SBIR-STTR Award

Agencies, researchers and companies recognize that today’s abundance of sensor and other data offers a great opportunity for better use of energy resources by introducing energy-awareness into algorithms for vehicle control and decision-making. AV-Connect has identified a gap between the broad availability of maps, traffic forecasts, and large streams of vehicle sensor telematics, and the need for energy-aware algorithms that use real-time data to optimize vehicle behavior that can reduce vehicle energy consumption. AV-Connect will combine machine learning algorithms and decision-making algorithms to process real- time data streams from vehicles’ telematics, traffic and weather forecasts, and deliver tailored route and charging recommendations for electrified vehicles. It will target range anxiety by accurately predicting vehicle energy performance and by selecting routes and charging options that minimize energy usage. AV-Connect’s proposed platform addresses the target set by topic 12.C, as it uses real-time data to identify and leverage opportunities for better energy usage, while alleviating a big obstacle to rapid adoption of electrified mobility. In Phase I we focus on EVs and PHEVs for personal transportation; in that space, we identified a technology gap due to the lack of integration between vehicle telematics data, traffic and routing maps. If successful, our platform can also increase the value of electric fleets of light vehicles and delivery robots. In Phase I, AV-Connect will deploy and quantify the impact of a learning-based eco-routing platform for Electric Vehicles (EVs) and Plug-in Hybrid EVs (PHEVs). The platform will consist of IoT software, machine learning algorithms, and decision-making algorithms. It will leverage real-time data streams from vehicles’ telematics, traffic and weather forecasts, and deliver tailored route and charging recommendations. It will target route energy reduction and range anxiety by accurately predicting vehicle behavior and by selecting routes and charging options that minimize energy usage. AV-Connect will use head-to-head road tests to validate the variation of energy consumption and travel time. AV-Connect’s WideSense Eco-Services platform will deliver numerous cloud services to electrified vehicles from high-precision range prediction, eco-routing, eco-cruise control among others. This would enable a more rapid adoption of EVs and improve their energy performance, resulting in dramatic reductions in fuel emissions and GHG through the replacement of gasoline vehicles.

Consumer surveys show that the biggest obstacles to the mass adoption of electric vehicles EVs by consumers are range anxiety, charging time, inadequate charging infrastructure & cost of vehicle. The company has developed high precision predictions of vehicle energy consumption and optimal charge management. The approach is to combine machine learning algorithms and predictive behavior modeling to process EV sensor telemetry, contextualized with maps, traffic and weather forecasts, and deliver high precision realtime predictions of journey charge consumption and charge depletion trajectory on the journey route while providing optimal charging recommendations based on driver preferences for journey time, time of arrival at destination, charging time and minimum battery charge during and end of trip. In Phase I, the company has developed and validated a learningbased cloud platform for EVs with observed energy savings of 1520%. The platform consists of: proprietary vehicle performance models capturing the energy consumption and travel time on a pervehicle, perdriver, perroadsegment basis; novel learning algorithms which estimate model parameters from contextual data; and modelbased algorithms. The algorithms predict and optimize vehicle performance on road networks delivering high precision charge consumption prediction, optimization of charging stops, and route optimization. During our Phase I technical development and customer interactions we have identified two critical elements required by automakers OEMs: 1 prediction accuracy: changes of time varying parameters such as weight, air drag and temperature gradients have a major effect on charge consumption, and 2 adoption: driver engagement cannot be taken for granted and the platform needs to deliver high precision prediction even when driver destination is unknown. In Phase II, we propose to build on the work of Phase I and develop models and learning algorithms to address both issues by improving prediction accuracy in parametervarying scenarios and regardless of driver engagement by learning of destination. The company’s Contextual Intelligence platform will deliver numerous cloud services to EVs from highprecision charge consumption prediction, intelligent charge management, ecorouting, ecocruise control among others. This would enable a more rapid adoption of EVs and improve their energy performance, resulting in dramatic reductions in fuel emissions and GHG through the replacement of gasoline vehicles.