In this paper, a parallel Image-based visual servoing/force controller is developed in order to solve the interaction problem between the collaborative robot and the environment so that the robot can track the position trajectory and the desired force at the same time. This control methodology is based on the image-based visual servoing (IBVS) dynamic computed torque control and couples the force control feedback in parallel. Simulations are performed on a collaborative Delta robot and two types of image features are tested to determine which one is better for this parallel IBVS/force controller. The results show the efficiency of this controller.

No abstract

Designing a robot with the best accuracy is always an attractive research direction in the robotics community. In order to create a Gough–Stewart platform with guaranteed accuracy performance for a dedicated controller, this paper describes a novel advanced optimal design methodology: control-based design methodology. This advanced optimal design method considers the controller positioning accuracy in the design process for getting the optimal geometric parameters of the robot. In this paper, three types of visual servoing controllers are applied to control the motions of the Gough–Stewart platform: leg-direction-based visual servoing, line-based visual servoing, and image moment visual servoing. Depending on these controllers, the positioning error models considering the camera observation error together with the controller singularities are analyzed. In the next step, the optimization problems are formulated in order to get the optimal geometric parameters of the robot and the placement of the camera for the Gough–Stewart platform for each type of controller. Then, we perform co-simulations on the three optimized Gough–Stewart platforms in order to test the positioning accuracy and the robustness with respect to the manufacturing errors. It turns out that the optimal control-based design methodology helps get both the optimum design parameters of the robot and the performance of the controller {robot + dedicated controller}.

With the breakthrough development of a series of technologies such as machine learning and internet of things, data plays an increasingly important role in everyone’s daily affairs and work. With the explosive exponential growth of data volume, data types are also quietly changing, from the traditional single, structured data to today’s diverse, semi-structured data. In the face of emerging new massive data, data mining technology has gradually become the focus of attention. Data mining was also known as knowledge discovery (KDD) at that time. It was mainly defined as a pattern hidden in massive data, which must be understood by people and bring potential benefits. In this paper, we mainly studies the basic principle and algorithm knowledge of data mining, and applies ridge regression and random forest algorithm model in real estate price forecasting. Finally, through the stacking thinking of ensemble learning in ensemble learning, we propose a fusion method of ridge regression and random forest model, and obtain a more accurate and stable prediction model.

No abstract