I-Corps: Risk Analysis System for Collision Avoidance with Wildlife

I-Corps项目的更广泛影响/商业潜力是开发交通安全数据分析平台，该平台将有助于减少野生动物车辆碰撞（wvc）造成的伤害、财产损失、创伤和环境影响。根据公共保险和美国运输部的数据，美国每年发生超过130万起交通事故，给保险公司、运输部和货运公司造成超过200亿美元的损失。初步的统计分析表明，一种新的统计模型在预测道路上遇到大型动物的可能性和碰撞的可能性方面是有效的。与公共安全管理人员、汽车保险索赔管理人员、卡车司机和乘客司机进行的广泛的客户调查表明，减少wvc的广泛、财务和安全需求。将拟议的技术商业化作为一项服务，将使公共安全管理人员能够了解其所在地区的风险因素，并为司机先发制人、有选择地部署安全对策。I-Corps项目的基础是开发一套统计分析算法，用于预测驾驶员在道路上看到动物的可能性、撞到动物的可能性以及碰撞的潜在严重程度（财产损失、轻伤、重伤或死亡）。这些拟议的风险模型融合了来自历史事故、过去和预测天气数据以及道路和地面数据的数据。拟议中的技术还包括物联网（IoT）设备，称为RADs：路边动物威慑器。建议的算法可以决定在哪里安装rad，还可以评估随着时间的推移崩溃统计数据的变化。这项技术可以使公共道路管理人员保持道路的安全、维护和正常运行。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值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 I-Corps project is the development of a traffic safety data analytics platform that will help reduce the injuries, property damage, trauma, and environmental impact caused by wildlife-vehicle collisions (WVCs). According to public insurance and US DOT sources, over 1.3 million WVCs occur every year in the US, causing over $20B in losses for insurers, DOTs, and freight haulers. Preliminary statistical analysis indicated the effectiveness of a novel statistical model in predicting the likelihood of encountering a large animal on a roadway, and the likelihood of a collision. Extensive customer discovery with public safety managers, auto insurance claims managers, truckers, and passenger drivers, indicated widespread and financial and safety needs to reduce WVCs. Commercialization of the proposed technology as a service will enable public safety managers to understand risk factors in their districts, and preemptively and selectively deploy safety countermeasures for drivers.This I-Corps project is based on the development of a suite of statistical analytics algorithms that predict the likelihood of a driver witnessing an animal on the road, the likelihood of hitting the animal, and the potential severity of the collision (property damage, light injury, serious injury, or fatality). These proposed risk models fuse data feeds from historical crashes, past and predictive weather data, and road and surface data. The proposed technology also includes internet of things (IoT) devices, called RADs: Roadside Animal Deterrents. The proposed algorithms may determine where to install the RADs, and also evaluate changes in crash statistics over time. The technology may enable public roadway managers to keep their roads safe, maintained, and properly operating.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.