A parallel implementation of a multisensor feature-based range-estimation method

Template matching in real-time is a fundamental issue in many applications in computer vision such as tracking, stereo vision and autonomous navigation. The goal of this paper is to present a system for automatic image sequence processing for autonomous aerial navigation research. Two main experiments were employed in this work, the first with clipping images of a geo-referenced aerial image, to simulate the unmanned aerial vehicle (UAV) navigation, and the second employing the video frames obtained from a camera fixed to a helicopter in a low level flight, simulating the vision system of an UAV. The image features used in recognition task were obtained by the SIFT algorithm. The recognition system consists on a video frame processing to estimate the UAV displacement. Promising results were obtained.

Efficient solid state NMR powder simulations using SMP and MPP parallel computation

The Global Navigation Satellite Systems (GNSS) such as Global Positioning System (GPS) are the prime land and autonomous vehicles navigation information source. However, urban canyons high rise buildings block the GPS signal. Therefore, the Inertial Navigation System (INS) or the Reduced Inertial Sensor System (RISS) are utilized as an alternative source of the navigation information. The RISS is able to produce a full navigation solution using less number of sensors and calculations. Dramatically, the RISS solution drifts over time as the INS system. The integration between the GPS and the RISS is mitigating each system drawbacks. However, during the GPS outage periods, the navigation system is only depending on the inertial measurements. The RISS is utilizing the odometer/speedometer to measure the vehicle's forward speed. Many types of error affect the odometer measurements. These errors are either due to the vehicle's specifications as the differences in wheel diameters, and/or inefficient wheelbase or the road nature as wheel slips, uneven road surfaces, and/or skidding. In this paper, a Radar-based RISS system is introduced to take place the traditional RISS or INS systems. The radar unit is an essential part of the adaptive cruise control (ACC) system. Furthermore, it is capable of measuring the relative velocity and distance between the carrying and the in front vehicle to reduce collisions and increase the safety of driving. In addition, the radar measurements are not affected by the error sources that affect the odometer. The idea is to invest the ground reflection and derive the forward speed of the onboard vehicle as the ACC keep a safe distance between the cars. A novel method based on extracting the ground reflection features is introduced to obtain the onboard vehicle's speed. The obtained speed is utilized with two accelerometers and one vertical gyroscope to produce the Radar-based RISS system. The proposed system has been integrated with the GPS producing a Radar-based RISS/GPS integrated navigation system. The system has been tested on a real road trajectory in a downtown area and involved several GPS signal outages. The results show the significant capabilities of the proposed system in keeping the navigation solution drift to a minimum especially when the GPS signal is in outage compared with the traditional RISS/GPS system.

In this paper we consider the problem related to the autonomous navigation of a robotic vehicle by modeling and describing the semantics of the context associated to the navigation. Considering the semantical modelling of the navigation context, as obstacles, pedestrians, roundabouts, information on the vehicle itself (load, power, etc.), on the robotic vehicle, it is integrating to add this symbolic artificial intelligence to a classical navigation control scheme. This semantic modeling generates an additional degree of abstraction by "reasoning" about the information collected by the various sensors of the autonomous vehicle in order to build a navigation context. This navigation context is able to provide decision support for the autonomous or semi-autonomous vehicle (interaction to the driver). In this paper, we present a project developed at Université de Technologie de Compiègne, Laboratory Heudiasyc (Heuristics, Diagnosis and Complex Systems), in France, showing initial modeling results by defining and selecting the relevant information in the creation of a context for the vehicle, structuring the contextual information so as to be able to reasoning on it and thus dynamically update the context in which the vehicle operates; maintaining information by choosing suitable data persistence models in order to be able to query previous simulations efficiently.

Currently, there are two approaches to implementing large-scale ice sheet simulations. One approach, which is based on the use of an evenly-spaced structured grid, is to simulate the entire ice sheet at the highest resolution required. The other approach is to model the ice sheet at different levels of resolution using unstructured meshes. Structured grids lend themselves quite well to partitioning on multi-core, distributed memory parallel computers, leading to good computational efficiency, load-balancing and reduced communication costs. The disadvantage is the significant computational resources required to model a system of this size at a high enough resolution to correctly model regions of the ice sheet undergoing rapid change. Unstructured meshes can reduce such costs by allocating more computational resources to areas of the ice sheet whose dynamics are evolving quickly and fewer resources to areas evolving more slowly. However, unstructured meshes do not easily lend themselves to effective decomposition on distributed memory parallel computers, and can experience poor cache utilization, significant load imbalance, high communication costs, and increased synchronization times. In this paper, we describe our alternative approach based on embedded simulation, which provides a degree of multi-resolution capabilities to structured grids while maintaining many of the computational efficiencies that come with the structured approach. We provide experimental results focusing on the scalability characteristics and cache efficiency of each approach as a function of increasing problem size and core counts. We show that the embedded approach scales very well across all problem sizes and core counts, and that the unstructured approach scales well at smaller problem sizes and core counts but degrades significantly as the problem size becomes large.

This paper presents the design and development of a mecanum wheel-based Automated Guided Vehicle (AGV), serving as a test platform for autonomous system research. The study highlights the essential elements of an Automated Guided Vehicle (AGV) and provides a thorough review of the literature. It explores the information, electrical, and mechanical actuator systems critical to the AGV's functioning. The AGV's navigation system is powered by a Jetson Nano minicomputer, with high-level software development implemented using the Robot Operating System (ROS). The software design focuses on modularity because it facilitates easier changes and maintenance, which is essential for research and rapid testing. The DC motors control subsystem controls AGV mobility by adjusting wheel speed and direction. These motors have incremental encoders that indicate wheel rotation. The Jetson Nano is used in the framework to process data from various sensors and monitor the AGV's performance. Experimental validation was carried out in both static and dynamic environments, where the AGV successfully executed autonomous navigation tasks with an average localization error, motion time, and path deviation. These results demonstrate the system's reliability, accuracy, and potential as a flexible test platform for developing and benchmarking autonomous navigation algorithms in research and educational contexts.

The complex nature of the ocean environment requires advanced computational acoustic models to gain insights into the dominating physical factors controlling the underwater sound propagation and scattering in the ocean. In this study, we explore the “ab-initio” approach to solve wave equations with numerical algorithms that can be implemented in distributed memory parallel computers. The goal is to improve the calculation speed so long-range global scale hydroacoustic wave propagation can be studied more efficiently and effectively. Two major algorithms: the finite difference time domain (FDTD) method and the Parabolic Equation (PE) method are investigated. Two PE-based numerical models are considered. One is the Split-Step-Fourier Parabolic Equation (SSFPE) model using split-step Fourier schemes in three-dimensional (3D) environments. The second PE model is a multi-frequency implementation of the Range-dependent Acoustic Model (RAM) that computes two-dimensional (2D) sound pressure fields. One of the primary challenges in global-scale hydroacoustic propagation modeling with the “ab-initio” approach is the demand for significant computational resources on both memories and computational speeds. To address this, we employed parallel computing techniques using directive-based programming languages, such as OpenACC and XscalableACC, to leverage the power of multiple Graphics Processing Unit (GPU) systems and Central Processing Unit (CPU) cluster computers. Our performance evaluation revealed substantial speedup gains. For the FDTD method, we achieved approximately 3.5-fold and 4-fold speedups with four GPUs and four CPU cluster nodes, respectively. With the 3D SSFPE model, we obtained a speedup of 3.7-fold using four CPU cluster nodes. A significant result was observed with the 2D broadband multi-frequency RAM model, where we achieved a 110-fold speedup compared to one core original implementation. These results demonstrate the promising potential of massively parallel computers for ocean acoustic propagation modeling and highlight the significant performance benefits of utilizing parallel computing techniques. Our findings emphasize the importance of efficient computational strategies.

Ray tracing is a well known technique to generate life-like images. Unfortunately, ray tracing complex scenes can require large amounts of CPU time and memory storage. Distributed memory parallel computers with large memory capacities and high processing speeds are ideal candidates to perform ray tracing. However, the computational cost of rendering pixels and patterns of data access cannot be predicted until runtime. To parallelize such an application efficiently on distributed memory parallel computers, the issues of database distribution, dynamic data management and dynamic load balancing must be addressed. In this paper, we present a parallel implementation of a ray tracing algorithm on the Intel Delta parallel computer. In our database distribution, a small fraction of database is duplicated on each processor, while the remaining part is evenly distributed among groups of processors. In the system, there are multiple copies of the entire database in the memory of groups of processors. Dynamic data management is acheived by an ALRU cache scheme which can exploit image coherence to reduce data movements in ray tracing consecutive pixels. We balance load among processors by distributing subimages to processors in a global fashion based on previous workload requests. The success of our implementation depends crucially on a number of parameters which are experimentally evaluated. © 1997 John Wiley & Sons, Ltd.

We present fast and highly scalable parallel computations for a number of important and fundamental matrix problems on distributed memory systems (DMS). These problems include matrix multiplication, matrix chain product, and computing the powers, the inverse, the characteristic polynomial, the determinant, the rank, the Krylov matrix, and an LU- and a QR-factorization of a matrix, and solving linear systems of equations. Our highly scalable parallel computations for these problems are based on a highly scalable implementation of the fastest sequential matrix multiplication algorithm on DMS. We show that compared with the best known parallel time complexities on parallel random access machines (PRAM), the most powerful but unrealistic shared memory model of parallel computing, our parallel matrix computations achieve the same speeds on distributed memory parallel computers (DMPC), and have an extra polylog factor in the time complexities on DMS with hypercubic networks. Furthermore, our parallel matrix computations are fully scalable on DMPC and highly scalable over a wide range of system size on DMS with hypercubic networks. Such fast (in terms of parallel time complexity) and highly scalable (in terms of our definition of scalability) parallel matrix computations were rarely seen before on any distributed memory systems.

We present fast and scalable parallel computations for a number of important and fundamental matrix problems on distributed memory systems (DMS). These problems include computing the powers, the inverse, the characteristic polynomial, the determinant, the rank, the Krylov matrix, and an LU- and a QR-factorization of a matrix, and solving linear systems of equations. These parallel computations are based on efficient implementations of the fastest sequential matrix multiplication algorithm on DMS. We show that compared with the best known time complexities on PRAM, our parallel matrix computations achieve the same speeds on distributed memory parallel computers (DMPC), and have an extra polylog factor in the time complexities on DMS with hypercubic networks. Furthermore, our parallel matrix computations are fully scalable on DMPC and highly scalable over a wide range of system size on DMS with hypercubic networks. Such fast and scalable parallel matrix computations were not seen before on any distributed memory systems.

The aim of this paper is to explore the possibility of using geo-referenced aerial images to augment an Unmanned Aerial Vehicle (UAV) navigation system in case of GPS failure. The proposed method is based on image matching between the current view from a monocular video camera and a previously known database of geo-referenced images. Only natural landmarks provided by a feature tracking algorithm will be considered, without the help of visual beacons or artificial landmarks. The novel idea is to perform global localization, position tracking, localization failure recovery and safe landing. Key points of current video frame and reference database are extracted by implementing Speeded-Up Robust Features (SURF) algorithm on a NVIDIA Geforce 240M graphics processing unit (GPU). The proposed system has been tested on real flight data and testing results confirmed that the proposed system is real-time and sufficiently robust to scale, rotation, illumination, noise and affine projection, thus it can be an ideal scheme for autonomous navigation system for UAVs under GPS blockage conditions.

The scalability of distributed-memory parallel computers makes them attractive candidates for solving large-scale problems. New languages, such as HPF, FortranD, and VPP Fortran, have been developed to enable existing software to be easily ported to such machines. Many distributed-memory parallel computers have been built, but none of them support the mechanisms required by such languages. We studied the mechanisms required by parallelizing compilers and proposed a new architecture to support them. Based on this proposed architecture, we developed a new distributed-memory parallel computer, the AP1000+, which is an enhanced version of the AP1000. Using scientific applications in VPP Fortran and C, such as NAS parallel benchmarks, we simulated the performance of the AP1000+.

An efficient parallel-computing method for modeling nonisothermal multiphase flow and multicomponent transport in porous and fractured media

Developing SPMD applications with load balancing

Summary This paper presents new methods for estimating the axle weight of a moving vehicle, using two piezoelectric sensors and adaptive-footprint tire model. It is more difficult to weigh vehicles in motion accurately than to weigh standing vehicles. The difficulties in weighing moving vehicles result from sensor limitations as well as dynamic loading effects induced by vehicle/pavement interactions. For example, two identical vehicles with the same weight will generate sensor signals that differ in the shape and the peak value, depending the tire pressure, vehicle speed, road roughness, and sensor characteristics. This paper develops a method that is much less sensitive to these variable factors in determining the axle weight of a moving vehicle. In the developed method, first the piezoelectric sensor signal is reconstructed using the inverse dynamics of a high-pass filter representing the piezoelectric sensor. Then, the reconstructed signal, is normalized, using the nominal road/tire contact length obtained using an adaptive-footprint tire model, and then integrated. Experiments are performed with 3 vehicles of known weight ranging from 1,400 kg to 28,040 kg. The developed method is compared to two other algorithms. Results show that the developed method is most consistent and accurate.