Graphics processing unit (GPU) programming environments have matured for general-purpose computing on GPUs. Significant challenges for GPUs include system software support for bounded response times and guaranteed throughput. In recent years, GPU technologies have been applied to real-time systems by extending the operating system modules to support real-time GPU resource management. Unfortunately, such a system extension makes it difficult to maintain the system with version updates because the OS kernel and device drivers must be modified at the source-code level, thereby preventing continuous research and development of GPU technologies for real-time systems. A loadable kernel module (LKM) framework, called Linux Real-Time eXtention with GPUs (Linux-RTXG), for managing real-time GPU resources with Linux without modifying the OS kernel and device drivers is proposed and evaluated experimentally. Linux-RTXG provides mechanisms for interrupt interception and independent synchronization to achieve real-time scheduling and resource reservation capabilities for GPU applications on top of existing device drivers and runtime libraries. Experimental results demonstrate that the overhead incurred by introducing the proposed Linux-RTXG is comparable to that of introducing existing kernel-dependent approaches. In addition, the results demonstrate that multiple GPU applications can be scheduled successfully by Linux-RTXG to meet their priority and quality-of-service requirements in real time.

This paper addresses a dynamic model and a control method of a space robot with a rigid manipulator and a flexible appendage. The control method has been developed for performing multiple tasks: end-point motion control and vibration suppression control of a flexible appendage. A simple dynamic model that considers coupling between the manipulator and the flexible appendage is proposed for the control method. The tasks are performed simultaneously on the basis of their order of priorities using a redundant manipulator. Additionally, because vibration suppression requires feedback of the state of the flexible appendage, a state estimator of the appendage using a force/torque sensor is developed. Finally, the proposed model, control method, and state estimator were verified experimentally using an air-floating system.

Graphics processing units (GPUs) embrace many-core compute devices where massively parallel compute threads are offloaded from CPUs. This heterogeneous nature of GPU computing raises non-trivial data transfer problems especially against latency-critical real-time systems. However even the basic characteristics of data transfers associated with GPU computing are not well studied in the literature. In this paper, we investigate and characterize currently-achievable data transfer methods of cutting-edge GPU technology. We implement these methods using open-source software to compare their performance and latency for real-world systems. Our experimental results show that the hardware-assisted direct memory access (DMA) and the I/O read-and-write access methods are usually the most effective, while on-chip micro controllers inside the GPU are useful in terms of reducing the data transfer latency for concurrent multiple data streams. We also disclose that CPU priorities can protect the performance of GPU data transfers.

This paper discusses a vibration suppression control method for a space robot with a rigid manipulator and flexible appendage. A suitable dynamic model that considers the coupling between the manipulator and flexible appendage was developed for the controller to accomplish the vibration suppression control of the flexible appendage. The flexible appendage was modeled using a virtual joint model, and the control method was developed on the basis of this model. Although this type of control requires feedback of the flexible appendage state, its direct measurement is generally difficult. Thus, an estimator of the flexible appendage state was constructed using a force/torque sensor attached between the base and flexible appendage. The control method was experimentally verified using an air-floating system.

Intraoral radiography is one of the most important techniques for dentists, which is commonly used to diagnose dental caries and gum disease. An intraoral radiograph shows a perspective projection image of the teeth of patient, so that the roentgenogram is affected by the positional relationship between film, teeth, and indicator cone which directs X-ray radiation toward the film. In order to administer intraoral radiography for a patient, he/she has to have a small X-ray film inserted in their oral cavity. The position and orientation of the film are properly adjusted by the dentist or radiologic technician. And then, the indicator cone is positioned outside the patient's mouth, and its orientation is determined depending on the teeth and film. Recently, it has been reported that the skill of intraoral radiography of dental students and interns are declining in Japan. The background of this issue is that the conventional training method needs to use an actual X-ray machine and lots of film, and much time to develop the roentgenogram. We assumed that these training inefficiencies would be improved by using virtual reality technique. In this paper, we propose a training simulator for intraoral radiography based on virtual reality, where the trainees quickly obtain a graphical image of intraoral radiograph on a computer display after the setting of film and indicator cone is finished. This paper presents a simulation algorithm for generating a graphical image of intraoral radiograph, and discusses about optimum design of an indicator cone positioning device for the simulator. Simulation results show that the proposed simulation algorithm provides realistic observations of intraoral radiograph