Kang Min

Robotic ultrasound-guided system improves surgical flexibility and accuracy. Ultrasound (US) calibration is the key to obtain spatial relationship and localization of US images. However, existing calibration methods mainly rely on an external tracker, which leads to complicated workflow and prone to error accumulation. In this paper, we proposed a robot-assisted automatic US calibration method. This method can automatically complete the US calibration without any external tracker, thus improving the calibration accuracy and simplifying the workflow. In addition, we propose an automatic image segmentation method incorporating prior knowledge. It automatically segments the features of the calibration model in the US image during the US scanning process, and ensures the smooth execution of the automatic robot calibration process. Specifically, we transformed the calibration problem into a point-to-point registration problem and conducted experiments using three different registration algorithms. The results show that the calibration accuracy of our method is 0.65±0.20 mm. Our method significantly reduces calibration time compared to manual calibration. We also compare the proposed method with state-of-the-art methods, and the results demonstrated that the proposed method performs better.

In this letter, a novel hybrid motion optimization framework is proposed for a humanoid upper-body robot with two 7-DOF arms and a 2-DOF waist, to flexibly and safely carry objects in constrained and dynamic environments. The framework consists of trilayer interconnected optimization, which is dedicated to planning the optimal carrying configuration, waist-arm motion trajectory, and dual-arm nullspace trajectory, respectively. The top layer finds the most dexterous waist-arm carrying configuration that satisfies environmental constraints, which is achieved by the effective integration of the multi-objective evolutionary algorithm (EA), the proposed optimal manipulation index, and the parameterization method. The middle layer applies a non-linear optimization method to plan collision-free trajectory that connects the initial and optimal carrying configuration. The bottom layer is achieved by equipping the top layer with elite reproduction operator strategy and adaptive evolution space strategy, generating dual-arm nullspace trajectory in real-time for dynamic obstacle avoidance. The various carrying experiments demonstrate the effectiveness of the proposed framework.

Force control is one of the core modules for surface finishing such as grinding, polishing and sanding. However, the current force control methods based on human skills lack in-depth analysis of data patterns or are only applicable to flat surfaces. In addition, surface finishing is mainly performed by hand, resulting in low processing efficiency and poor product consistency. Therefore, this paper proposes a force control method that incorporates human skills to achieve relatively accurate force skill transfer and complex surface finishing. Firstly, human skills consisting of the force skill and the motion skill are learned. The force skill is used to generate the desired force. Then, a series of discrete poses are obtained based on human demonstration and combined with the motion skill to generate the desired trajectory. Finally, a computed-torque impedance control method is proposed to achieve relatively accurate force skill transfer and complex surface finishing by incorporating the desired trajectory and the desired force. The experiments are conducted on a platform composed of a 7-DOF collaborative robot manipulator from Franka Emika and a complex violin surface. The results demonstrate that the proposed force control method can achieve relatively accurate force skill transfer and improve the surface quality of the workpiece.

This article proposes a stable and high-accuracy model-free calibration method for non-open robotic systems, which can significantly improve the robot positional accuracy. Two improvements are made to the existing kriging-based error compensation method to achieve robustness/practicality enhancement goals. The semivariogram model is solved using the sequential quadratic programming algorithm, and the distance weight coefficients are added to the objective function. The accuracy of semivariogram modeling is guaranteed, thereby improving the performance and stability of error compensation. The hand-eye (the pose matrix between the robot base and the laser tracker) and the tool center point position are calibrated based on Kronecker products without relying on the spatial analyzer software to construct the robot base coordinate system separately. Thus, the calibration accuracy and efficiency are significantly improved. Experiments have been conducted, and the results reveal that the proposed method can significantly reduce the robot positional error. Furthermore, the proposed approach performs better than the existing kriging-based error compensation method without Kronecker products. The maximum, mean, and root mean square values of the absolute positional errors are reduced by 34.48%, 8.09%, and 10.05%, respectively.

Existing machine vision-based roughness measurement methods cannot accurately measure the roughness of free-form surfaces (with large curvature variations). To overcome this problem, this paper proposes a roughness measurement method based on a generative adversarial network (GAN) and a BP neural network. Firstly, this method takes images and curvature of free-form surfaces as training samples. Then, GAN is trained for roughness measurement through each game between generator and discriminant network by using real samples and pseudosamples (from generator). Finally, the BP neural network maps the image discriminant value of GAN and radius of curvature into roughness value (Ra). Our proposed method automatically learns the features in the image by GAN, omitting the independent feature extraction step, and improves the measurement accuracy by BP neural network. The experiments show that the accuracy of the proposed roughness measurement method can measure free-form surfaces with a minimum roughness of 0.2 μm, and measurement results have a margin of 10%.