Abstract: In some implementations, a method includes receiving, by one or more processing devices configured to control a traffic signal at an intersection of roads, camera data providing images of the intersection, the processing devices being located proximate to the intersection, using one or more local machine learning models to identify objects at the intersection and paths of the objects based on the camera data, providing traffic data generated from outputs of the one or more local machine learning models to a remote traffic planning system over a network, receiving, from the remote traffic planning system, a remote instruction for the traffic signal determined using one or more remote machine learning models, and providing a control instruction to the traffic signal at the intersection that is determined based on (i) the remote instruction from the remote traffic planning system, and (ii) a local instruction generated by the processing devices.

Abstract: In some implementations, vehicle data indicating a state of a vehicle is received. A current vehicle context is determined based on the vehicle data. Message data indicating one or more candidate messages is received, with each message having a corresponding display context. It is determined whether a particular message of the candidate messages has a display context that matches the current vehicle context. In response to determining that a particular message of the candidate messages has a display context that matches the current vehicle contexts, the particular message is provided for output on a display of the vehicle.

Abstract: In some implementations, a method includes receiving, by one or more processing devices configured to control a traffic signal at an intersection of roads, camera data providing images of the intersection, the processing devices being located proximate to the intersection, using one or more local machine learning models to identify objects at the intersection and paths of the objects based on the camera data, providing traffic data generated from outputs of the one or more local machine learning models to a remote traffic planning system over a network, receiving, from the remote traffic planning system, a remote instruction for the traffic signal determined using one or more remote machine learning models, and providing a control instruction to the traffic signal at the intersection that is determined based on (i) the remote instruction from the remote traffic planning system, and (ii) a local instruction generated by the processing devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for wireless user interface projection for vehicles are disclosed. In one aspect, a method includes the actions of receiving, by a mobile device, a wireless signal transmitted by a processing unit of a vehicle that includes a screen, the wireless signal including an identifier for the processing unit. The actions further include determining that the identifier corresponds to a trusted processing unit to which the mobile device is configured to provide projected UI information. The actions further include automatically establishing a wireless connection between the mobile device and the processing unit that is associated with the identifier. The actions further include automatically providing, by the mobile device, projected UI information to the processing unit for display on the screen of the vehicle.

Abstract: In some implementations, vehicle data indicating a state of a vehicle is received. A current vehicle context is determined based on the vehicle data. Message data indicating one or more candidate messages is received, with each message having a corresponding display context. It is determined whether a particular message of the candidate messages has a display context that matches the current vehicle context. In response to determining that a particular message of the candidate messages has a display context that matches the current vehicle contexts, the particular message is provided for output on a display of the vehicle.