The present disclosure relates to systems, devices and methods for vehicle control with natural-language guidance instructions. In one embodiment, a method is provided for control vehicle operation based on natural-language guidance instructions and image data detected by a camera mounted to a vehicle. One or more targets may be identified based on the guidance instructions to identifying vehicle position and/or operation. Object detection may be performed on the image data and control commands may be determined in response to the object detection. Operation of the vehicle may be controlled based on the control command. Natural-language guidance instructions can allow for directions and/or destinations to be provided without an operator or passenger of the vehicle having an address or map identifier of a destination. Processes and configurations are provided for confirming natural-language instructions and assessing image data to control vehicle operation.