Abstract: Systems and methods of configuring and using a machine-learned safety risk model to predict a corresponding risk of vehicular collision for different candidate routes are disclosed herein. In some example embodiments, a computer system obtains accident data and feature data for historical routes that have been communicated electronically as navigation guidance, trains a safety risk model using the accident data and the feature data of the historical routes as training data in a machine learning process, and then evaluates one or more routing algorithms by generating a corresponding set of routes for each routing algorithm and generating a corresponding performance measurement for each set of routes using the trained safety risk model.

Abstract: A system includes a sensor array and a processing circuit. The processing circuit is operable to: store a policy; receive the sensor information from the sensor array; receive horizon information from a horizon system; input the sensor information and the horizon information into the policy; determine an output of the policy based on the input of the sensor information and the horizon information; control operation of a vehicle system according to the output; compare the sensor information received after controlling operation of the vehicle system according to the output relative to a reward or penalty condition; provide one of a reward signal or a penalty signal in response to the comparison; update the policy based on receipt of the reward signal or the penalty signal; and control the vehicle system using the updated policy to improve operation in view of the operating parameter.