In this paper, two integrated target identification and acquisition algorithms and a graphical user interface (GUI) simulation tool for automated assembly of parallel manipulators are proposed. They seek to identify the target machine part from the workspace, obtain its location and pose parameters, and accomplish its assembling task while avoiding the collision with other items (obstacles). Fourier descriptors (FDs) and support vector machine (SVM) are adopted in this approach. The image of task area of workspace is obtained through machine vision, and the target assembling parts are identified. To acquire the location and pose information of the target, a modulus-shift matching (MSM) algorithm is proposed and integrated into the FD and SVM approaches, which could efficiently obtain the pose parameters while eliminating the effect of choice of starting point. The simulation results of two integrated algorithms, FD-MSM and SVM-MSM, are then compared and analyzed. In addition, a GUI is designed to visualize and assist the assembly process. An application on delta parallel robot with an extra rotational degree of freedom (DOF) is presented.

The major drawbacks of current lower limb rehabilitation robots are high cost and complex structure which make them inappropriate to be applied in the community and family. In this paper, we design an 1-degree-of-freedom (DOF) robot with humanoid gait for lower limb rehabilitation based on Watt-I six-bar mechanism. Let the normal gait trajectory be target trajectory, the dimensions of the mechanism are calculated by path synthesis. First, the objective function to reflect the accuracy of trajectory reproduction and relevant constraints are established. Then GA-BFGS hybrid algorithm is used to minimize the objective function. After that, the optimized mechanism is analyzed by trajectory comparison, velocity / acceleration analysis and joint angle detection. Further, the kinematic simulation of the mechanism is also completed. The results show that while the crank is rotating at a constant speed, the mechanism can reproduce the time sequence and the shape of target trajectory approximately to realize walk training for patients with lower limb disorders whose legs are 810.0–860.0mm long (the corresponding heights are about 1650.0–1750.0mm). Finally, the specific structure of lower limb rehabilitation robot based on this mechanism is designed and the principle prototype model is given.

This paper develops a robotic cognitive rehabilitation therapy (CRT) system to assist patients with mild cognitive impairment (MCI) in block design test (BDT) rehabilitation training. This system bridges the treatment gap that occurs when one physician has several patients to attend to. One physician can setup the BDT training task and simultaneously monitor the training progress of several patients with MCI, which forms an effective one-to-many rehabilitation model. A target information acquisition method is designed to realize target detection and position extraction in automatic rehabilitation. Two graphic user interfaces (GUIs) are developed to provide intuitive control and immediate visual feedback. Different BDTs are selected from the benchmark by the physician in an integrated GUI (I-GUI) and are assigned to several patient GUIs (P-GUIs), respectively. During training, automatic visual assistance can be triggered by the help button and the patients can be guided in finding the target block. Additionally, a robotic arm could be engaged to further help with teaching so that patients can follow the instructions given by the P-GUI and imitate the demonstration given by the robot arm to finish the training task. This system converts traditional MCI rehabilitation into an automatic process, creating an effective model of BDT training for MCI rehabilitation.

Lower limb rehabilitation robots, which usually produce repeated rehabilitative motion, not only simulate general human walking to help patients practice, but also do benefits to the remodel central nervous system to learn and store correct motion model. However, patients with different body parameters usually have different lower limb motion trajectories, and sometimes even the same person’s multiple motion trajectories could differ, thus the task of designing a specific lower limb rehabilitation mechanism for the realization of every motion trajectory is not practical. In this paper, we propose an approach to the clustering of motion trajectories of human lower limb to obtain a limited number of rehabilitation task motion types. Firstly, Gaussian distribution is adopted for the fitting of multiple trajectories of the same person. Through comparison of various clustering algorithms according to separation and compactness, Hierarchical clustering algorithm is chosen to obtain the partitions of the clusters. Finally, the Gaussian process regression (GPR) model of each cluster is established. Results show that clusters generated by this approach can reflect motion trajectory of the subjects and predict human lower limb motion pattern. With a limited number of lower-limb motion patterns, the design task of rehabilitation robots could be greatly simplified.

No abstract