics are crucial for the experimental performance of linearization-based controllers for industrial robots. This paper identifies the challenges in linearization-based control of industrial robots with such a drivetrain configuration based on experimental results on a KUKA KR-210-2. Using an exemplary approach, it is shown that a linearization-based controller does not provide the theoretical performance due to needed model simplifications. For this purpose, simulation and experimental results are compared to a linear robot controller with motor-side feedback. These results indicate why such controllers are still a valid alternative for the practical application of similar industrial robots.

Much of the technology that makes robots reliable, human friendly, and industrial robotics adaptable for numerous applications has emerged from manufacturers of industrial robots. With an estimated installation base in 2014 of about 1.5 million units, some 171000 new installations in that year and an annual turnover of the robotics industry estimated to be US$ 32 billion, industrial robots are by far the largest commercial application of robotics technology today. The foundations for robot motion planning and control were initially developed with industrial applications in mind. These applications deserve special attention in order to understand the origin of robotics science and to appreciate the many unsolved problems that still prevent the wider use of robots in today’s agile manufacturing agile manufacturing environments. In this chapter, we present a brief history and descriptions of typical industrial robotics applications and at the same time we address current critical state-of-the-art technological developments. We show how robots with different mechanisms fit different applications and how applications are further enabled by latest technologies, often adopted from technological fields outside manufacturing automation. We will first present a brief historical introduction to industrial robotics with a selection of contemporary application examples which at the same time refer to a critical key technology. Then, the basic principles that are used in industrial robotics and a review of programming methods will be outlined. We will also introduce the topic of system integration particularly from a data integration point of view. The chapter will be closed with an outlook based on a presentation of some unsolved problems that currently inhibit wider use of industrial robots.

In this paper, we present an object-oriented C++ library for robotic manipulator control and simulation, THRControl, which is inherited from Qt and VTK. The library package has advantages include support cross-platform applications; high flexibility and high computational efficiency meet the need of computations required in robot control such as forward kinematics, inverse dynamics, and jacobian. The experimental results show that it is very easy is construct a user-friendly manipulator control and simulation system.