Geomatics Multi-Sensor Systems

地理信息多传感器系统

• 批准号: CRC-2021-00268
• 负责人: ELSHEIMY, NASER
• 金额: $ 7.29万
• 依托单位: University of Calgary
• 依托单位国家: 加拿大
• 项目类别: Canada Research Chairs
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=755069
• 关键词: Geomatics; Multi; Sensor; Systems

During the past decade, the use of Autonomous Vehicles Systems (AVS) has experienced continued growth across military and governmental agencies, industry, and academia. Among these AVS, Self-Driving Vehicles "SDV" and Unmanned Aerial Vehicles "UAV" have drawn the most comprehensive attention from many users.The trust of AVS hinges on the reliability of the autonomy including the crucial task of Positioning, Location And Navigation (PLAN) of such vehicles. AVS typically rely on satellite-based Global Navigation Satellite Systems (GNSS), such as GPS, as the core positioning technology. However, the performance of GNSS greatly suffers in degraded environments such as signal blockage, multipath and signal jamming and as a result navigation of current AVS relies more heavily on digital maps and remote sensing sensors (e.g. laser detection and ranging (LiDAR), Cameras, RADAR) to perceive the environment. However, these sensors also suffer in degraded environmental conditions such as low-visibility, rain, and fog. A third category are self-contained/environment-independent navigation sensors such as Inertial Navigation Systems (INS) which measure the motion dynamics using accelerometers and gyroscopes. These sensors can provide PLAN everywhere at a very high rate independent of weather conditions or external signals or infrastructure. However, their performance degrades with time in the absence of updates from external sources. As such, current PLAN techniques for AVS all have advantages and drawbacks; there is no single technique that appears to be sufficiently versatile to address the challenges mentioned above.The CRC research program will advance the development of technologies and processing platforms that enable the deployment of novel PLAN systems operating efficiently in all environments and specifically in degraded environments conditions such as GNSS Signal blockage, darkness, absence of visual features/landmarks, smoke, fog and rain. This will be achieved through multi-sensor fusion of all available sensors to provide continuous and robust positioning anywhere and in all environments and machine intelligence algorithms to manage and coordinate the heterogeneous set of sensors/systems into a robust positioning system to meet the demand for safety-critical autonomous navigation. From autonomy perspective, the chair work is expected to have a large impact on the acceptance and trust of AVS as it will increase its reliability.

在过去的十年中，自动驾驶车辆系统（AVS）的使用在军事和政府机构、工业和学术界持续增长。其中，无人驾驶汽车（SDV）和无人驾驶飞行器（UAV）受到了众多用户最全面的关注。自动驾驶系统的信任取决于自动驾驶的可靠性，包括车辆的关键任务定位、定位和导航（PLAN）。AVS通常以GPS等基于卫星的全球导航卫星系统（GNSS）为核心定位技术。然而，在信号阻塞、多径和信号干扰等退化环境中，GNSS的性能会受到很大影响，因此当前AVS的导航更多地依赖于数字地图和遥感传感器（如激光探测和测距（LiDAR）、相机、雷达）来感知环境。然而，这些传感器在低能见度、雨和雾等恶劣环境条件下也会受到影响。第三类是自包含/独立于环境的导航传感器，如惯性导航系统（INS），它使用加速度计和陀螺仪测量运动动力学。这些传感器可以在任何地方以非常高的速率提供PLAN，而不受天气条件或外部信号或基础设施的影响。但是，在没有外部源更新的情况下，它们的性能会随着时间的推移而下降。因此，目前用于AVS的PLAN技术都有优点和缺点；没有任何一种技术似乎足以解决上述挑战。CRC研究计划将推进技术和处理平台的发展，使新型PLAN系统能够在所有环境中高效运行，特别是在GNSS信号阻塞、黑暗、缺乏视觉特征/地标、烟雾、雾和雨等退化环境条件下。这将通过所有可用传感器的多传感器融合来实现，以在任何地方和所有环境中提供连续和强大的定位，以及机器智能算法来管理和协调异构传感器/系统集，使其成为一个强大的定位系统，以满足对安全至关重要的自主导航的需求。从自动驾驶的角度来看，主席工作预计将对AVS的接受度和信任度产生重大影响，因为它将提高其可靠性。