Abstract: Methods and systems are presented for improving engaging automatic vehicle motive power source stopping and inhibiting automatic vehicle motive power source stopping. The methods and systems include processing driver inputs in a machine learning model and characterizing the driver in one of a plurality of driver groups. Automatic vehicle motive power source stopping and starting may be adjusted responsive to a group in which a driver is a member.

Abstract: The present invention extends to methods, systems, and computer program products for evaluating autonomous vehicle algorithms. Aspects use (e.g., supervised) machine learning techniques to analyze performance of autonomous vehicle algorithms on real world and simulated data. Machine learning techniques can be used to identify scenario features that are more likely to influence algorithm performance. Machine learning techniques can also be used to consolidate insights and automate the generation of relevant test cases over multiple iterations to identify error-prone scenarios.

Abstract: Systems and methods are disclosed for a package delivery platform. The package delivery platform may be configured to receive a package from a drone. The package may include a magnetic material. The package delivery platform may include a platform body, a plurality of magnets disposed about the platform body, and a controller configured to control the plurality of magnets in order to secure the package to the platform body.

Abstract: Methods and systems are presented for improving engaging automatic vehicle motive power source stopping and inhibiting automatic vehicle motive power source stopping. The methods and systems include processing driver inputs in a machine learning model and characterizing the driver in one of a plurality of driver groups. Automatic vehicle motive power source stopping and starting may be adjusted responsive to a group in which a driver is a member.

Abstract: The present invention extends to methods, systems, and computer program products for evaluating autonomous vehicle algorithms. Aspects use (e.g., supervised) machine learning techniques to analyze performance of autonomous vehicle algorithms on real world and simulated data. Machine learning techniques can be used to identify scenario features that are more likely to influence algorithm performance. Machine learning techniques can also be used to consolidate insights and automate the generation of relevant test cases over multiple iterations to identify error-prone scenarios.

Abstract: Systems and methods are disclosed for a package delivery platform. The package delivery platform may be configured to receive a package from a drone. The package may include a magnetic material. The package delivery platform may include a platform body, a plurality of magnets disposed about the platform body, and a controller configured to control the plurality of magnets in order to secure the package to the platform body.