Machine Learning-based Multi-Sensor Positioning and Mapping for Autonomous Vehicles

基于机器学习的自动驾驶汽车多传感器定位和建图

• 批准号: 560898-2020
• 负责人: Noureldin, AboelmagdM
• 金额: $ 6.12万
• 依托单位: Royal Military College of Canada
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 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=751924
• 关键词: Machine; Learning; based; Multi; Sensor

Autonomous vehicles (AVs) are cars, buses or trucks that can travel with limited or no human intervention. They combine sensors, perception systems and software to control, navigate, and safely drive the vehicle. AVs promise to improve our transportation system's efficiency, reduce collisions and traffic congestion, and improve mobility for our growing population. As the world continues to move toward a more efficient transportation system driven by AVs, there is an increasing demand for new technologies that guarantee AVs' efficient and safe operation. Trust in AVs hinges on the reliability of autonomy, including the crucial task of positioning, which should be accurately provided at high precision everywhere for all environments.This research will enable the development and deployment of robust positioning and mapping systems for AVs at a decimeter level of accuracy with high integrity. Our proposed solution will sustain this performance seamlessly everywhere in all operating conditions. With our industry partner, Micro Engineering Tech, we will introduce a new paradigm for the positioning and mapping of AVs. It will expand the present technologies' capabilities and enable the processing of a broader range of complementary sensors and systems on a single platform. This research will revolutionize AV multi-sensor positioning and mapping. We will develop unique machine learning methods to manage and coordinate the heterogeneous set of AV sensors/systems for efficient and safe autonomous driving. This research will significantly impact the acceptance of and trust in AVs by enhancing safety and reliability and decreasing the failure rate in degraded environments. It will also help achieve ubiquitous positioning technology and improve Canada's position in the AV services sector. Moreover, the training of highly qualified personnel (HQP) is an essential component of this research program. A diverse group of 10 talented HQP will be involved to contribute towards advancing Canada's AV technologies.

自动驾驶车辆 (AV) 是指可以在有限或无需人工干预的情况下行驶的汽车、公共汽车或卡车。它们结合了传感器、感知系统和软件来控制、导航和安全驾驶车辆。自动驾驶汽车有望提高交通系统的效率，减少碰撞和交通拥堵，并改善不断增长的人口的流动性。随着世界不断走向由自动驾驶汽车驱动的更高效的交通系统，对保证自动驾驶汽车高效、安全运行的新技术的需求不断增加。对自动驾驶汽车的信任取决于自主的可靠性，包括关键的定位任务，应在任何环境下、任何地方以高精度准确提供定位。这项研究将有助于开发和部署分米级的强大自动驾驶汽车定位和地图系统的准确性和高完整性。我们提出的解决方案将在所有操作条件下在任何地方无缝地维持这种性能。我们将与我们的行业合作伙伴 Micro Engineering Tech 合作，推出自动驾驶汽车定位和绘图的新范例。它将扩展现有技术的能力，并能够在单一平台上处理更广泛的互补传感器和系统。这项研究将彻底改变 AV 多传感器定位和映射。我们将开发独特的机器学习方法来管理和协调异构的自动驾驶传感器/系统，以实现高效、安全的自动驾驶。这项研究将通过提高安全性和可靠性并降低退化环境中的故障​​率来显着影响自动驾驶汽车的接受度和信任度。它还将有助于实现无处不在的定位技术，并提高加拿大在视听服务领域的地位。此外，高素质人才（HQP）的培训是该研究计划的重要组成部分。由 10 名才华横溢的 HQP 组成的多元化团队将参与其中，为推进加拿大的 AV 技术做出贡献。