SBIR Phase I: Autonomous active safety systems for verifiably safe operation of ground vehicles

SBIR 第一阶段：用于地面车辆可验证安全运行的自主主动安全系统

• 批准号: 2006225
• 负责人: Jeffrey Johnson
• 金额: $ 22.5万
• 依托单位: MAPLESS AI, INC.
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-15 至 2021-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2006225&HistoricalAwards=false
• 关键词: SBIR; Phase; Autonomous; active; safety

pThe broader impact of this Small Business Innovation Research (SBIR) Phase I project will develop technology that will enable automated transportation systems to verifiably maintain safety without relying on a human driver as a fallback. Driver-related factors were involved in an estimated 94% of fatal crashes; up to 80% could have been mitigated or prevented by advanced technology. More broadly, each year vehicle collisions in the U.S. result in 35,000-40,000 fatalities, over 2.3 M serious injuries, and costs of $850 B. The success of the proposed work will demonstrate that simple, robust methods can be used to achieve safe autonomous vehicle behavior./p pThis Small Business Innovation Research (SBIR) Phase I project will explore translation of an advanced autonomous control system in a combination of advances in multi-agent control theory and new, sensor-based control techniques. This project addresses the challenges of translating theoretical advances into industrial-grade algorithms and defining a vehicle safety system that does not rely on a human fallback mechanism. The Phase I work addresses these technical hurdles through: 1) a feasibility study of a prototype system, and 2) an extensive verification and validation process for a safety case report./p pThis award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria./p

P这项小型企业创新研究（SBIR）I阶段项目的更广泛影响将开发技术，该技术将使自动运输系统能够可靠地保持安全性，而不会依靠人类驾驶员作为后备。 据估计，与驾驶员有关的因素涉及94％的致命崩溃；先进技术可以减轻或预防多达80％的人。更广泛地说，美国每年的车辆碰撞会导致35,000-40,000人死亡，超过2.3 m的重伤，成本为850美元。拟议工作的成功将表明，可以使用简单，可靠的方法来实现安全的自动驾驶行为。新的，基于传感器的控制技术。该项目解决了将理论进步转化为工业级算法的挑战，并定义了不依赖人类后备机制的车辆安全系统。第一阶段的工作通过以下方式解决了这些技术障碍：1）对原型系统的可行性研究，以及2）针对安全案例报告的广泛验证和验证过程。/PPITHIS奖反映了NSF的法定任务，并被视为值得通过基金会的知识分子和更广泛的影响审查标准来通过评估来提供支持。