Parallel and scalable custom computing for real-time fluid simulation on a cluster node with four tightly-coupled FPGAs

In mechanical engineering educations, simulating fluid thermodynamics is rather helpful for students to understand the fluid’s natural behaviors. However, rendering both high-quality and realtime simulations for fluid dynamics are rather challenging tasks due to their intensive computations. So, in order to speed up the simulations, we have taken advantage of GPU acceleration techniques to simulate interactive fluid thermodynamics in real-time. In this paper, we present an elegant, basic, but practical OpenGL/SL framework for fluid simulation with a heat map rendering. By solving Navier-Stokes equations coupled with the heat diffusion equation, we validate our framework through some real-case studies of the smoke-like fluid rendering such as their interactions with moving obstacles and their heat diffusion effects. As shown in Fig. 1, a group of experimental results demonstrates that our GPU-accelerated solver of Navier-Stokes equations with heat transfer could give the observers impressive real-time and realistic rendering results.

Download Full-text

Approaches to design of temporary blackout handling capabilities and an evaluation with a real-time tightly coupled network testbed

[1991] Digest of Papers. Fault-Tolerant Computing: The Twenty-First International Symposium ◽

10.1109/ftcs.1991.146703 ◽

2002 ◽

Author(s):

K.H. Kim ◽

W.J. Guan ◽

A. Damm ◽

J.A. Rohr

Keyword(s):

Real Time ◽

Tightly Coupled

Download Full-text

Concurrency Control in Real-Time E-Collaboration Systems

E-Collaboration ◽

10.4018/978-1-60566-652-5.ch019 ◽

2009 ◽

pp. 211-218

Author(s):

Wenbing Zhao

Keyword(s):

User Interface ◽

System Design ◽

Real Time ◽

Graphical User Interface ◽

Concurrency Control ◽

Wide Area ◽

Wide Area Networks ◽

System State ◽

Decentralized System ◽

Tightly Coupled

For all e-collaboration systems, some degree of concurrency control is needed so that two people do not step on each other’s foot. The demand for good concurrency control is especially high for the tightly coupled, real-time e-collaboration systems. Such systems require quick responses to user’s actions, and typically require a WYSIWIS (what you see is what I see) graphical user interface (Ellis, Gibbs, & Rein, 1991). This requirement, together with the fact that users are often separated geographically across wide-area networks, favors a decentralized system design where the system state is replicated at each user’s site. This places further challenges on the design of concurrency control for these systems.

Download Full-text

Two-Way Real Time Fluid Simulation Using a Heterogeneous Multicore CPU and GPU Architecture

2011 IEEE Workshop on Principles of Advanced and Distributed Simulation ◽

10.1109/pads.2011.5936750 ◽

2011 ◽

Author(s):

Jose Ricardo da S. Junior ◽

Esteban Clua ◽

Anselmo Montenegro ◽

Marcos Lage ◽

Cristina Vasconcellos ◽

...

Keyword(s):

Real Time ◽

Fluid Simulation ◽

Heterogeneous Multicore ◽

Multicore Cpu ◽

Gpu Architecture

Download Full-text

Enabling robust and accurate navigation for UAVs using real-time GNSS precise point positioning and IMU integration

The Aeronautical Journal ◽

10.1017/aer.2020.80 ◽

2020 ◽

Vol 125 (1283) ◽

pp. 87-108

Author(s):

C. Chi ◽

X. Zhan ◽

S. Wang ◽

Y. Zhai

Keyword(s):

Real Time ◽

Precise Point Positioning ◽

Three Dimensional ◽

Coupled System ◽

Measurement Unit ◽

Satellite Geometry ◽

Tightly Coupled ◽

Point Positioning ◽

Gnss Measurements ◽

The One

ABSTRACTAccurate navigation is required in many Unmanned Aerial Vehicle (UAV) applications. In recent years, GNSS Precise Point Positioning (PPP) has been recognised as an efficient approach for providing precise positioning services. In contrast to the widely used Real-Time Kinematic (RTK), PPP is independent of reference stations, which greatly broadens its scope of application. However, the accuracy and reliability of PPP can be significantly decreased by poor GNSS satellite geometry and outage. In response, a real-time four-constellation GNSS PPP is applied to improve the geometry in this work, and PPP is tightly coupled with an Inertial Measurement Unit (IMU) to smooth the position and velocity output, thus improving the robustness of the navigation solution. Experimental flight tests are carried out using a UAV in an open-sky area, and GNSS-challenged environments are simulated. The results show that the four-constellation GNSS PPP/IMU integration reduces the Root-Mean-Square (RMS) Three-Dimensional (3D) positioning and velocity error by 76.4% and 67.1%, respectively, in open sky with respect to the one-GNSS PPP. Under scenarios where GNSS measurements are insufficient, the coupled system can still provide continuous solutions. Moreover, the coupled PPP/IMU system can also maintain the convergence of PPP during GNSS-challenged periods and can greatly shorten the re-convergence period of PPP when the UAV returns to the open sky.

Download Full-text

Visual-Inertial Odometry of Smartphone under Manhattan World

Remote Sensing ◽

10.3390/rs12223818 ◽

2020 ◽

Vol 12 (22) ◽

pp. 3818

Author(s):

YuAn Wang ◽

Liang Chen ◽

Peng Wei ◽

XiangChen Lu

Keyword(s):

Mobile Phone ◽

Structural Feature ◽

Real Time ◽

Structural Features ◽

Feature Extraction Method ◽

The Public ◽

Window Method ◽

Tightly Coupled ◽

Sliding Window Method ◽

Public Datasets

Based on the hypothesis of the Manhattan world, we propose a tightly-coupled monocular visual-inertial odometry (VIO) system that combines structural features with point features and can run on a mobile phone in real-time. The back-end optimization is based on the sliding window method to improve computing efficiency. As the Manhattan world is abundant in the man-made environment, this regular world can use structural features to encode the orthogonality and parallelism concealed in the building to eliminate the accumulated rotation error. We define a structural feature as an orthogonal basis composed of three orthogonal vanishing points in the Manhattan world. Meanwhile, to extract structural features in real-time on the mobile phone, we propose a fast structural feature extraction method based on the known vertical dominant direction. Our experiments on the public datasets and self-collected dataset show that our system is superior to most existing open-source systems, especially in the situations where the images are texture-less, dark, and blurry.

Download Full-text