STTR Phase I: Internet of Things (IOT) Safety Device and System for Micro-Mobility Products

这一小型企业技术转让(STTR)第一阶段项目的更广泛影响/商业潜力是开发新技术，以增强微型移动车辆和车队(自行车、电动自行车和电动滑板车)的安全性。微型移动性在减少城市环境中的拥堵、排放和噪音污染方面具有很高的潜力。这些车辆可以解决许多第一英里和最后一英里的运输挑战。该项目开发的技术将把低成本传感器、先进的机器学习和基于模型的算法与基于物联网(IOT)的微移动安全设备技术相结合。此外，基于物联网的早期检测和预警系统可以解决微型移动性使用中的安全问题，从而开发出强大的生态系统。创新的物联网技术，并将其转变为对微型移动车辆和车队的安全和可靠性至关重要的产品和服务。这项技术包括提前预测车辆制动部件和系统未来可能出现的故障，以及及早检测危险驾驶条件(由于骑手的不当行为、路况或天气条件)。该解决方案将向骑手发出警告和主动警报，并提供可操作的建议(例如，主动维护)。该项目将开发和评估基于模型和机器学习辅助的算法，用于检测、隔离和预测故障和危险驾驶条件，以及相关的决策准确性置信度。在实验条件和约束条件下，安全装置和操作的性能将使用端到端模拟和试验台进行评估。该奖项反映了NSF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 Technology Transfer (STTR) Phase I project is the development of new technologies to enhance the safety of micro-mobility vehicles and fleets (bicycles, electronic bikes, and electric scooters). Micro-mobility has a high potential to reduce congestion, emissions, and noise pollution in urban settings. These vehicles can address many first- and last-mile transportation challenges. The technology developed in this project will integrate low-cost sensors, advanced machine learning and model-based algorithms with Internet of Things (IOT)-based technologies for micro-mobility safety devices. Furthermore, IOT-based early detection and warning systems can address safety concerns in the use of micro-mobility, resulting in the development of strong ecosystems.This Small Business Technology Transfer (STTR) Phase I project will develop and evaluate a cost-effective. innovative, IOT technology and turn it into a product and service that are essential to the safety and reliability of the micro-mobility vehicles and fleets. The technology involves predicting likely future failures in vehicle braking components and systems in advance of their occurrence as well as early detection of hazardous driving conditions (due to misbehavior of riders, road conditions, or weather conditions). The solution will issue warnings to the rider and proactive alerts with actionable recommendations (e.g., for proactive maintenance). The project will develop and evaluate model-based and machine-learning-assisted algorithms for the detection, isolation, and prediction of failures and hazardous driving conditions as well as the associated level of confidence in the accuracy of the decisions. The performance of the safety device and operation under experimental conditions and constraints will be evaluated using end-to-end simulation and a testbed.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.