A vehicle includes a transmission and a controller. The transmission is configured to transition between automatic and manual modes. The controller is programmed to, in response to the transmission operating in the manual mode and an absence of receiving a manual command to shift the transmission for a predetermined period of time, transition the operation of the transmission from the manual mode to the automatic mode. The controller is further programmed to, in response to the transmission operating in the manual mode, an absence of receiving the manual command to shift the transmission for the predetermined period of time, and a condition flagged to suppress an upshift in the transmission, remain in the manual mode.

A machine-learned model is trained using human driving data to determine a desired vehicle speed based from a set of driving-environment characteristics. An autonomous-vehicle control system obtains, from cameras, sensors, services, and data sources, a variety of sensor data. The sensor data is used to determine a set of characteristics for the driving-environment for the autonomous vehicle. Using the machine-learned model, the autonomous-vehicle control system determines a human-like desired speed for the autonomous vehicle based at least in part on the determined characteristics of the driving-environment.