This paper describes a pose measurement and tracking strategy for an automatic tracking-based scanning system through developing a ball-shaped target. The target structure is introduced. Then, to determine the target pose, a coded marker and accurate center extraction method is proposed using subpixel and cross-ratio invariance principle. Furthermore, the target coordinate system is established by vision-based target calibration. A confidence-based tracker is proposed, enabling higher tracking confidence and accuracy, and keeping a high tracking speed. The stereo vision estimates the 3D position and orientation of the moving target in real-time. The trajectory is smoothed dynamically based on the Kalman filter. Experiments are implemented to verify the tracking speed, accuracy, and spatial accessibility in robot tracking applications. Additionally, the proposed target and strategy have good performance in full-space and fall-orientation tracking.

Compared with a single manipulator manufacturing cell, a dual manipulator cooperative system has more advantages in reconfigurability and flexibility. However, there are calibration errors and multi-source disturbances in the collaborative process, which lead to the processing trajectory accuracy defects of large-scale associated machining features. To solve the above problems, a practical path tracking synchronous control algorithm based on position-based visual servoing (PBVS) is proposed in this paper for the dual manipulator cooperative system, the proposed dynamic path tracking cross-coupled sliding mode controller (PTCSMC) scheme can realize dynamic paths correction while executing the pre-planned paths. In addition, for the cross-coupled technology to be applied into the proposed control algorithm for dynamic path tracking based on the real-time feedback of the highly repeatable 3D visual measurement instrument (VMI), the tracking and synchronous errors of the dual manipulators converge synchronously to zero. Finally, the stability of proposed control algorithm is proven by the Lyapunov method. In the end, the real-time line and circle path tracking experimental results using two industrial manipulators demonstrate the effectiveness of the proposed algorithm.

Taking human-robot collaborative assembly as an example, the methods based on contact forces can improve the assembly efficiency of industrial robots with large components in industrial manufacturing. However, due to the large size, high payload, assembly accuracy and dynamic changes in grip position, accurately estimating the contact forces between the payload and the operator becomes challenging when handling these large components. In this paper, a two-stage method is proposed for payload dynamic parameter identification. The parameter identification equation in the sensor coordinate system is initially established. Furthermore, the identification model of recursive restricted total least squares (RRTLS) based on total least squares (TLS) is constructed to achieve low-consumption online identification. According to the assembly requirements and payload characteristics, the posture coordinate system is designed for safety, including the feasible workspace for the robot. Subsequently, the static identification postures and dynamic excitation trajectory are planned to obtain static values and dynamic inertial parameters. In the end, a high-payload human-robot collaborative assembly system is built to validate the proposed method. Experimental results show that compared with the existing methods, the proposed approach can effectively identify and compensate the payload, leading to more accurate external force sensing.

Benchmark feature detection is critical in mobile robot automatic drilling systems for compensating robot accuracy and assembly errors in aerospace manufacturing. System accuracy is influenced by reference feature recognition, which is often hindered by material interference and background noise. To address these issues, this paper proposes a method that uses a 2D industrial camera for image capture, applies deep learning for initial target recognition and positioning, and then determines the feature extraction location based on the initial recognition. The extracted benchmark positions are accurately fitted using an improved Huber algorithm. Experimental results demonstrate that this approach improves the benchmark feature detection recognition rate by 43.8%, center recognition accuracy by 78.26%, and overall hole processing accuracy by 54.69%.