SBIR Phase I: Enabling Safe, High-Speed Autonomous Mobile Robots in Warehouse Environments

这个小型企业创新研究(SBIR)第一阶段项目的更广泛影响/商业潜力将是开发一种自主移动机器人(AMR)软件堆栈，旨在安全地优化仓库中的物料移动吞吐量。目前，由于机器人的感知能力有限，仓库中的AMR的运行速度不到人类驱动AMR的一半。这一决定的结果是车辆的潜在吞吐量大幅减少，转化为更小的设施车队规模，以及相关的成本和材料节省。改进的AMR运营将解决仓库劳动力短缺的问题，并提高安全性。根据美国职业安全与健康管理局(OSHA)的数据，每年大约有85-90起叉车事故死亡，超过7000人受伤需要请假数天。通过使用拟议的软件堆栈实现叉车的自动化，这些安全事故将显著减少。该项目将基于自动驾驶汽车中使用的系统开发与更安全的AMR相关的软件。这个小型企业创新研究(SBIR)第一阶段项目正在为仓库中的自主移动机器人(AMR)开发一个软件堆栈，以将AMR的敏捷性和空间感知提高到与人类相似的水平。这项拟议的创新通过使用高清(HD)地图和三维(3D)感知，从自动驾驶汽车的进步中获得灵感。这些高清地图将利用3D LiDAR系统的最新进展和深度学习方法进行目标检测，从而实现更高速度的操作。该项目将使自动驾驶速度从2.0米/S安全提高到3.0米/小时。为了确保车辆安全不受影响，系统将按照美国国家标准学会/工业卡车标准发展基金会(ANSI/ITSDF)B56.5安全标准进行测试，以满足物体检测要求。该奖项反映了美国国家公路交通安全基金会的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will be the development of an autonomous mobile robot (AMR) software stack designed to safely optimize material movement throughput in warehouses. Currently, AMRs in warehouses operate at less than half the speed of their human-driven counterparts due to the robot’s limited perception capabilities. A consequence of this decision is a dramatic reduction in the vehicle’s potential throughput, translating to a smaller facility fleet size with associated cost and material savings. Improved AMR operation will address warehouse labor shortages and improve safety. According to the Occupational Safety and Health Administration (OSHA), there are roughly 85-90 forklift fatalities each year, and over 7,000 injuries requiring days away from work. By automating forklift trucks with the proposed software stack, these safety incidents will be significantly reduced. This project will develop software associated with safer AMRs based on systems used in autonomous cars. This Small Business Innovation Research (SBIR) Phase I project is developing a software stack for autonomous mobile robots (AMRs) in warehouses to improve AMR agility and spatial awareness to human-like levels. The proposed innovation takes inspiration from advances in self-driving cars through the use of high-definition (HD) mapping and three-dimensional (3D) perception. These HD maps will leverage the latest advances in 3D LiDAR systems and deep learning approaches for object detection, enabling operation at higher speeds. This project will enable safe increases in AMR speeds from 2.0 to 3.0 m/s. To ensure vehicle safety is not compromised, systems will be tested to and meet the American National Standards Institute/Industrial Truck Standards Development Foundation (ANSI/ITSDF) B56.5 safety standard for object detection requirements.This 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.