Search results

In this paper, the authors aim to propose a method for learning robotic assembly sequences, where precedence constraints and object relative size and location constraints can be learned by demonstration and autonomous robot exploration.

To successfully plan the operations involved in assembly tasks, the planner needs to know the constraints of the desired task. In this paper, the authors propose a methodology for learning such constraints by demonstration and autonomous exploration. The learning of precedence constraints and object relative size and location constraints, which are needed to construct a planner for automated assembly, were investigated. In the developed system, the learning of symbolic constraints is integrated with low-level control algorithms, which is essential to enable active robot learning.

The authors demonstrated that the proposed reasoning algorithms can be used to learn previously unknown assembly constraints that are needed to implement a planner for automated assembly. Cranfield benchmark, which is a standardized benchmark for testing algorithms for robot assembly, was used to evaluate the proposed approaches. The authors evaluated the learning performance both in simulation and on a real robot.

The authors' approach reduces the amount of programming that is needed to set up new assembly cells and consequently the overall set up time when new products are introduced into the workcell.

In this paper, the authors propose a new approach for learning assembly constraints based on programming by demonstration and active robot exploration to reduce the computational complexity of the underlying search problems. The authors developed algorithms for success/failure detection of assembly operations based on the comparison of expected signals (forces and torques, positions and orientations of the assembly parts) with the actual signals sensed by a robot. In this manner, all precedence and object size and location constraints can be learned, thereby providing the necessary input for the optimal planning of the entire assembly process.

The purpose of this paper is to propose a new method based on three-dimensional (3D) vision technologies and human skill integrated deep learning to solve assembly positioning task such as peg-in-hole.

Hybrid camera configuration was used to provide the global and local views. Eye-in-hand mode guided the peg to be in contact with the hole plate using 3D vision in global view. When the peg was in contact with the workpiece surface, eye-to-hand mode provided the local view to accomplish peg-hole positioning based on trained CNN.

The results of assembly positioning experiments proved that the proposed method successfully distinguished the target hole from the other same size holes according to the CNN. The robot planned the motion according to the depth images and human skill guide line. The final positioning precision was good enough for the robot to carry out force controlled assembly.

The developed framework can have an important impact on robotic assembly positioning process, which combine with the existing force-guidance assembly technology as to build a whole set of autonomous assembly technology.

This paper proposed a new approach to the robotic assembly positioning based on 3D visual technologies and human skill integrated deep learning. Dual cameras swapping mode was used to provide visual feedback for the entire assembly motion planning process. The proposed workpiece positioning method provided an effective disturbance rejection, autonomous motion planning and increased overall performance with depth images feedback. The proposed peg-hole positioning method with human skill integrated provided the capability of target perceptual aliasing avoiding and successive motion decision for the robotic assembly manipulation.

This paper aims to increase the safety of the robots’ operation by developing a novel method for real-time implementation of velocity scaling and obstacle avoidance as the two widely accepted safety increasing concepts.

A fuzzy version of dynamic movement primitive (DMP) framework is proposed as a real-time trajectory generator with imbedded velocity scaling capability. Time constant of the DMP system is determined by a fuzzy system which makes decisions based on the distance from obstacle to the robot’s workspace and its velocity projection toward the workspace. Moreover, a combination of the DMP framework with a human-like steering mechanism and a novel configuration of virtual impedances is proposed for real-time obstacle avoidance.

The results confirm the effectiveness of the proposed method in real-time implementation of the velocity scaling and obstacle avoidance concepts in different cases of single and multiple stationary obstacles as well as moving obstacles.

As the provided experiments indicate, the proposed method can effectively increase the real-time safety of the robots’ operations. This is achieved by developing a simple method with low computational loads.

This paper proposes a novel method for real-time implementation of velocity scaling and obstacle avoidance concepts. This method eliminates the need for modification of original DMP formulation. The velocity scaling concept is implemented by using a fuzzy system to adjust the DMP’s time constant. Furthermore, the novel impedance configuration makes it possible to obtain a non-oscillatory convergence to the desired path, in all degrees of freedom.

As complex analysis of contact models is required in the traditional assembly strategy, it is still a challenge for a robot to complete the multiple peg-in-hole assembly tasks autonomously. This paper aims to enable the robot to complete the assembly tasks autonomously and more efficiently, with the strategies learned by reinforcement learning (RL), a learning-accelerated deep deterministic policy gradient (LADDPG) algorithm is proposed.

The multiple peg-in-hole assembly strategy is designed in two modules: an advanced planning module and a bottom control module. The advanced module is completed by the LADDPG agent, which is used to derive advanced commands based on geometric and environmental constraints, that is, the desired contact force. The bottom-level control module will drive the robot to complete the compliant assembly task through the adaptive impedance algorithm according to the command set issued by the advanced module. In addition, a set of safety assurance mechanisms is developed to safely train a collaborative robot to complete autonomous learning.

The method can complete the assembly tasks well through RL, and it can realize satisfactory compliance of the robot to the environment. Compared with the original DDPG algorithm, the average values of the instantaneous maximum contact force and contact torque during the assembly process are reduced by approximately 38% and 74%, respectively.

The entire algorithm can also be applied to other robots and the assembly strategy can be applied in the field of the automatic assembly.

A compliant assembly strategy based on the LADDPG algorithm is proposed to complete the automated multiple peg-in-hole assembly tasks.

The purpose of this paper is to investigate the multi-skilled workers assignment problem in complex assembly systems such as aircraft assembly lines. An adaptive binary particle swarm optimization (A-BPSO) algorithm is proposed, which is used to balance the workload of both assembly stations and processes and to minimize the human cost.

Firstly, a cycle time model considering the cooperation of multi-skilled workers is constructed. This model provides a quantitative description of the relationship between the cycle time and multi-skilled workers by means of revising the standard learning curve with the “Partition-And-Accumulate” method. Then, to improve the accuracy and stability of the current heuristic algorithms, an A-BPSO algorithm that suits for the discrete optimization problems is proposed to assign multi-skilled workers to assembly stations and processes based on modified sigmoid limiting function.

The proposed method has been successfully applied to a practical case, and the result justifies its advantage as well as adaptability to both theory and engineering application.

A novel cycle time model considering cooperation of multi-skilled workers is constructed so that the calculation results of cycle time are more accurate and closer to reality. An A-BPSO algorithm is proposed to improve the stability and convergence in dealing with the problems with higher dimensional search space. This research can be used by the project managers and dispatchers on assembly field.

Introduction Consider a hi‐fi loudspeaker manufacturing company acquired on the brink of insolvency by an American multinational. The new owners discover with growing concern that the product range is obsolete, that manufacturing facilities are totally inadequate and that there is a complete absence of any real management substance or structure. They decide on the need to relocate urgently so as to provide continuity of supply at the very high — a market about to shrink at a rate unprecedented in its history.

Steam turbine final assembly is a dynamic process, in which various interference events occur frequently. Currently, data transmission relies on oral presentation, while scheduling depends on the manual experience of managers. This mode has low information transmission efficiency and is difficult to timely respond to emergencies. Besides, it is difficult to consider various factors when manually adjusting the plan, which reduces assembly efficiency. The purpose of this paper is to propose a knowledge-based real-time scheduling system under cyber-physical system (CPS) environment which can improve the assembly efficiency of steam turbines.

First, an Internet of Things based CPS framework is proposed to achieve real-time monitoring of turbine assembly and improve the efficiency of information transmission. Second, a knowledge-based real-time scheduling system consisting of three modules is designed to replace manual experience for steam turbine assembly scheduling.

Experiments show that the scheduling results of the knowledge-based scheduling system outperform heuristic algorithms based on priority rules. Compared with manual scheduling, the delay time is reduced by 43.9%.

A knowledge-based real-time scheduling system under CPS environment is proposed to improve the assembly efficiency of steam turbines. This paper provides a reference paradigm for the application of the knowledge-based system and CPS in the assembly control of labor-intensive engineering-to-order products.

In this paper, an assembly sequence planning system, based on binary vector representations, is developed. The neural network approach has been employed for analyzing optimum assembly sequence for assembly systems.

The input to the assembly system is the assembly's connection graph that represents parts and relations between these parts. The output to the system is the optimum assembly sequence. In the constitution of assembly's connection graph, a different approach employing contact matrices and Boolean operators has been used. Moreover, the neural network approach is used in the determination of optimum assembly sequence. The inputs to the networks are the collection of assembly sequence data. This data is used to train the network using the back propagation (BP) algorithm.

The proposed neural network model outperforms the available assembly sequence‐planning model in predicting the optimum assembly sequence for mechanical parts. Due to the parallel structure and fast learning of neural network, this kind of algorithm will be utilized to model another types of assembly systems.

In the proposed neural approach, the back propagation algorithm is used. Various training algorithms can be employed.

The simulation results suggest that the neural predictor would be used as a predictor for possible practical applications on modeling assembly sequence planning system.

This paper discusses a new modelling scheme known as artificial neural networks. The neural network approach has been employed for analyzing feasible assembly sequences and optimum assembly sequence for assembly systems.

New methods to introduce topics in classrooms are needed to enhance the construction management educational experience. One of these new methods is showing real time videos that highlight the various elements of concern in the classroom lecture. The purpose of this paper is to use augmented reality technology (ART) and a layer of artificial visualizations to simulate the environmental context and spatio-temporal constraints of various construction processes. The superimposition of images serves as an instructional mechanism to virtually incorporate jobsite experiences into classrooms. This enhancement of spatio-temporal constraints enables learners to visualize context and hidden processes otherwise unattainable through traditional classroom lectures.

A significantly improved perception of reality is created through the combination of the learners’ ability to understand the complexity of construction products (e.g. assemblies) and associated jobsite processes by viewing the real environment augmented with computer-generated information layers.

Testing the ART video in a classroom with undergraduate construction management students showed that students who were exposed to the ART video were able to remember and identify the highlighted elements in the corresponding assembly more effectively than those who were not.

ART is a valuable tool in enhancing classroom learning and gives educators a teaching advantage when they combine traditional classroom lectures with ART enabled media.