scholarly journals A Low-Cost Model Vehicle Testbed with Accurate Positioning for Autonomous Driving

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Benjamin Vedder ◽  
Jonny Vinter ◽  
Magnus Jonsson

Accurate positioning is a requirement for many applications, including safety-critical autonomous vehicles. To reduce cost and at the same time improving accuracy for positioning of autonomous vehicles, new methods, tools, and research platforms are needed. We have created a low-cost testbed consisting of electronics and software that can be fitted on model vehicles allowing them to follow trajectories autonomously with a position accuracy of around 3 cm outdoors. The position of the vehicles is derived from sensor fusion between Real-Time Kinematic Satellite Navigation (RTK-SN), odometry, and inertial measurement and performs well within a 10 km radius from a base station. Trajectories to be followed can be edited with a custom GUI, where also several model vehicles can be controlled and visualized in real time. All software and Printed Circuit Boards (PCBs) for our testbed are available as open source to make customization and development possible. Our testbed can be used for research within autonomous driving, for carrying test equipment, and other applications where low cost and accurate positioning and navigation are required.

2021 ◽  
Vol 11 (16) ◽  
pp. 7225
Author(s):  
Eugenio Tramacere ◽  
Sara Luciani ◽  
Stefano Feraco ◽  
Angelo Bonfitto ◽  
Nicola Amati

Self-driving vehicles have experienced an increase in research interest in the last decades. Nevertheless, fully autonomous vehicles are still far from being a common means of transport. This paper presents the design and experimental validation of a processor-in-the-loop (PIL) architecture for an autonomous sports car. The considered vehicle is an all-wheel drive full-electric single-seater prototype. The retained PIL architecture includes all the modules required for autonomous driving at system level: environment perception, trajectory planning, and control. Specifically, the perception pipeline exploits obstacle detection algorithms based on Artificial Intelligence (AI), and the trajectory planning is based on a modified Rapidly-exploring Random Tree (RRT) algorithm based on Dubins curves, while the vehicle is controlled via a Model Predictive Control (MPC) strategy. The considered PIL layout is implemented firstly using a low-cost card-sized computer for fast code verification purposes. Furthermore, the proposed PIL architecture is compared in terms of performance to an alternative PIL using high-performance real-time target computing machine. Both PIL architectures exploit User Datagram Protocol (UDP) protocol to properly communicate with a personal computer. The latter PIL architecture is validated in real-time using experimental data. Moreover, they are also validated with respect to the general autonomous pipeline that runs in parallel on the personal computer during numerical simulation.


2020 ◽  
Vol 13 (1) ◽  
pp. 89
Author(s):  
Manuel Carranza-García ◽  
Jesús Torres-Mateo ◽  
Pedro Lara-Benítez ◽  
Jorge García-Gutiérrez

Object detection using remote sensing data is a key task of the perception systems of self-driving vehicles. While many generic deep learning architectures have been proposed for this problem, there is little guidance on their suitability when using them in a particular scenario such as autonomous driving. In this work, we aim to assess the performance of existing 2D detection systems on a multi-class problem (vehicles, pedestrians, and cyclists) with images obtained from the on-board camera sensors of a car. We evaluate several one-stage (RetinaNet, FCOS, and YOLOv3) and two-stage (Faster R-CNN) deep learning meta-architectures under different image resolutions and feature extractors (ResNet, ResNeXt, Res2Net, DarkNet, and MobileNet). These models are trained using transfer learning and compared in terms of both precision and efficiency, with special attention to the real-time requirements of this context. For the experimental study, we use the Waymo Open Dataset, which is the largest existing benchmark. Despite the rising popularity of one-stage detectors, our findings show that two-stage detectors still provide the most robust performance. Faster R-CNN models outperform one-stage detectors in accuracy, being also more reliable in the detection of minority classes. Faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff but needs lower resolution images to reach real-time speed. Furthermore, the anchor-free FCOS detector is a slightly faster alternative to RetinaNet, with similar precision and lower memory usage.


2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Benjamin Vedder ◽  
Bo Joel Svensson ◽  
Jonny Vinter ◽  
Magnus Jonsson

Autonomous vehicles need accurate and dependable positioning, and these systems need to be tested extensively. We have evaluated positioning based on ultrawideband (UWB) ranging with our self-driving model car using a highly automated approach. Random drivable trajectories were generated, while the UWB position was compared against the Real-Time Kinematic Satellite Navigation (RTK-SN) positioning system which our model car also is equipped with. Fault injection was used to study the fault tolerance of the UWB positioning system. Addressed challenges are automatically generating test cases for real-time hardware, restoring the state between tests, and maintaining safety by preventing collisions. We were able to automatically generate and carry out hundreds of experiments on the model car in real time and rerun them consistently with and without fault injection enabled. Thereby, we demonstrate one novel approach to perform automated testing on complex real-time hardware.


2019 ◽  
Vol 72 (04) ◽  
pp. 917-930
Author(s):  
Fang-Shii Ning ◽  
Xiaolin Meng ◽  
Yi-Ting Wang

Connected and Autonomous Vehicles (CAVs) have been researched extensively for solving traffic issues and for realising the concept of an intelligent transport system. A well-developed positioning system is critical for CAVs to achieve these aims. The system should provide high accuracy, mobility, continuity, flexibility and scalability. However, high-performance equipment is too expensive for the commercial use of CAVs; therefore, the use of a low-cost Global Navigation Satellite System (GNSS) receiver to achieve real-time, high-accuracy and ubiquitous positioning performance will be a future trend. This research used RTKLIB software to develop a low-cost GNSS receiver positioning system and assessed the developed positioning system according to the requirements of CAV applications. Kinematic tests were conducted to evaluate the positioning performance of the low-cost receiver in a CAV driving environment based on the accuracy requirements of CAVs. The results showed that the low-cost receiver satisfied the “Where in Lane” accuracy level (0·5 m) and achieved a similar positioning performance in rural, interurban, urban and motorway areas.


Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1956
Author(s):  
Natalia Wielgocka ◽  
Tomasz Hadas ◽  
Adrian Kaczmarek ◽  
Grzegorz Marut

Global Navigation Satellite Systems (GNSS) have revolutionized land surveying, by determining position coordinates with centimeter-level accuracy in real-time or up to sub-millimeter accuracy in post-processing solutions. Although low-cost single-frequency receivers do not meet the accuracy requirements of many surveying applications, multi-frequency hardware is expected to overcome the major issues. Therefore, this paper is aimed at investigating the performance of a u-blox ZED-F9P receiver, connected to a u-blox ANN-MB-00-00 antenna, during multiple field experiments. Satisfactory signal acquisition was noticed but it resulted as >7 dB Hz weaker than with a geodetic-grade receiver, especially for low-elevation mask signals. In the static mode, the ambiguity fixing rate reaches 80%, and a horizontal accuracy of few centimeters was achieved during an hour-long session. Similar accuracy was achieved with the Precise Point Positioning (PPP) if a session is extended to at least 2.5 h. Real-Time Kinematic (RTK) and Network RTK measurements achieved a horizontal accuracy better than 5 cm and a sub-decimeter vertical accuracy. If a base station constituted by a low-cost receiver is used, the horizontal accuracy degrades by a factor of two and such a setup may lead to an inaccurate height determination under dynamic surveying conditions, e.g., rotating antenna of the mobile receiver.


2020 ◽  
Author(s):  
Robert Winkler

<div>Air, water, and soil are essential for terrestrial life, but pollution, overexploitation, and climate change jeopardize the availability of these primary resources. Thus, assuring human health and food production requires efficient strategies and technologies for environmental protection. Knowing key parameters such as soil moisture, air, and water quality is essential for smart farming and urban development. </div><div>The MeteoMex project aims to build simple hardware kits and their integration into current Internet-of-Things (IoT) platforms. This paper shows the use of low-end Wemos D1 mini boards to connect environmental sensors to the open-source platform ThingsBoard. Two printed circuit boards (PCB) were designed for mounting components. Analog, digital and I<sup>2</sup>C sensors are supported. The Wemos ESP8266 microchip provides WiFi capability and can be programmed with the Arduino IDE. Application examples for the MeteoMex aeria and terra kits demonstrate their functionality for air quality, soil, and climate monitoring.</div><div>Further, a prototype for monitoring wastewater treatment is shown, which exemplifies the capabilities of the Wemos board for signal processing. The data are stored in a PostgreSQL database, which enables data mining. The MeteoMex IoT system is highly scalable and of low cost, which makes it suitable for deployment in agriculture 4.0, industries, and public areas. </div><div>Circuit drawings, PCB layouts, and code examples are free to download from https://github.com/robert-winkler/MeteoMex.</div>


2010 ◽  
Vol 7 (2) ◽  
pp. 32 ◽  
Author(s):  
L. Khriji ◽  
F. Touati ◽  
N. Hamza

 Nowadays, there is a significant improvement in technology regarding healthcare. Real-time monitoring systems improve the quality of life of patients as well as the performance of hospitals and healthcare centers. In this paper, we present an implementation of a designed framework of a telemetry system using ZigBee technology for automatic and real-time monitoring of Biomedical signals. These signals are collected and processed using 2-tiered subsystems. The first subsystem is the mobile device which is carried on the body and runs a number of biosensors. The second subsystem performs further processing by a local base station using the raw data which is transmitted on-request by the mobile device. The processed data as well as its analysis are then continuously monitored and diagnosed through a human-machine interface. The system should possess low power consumption, low cost and advanced configuration possibilities. This paper accelerates the digital convergence age through continual research and development of technologies related to healthcare. 


2011 ◽  
Vol 2011 (DPC) ◽  
pp. 001918-001948
Author(s):  
Catherine Bunel ◽  
Stephane Bellenger ◽  
Sebastien Leruez ◽  
Lionel Lenoir ◽  
Franck Murray

Thanks to their 3D structure, the Silicon Capacitors offer drastic improvements in terms of performances compared to the commonly used ceramic and tantalum capacitors. They are also a smart way to reduce the application volume and increase the IP protection level. With the increasing complexity in the die and package designs and ever increasing cost pressure in today's microelectronic industry, IPDIA is offering for a large range of products, customized or standard components, a low cost packaging solution: the Wafer Level Chip Scale Packaging. While wire-bond interface may remain the preference for many applications, face-down direct chip attachment has gained wide acceptance. More than interacting on electrical functionality, WLCSP is interacting on mechanical and thermo mechanical properties with a higher miniaturization and a transfer directly on printed circuit boards without additional packaging steps. This paper presents the main characteristics of the 3D-IPD advanced technology emphasizing on its capability and advantages versus discrete components illustrated by different applications using ultra-thin IPD ( down to 60 μm ) and WLCSP.


Author(s):  
Kang-Sun Choi ◽  
Jae-Young Pyun ◽  
Nam-Hyeong Kim ◽  
Byeong-Doo Choi ◽  
Sung-Jea Ko

2017 ◽  
Vol 56 (2) ◽  
pp. 026108
Author(s):  
Jau-Ji Jou ◽  
Tien-Tsorng Shih ◽  
Cheng-Ying Wu ◽  
Zhe-Xian Su

Sign in / Sign up

Export Citation Format

Share Document