Search results

The purpose of this paper is to design an integrated localization system for mobile robots in underground environments for exploring and rescuing tasks after incidents and detection of hazard gas in tunnels before ingress.

An integrated localization system mainly based on a strap‐down inertial measurement unit and a digital compass is designed for exploring and rescuing task in coal mines and tunnels. After a system model was founded, a filtering algorithm combining a wavelet‐based pre‐filter with unscented Kalman filters was developed for reckoning tracks of robots and localizing it.

Based on this research, an integrated localization system for robots in underground environments can be developed to explore some regions and rescue people. Although errors of localization exist, performance of the integrated system should be improved if some sensors and landmarks or maps of tunnels are introduced.

What is proposed in this paper is an integrated localization system used in underground environments. In this research, property of environments has been taken into account as an important disturbance when filtering thresholds were set.

The purpose of this paper is to present the control methods of the exoskeleton robotic arm for stroke rehabilitation.

The robotic arm is driven by the pneumatic muscle actuators. The control system provides independent control for the robot. The joint axes of the robotic arm are arranged to mimic the natural upper limb workspace.

Findings are the classification of training modes and control methods of rehabilitation training, and the characters of both the instant spasm and the sustaining one.

This paper is a preliminary step in the control system and the kinematical characteristics should be analyzed to achieve high precision of movement.

Based on a hierarchical structure, the control system allows the execution of sequence of switching control methods: position, force, force/position and impedance. Patient‐active‐robot‐passive and patient‐passive‐robot‐active (PPRA) training modes are also presented in this paper. In PPRA mode, the robotic arm can provide pre‐specified resistances on the patient's arm. Both instant and sustaining spasms are taken into account for safety.

The purpose of this paper is to present the static and dynamic characteristics of the rehabilitation joint.

The rehabilitation joint is driven by pneumatic muscle actuators (PMAs). Rehabilitation robot is normally composed of several rehabilitation joints. The static and dynamic characteristics of the rehabilitation joint are important for control of the rehabilitation robot. Analysis and modeling of the rehabilitation joint is based on experiments.

The static model of the PMA is obtained by the method of curve fitting and achieved better precision compared to the existing representative models. A second‐order model fits the dynamic characteristic of the rehabilitation joint better than a first order one.

The rehabilitation joint and the patient's joint combine to make an independent system, and the unstable factors of the patient's joint make it difficult in precisely modeling the rehabilitation joint.

The characteristics of the rehabilitation joint are all based on the data that were recorded in a series of with experiments, the same with modeling of the rehabilitation joint.

The benefits of artificial intelligence (AI) related technologies for manufacturing firms are well recognized, however, there is a lack of industrial AI (I-AI) maturity models to enable companies to understand where they are and plan where they should go. The purpose of this study is to propose a comprehensive maturity model in order to help manufacturing firms assess their performance in the I-AI journey, shed lights on future improvement, and eventually realize their smart manufacturing visions.

This study is based on (1) a systematic review of literature on assessing I-AI-related technologies to identify relevant measured indicators in the maturity model, and (2) semi-structured interviews with domain experts to determine maturity levels of the established model.

The I-AI maturity model developed in this study includes two main dimensions, namely “Industry” and “Artificial Intelligence”, together with 12 first-level indicators and 35 second-level indicators under these dimensions. The maturity levels are divided into five types: planning level, specification level, integration level, optimization level, and leading level.

The maturity model integrates indicators that can be used to assess AI-related technologies and extend the existing maturity models of smart manufacturing by adding specific technical and nontechnical capabilities of these technologies applied in the industrial context. The integration of the industry and artificial intelligence dimensions with the maturity levels shows a road map to improve the capability of applying AI-related technologies throughout the product lifecycle for achieving smart manufacturing.