Search

Reach-and-grasp is one of the most fundamental activities in daily life, while few rehabilitation robots provide integrated and active training of the arm and hand for patients after stroke to improve their mobility. In this study, a novel hybrid arm-hand rehabilitation robot (HAHRR) was built for the reach-and-grasp task. This hybrid structure consisted of a cable-driven module for three-dimensional arm motion and an exoskeleton for hand motion, which enabled assistance of the arm and hand simultaneously. To implement active compliance control, an EMG-based admittance controller was applied to the HAHRR. Experimental results showed that the HAHRR with the EMG-based admittance controller could not only assist the subject in fulfilling the reach-and-grasp task, but also generate smoother trajectories compared with the force-sensing-based admittance controller. These findings also suggested that the proposed approach might be applicable to post-stroke arm-hand rehabilitation training.

Rehabilitation robots play an increasingly important role in the recovery of motor function for stroke. To ensure a natural physical human-robot interaction (pHRI) and enhance the active participation of subjects, it is necessary for the robots to understand the human intention and cooperate actively with humanlike characteristics. This study proposed a hybrid active control algorithm with human motion intention detection. The motion intention was defined as the desired position and velocity, which were continuously estimated according to the human upper-limb model and minimum jerk model, respectively. The motion intention was then fed into a hybrid force and position controller of an upper-limb cable driven rehabilitation robot (CDRR). And a three-dimensional reaching task without predefined trajectory was employed to validate the effectiveness of the proposed control algorithm. Experimental results showed that the control algorithm could continuously recognize the human motion intention and enabled the robot better movement performance indicated as smaller offset error, smoother trajectory, and lower impact. The proposed method could guarantee a natural pHRI and improve the engagement of the subjects, which has great potential in clinical applications.

Cable-driven parallel robots (CDPRs) have become increasingly widely used in rehabilitation training, while the control of cable tension remains a major problem. In this study, we propose a method based on deep reinforcement learning to optimize cable tension distribution in a 3-DOF CDPR, which has one redundant cable and is used for upper-limb rehabilitation. The reference trajectory with an approximately triangular shape and a circumference of around 0.50 m is captured from 3-dimensional human motion, and then the end-effector is allowed to track the trajectory within an error range of ± 0.02 m. The simulation results suggest that the total tension of the four cables and the jerk value of the tracking trajectory both decrease with increasing training time. The proposed method will be validated later by actual experiments on the 3-DOF CDPR.

This paper presents a novel wearable hand exoskeleton (WHE) system with light weight and adjustable character. The mechanical structure of the WHE is based on articulated linkages. The multi-mode signal acquisition module consists of two wearable sensors for detecting the electromyography (EMG) signals and the fingertip force signals. EMG based control is applied to the WHE system. The performance of the WHE system was tested through the free motion task and the grasping object task. Results showed that the WHE could assist hand function in the daily grasping tasks. In the future work, training experiments will be performed on patients.

This paper presents a novel method to model urban land use conversion using support vector machines (SVMs), a new generation of machine learning algorithms used in the classification and regression domains. This method derives the relationship between rural-urban land use change and various factors, such as population, distance to road and facilities, and surrounding land use. Our study showed that SVMs are an effective approach to estimating the land use conversion model, owing to their ability to model non-linear relationships, good generalization performance, and achievement of a global and unique optimum. The rural-urban land use conversions of New Castle County, Delaware between 1984---1992, 1992---1997, and 1997---2002 were used as a case study to demonstrate the applicability of SVMs to urban expansion modeling. The performance of SVMs was also compared with a commonly used binomial logistic regression (BLR) model, and the results, in terms of the overall modeling accuracy and McNamara's test, consistently corroborated the better performance of SVMs.

Modeling land-use change is a prerequisite to understanding the complexity of land-use-change patterns. This paper presents a novel method to model urban land-use change using support-vector machines (SVMs), a new generation of machine learning algorithms used in classification and regression domains. An SVM modeling framework has been developed to analyze land-use change in relation to various factors such as population, distance to roads and facilities, and surrounding land use. As land-use data are generally unbalanced, in the sense that the unchanged data overwhelm the changed data, traditional methods are incapable of classifying relatively minor land-use changes with high accuracy. To circumvent this problem, an unbalanced SVM has been adopted by enhancing the standard SVMs. A case study of Calgary land-use change demonstrates that the unbalanced SVMs can achieve high and reliable performance for land-use-change modeling.

In recent years, there has been a significant shift in the development of a Geographic Information System (CIS) from desktop applications to mobile field applications. By integrating the precision location data collection capability of Global Positioning System (GPS) and the spatial processing power of GIS, mobile GIS provides an ideal basis of building systems for field workers to collect data with increased efficiency and ease. This paper presents the design and implementation of a pavement distress data collection and management system for efficient airport pavement condition inspection with the aid of mobile GIS. The system seeks to streamline the field data collection process by offering a customized user interface for distress data entry, transformation, retrieval, and real-time transmission through wireless handheld devices. An R*-tree algorithm has been explored to index the distress data and speed up the retrieval of distress information when performing spatial and attribute searches. A least squares adjustment algorithm is also introduced in an effort to improve the precision of GPS data. Furthermore, a wireless communication algorithm has been developed to enable the transmission of distress data from the mobile client in the field to the in-house GIS server. On the side of hardware, Pocket PC has been chosen as the platform for deploying all field operations. Three peripheral devices, namely the GPS receiver, digital camera and wireless card, are attached to the Pocket PC for capturing distress location, digital photos and support wireless communication, respectively. The effectiveness and efficiency of the system have been tested and verified by various field trials in Singapore Changi International Airport.