Autonomous sense and guide machine learning system

One or more computing systems comprising one or more computer-readable storage mediums storing computer-executable instructions for generating a machine learning system to generate guidance information based on locations of objects, such that execution of the instructions causes operations comprising:

• accessing training data that includes a plurality of training times-of-arrival (TOAs) for each of a plurality of looks and guidance information for the plurality of looks, the guidance information being based on a training collection of object locations, wherein the TOAs of a look of the plurality of looks represent, for each object location of the training collection of object locations, a time between a signal transmitted by each of a plurality of transmitters of a sensor array on a platform that is not located at any of the object locations and a corresponding return signal received by each of a plurality of receivers of the sensor array on the platform, wherein return signals corresponding to an object location of the training collection of object locations represent signals transmitted by the plurality of transmitters of the sensor array on the platform and subsequently reflected from an object at the object location;
• and
• training a machine learning system using the training data wherein the machine learning system inputs TOA information and outputs guidance information.