An autonomous vehicle (AV) system includes an AV control system that resolves unique situations encountered while operating as a ride hail provider. The AV control system includes an artificial intelligence (AI) agent programmed to receive a situation data set as an input from vehicle sensors or from another AI agent. The situation data set can include a generic representation of information describing and characterizing the circumstances and details of the current situation. The system may access a knowledge library having catalogued prior situation data sets describing situations encountered by the AV or other vehicles in a fleet. The AV control system may search the knowledge library for similar situations encountered by a fleet vehicle. Once a similar situation is identified, the AV control system may identify one or more remedies that were executed to handle the prior situation, and execute the remedy to address the current situation.

A vehicle is configured to transport a passenger through autonomous travel. The vehicle includes an in-vehicle camera configured to image the passenger to generate an image, a camera controller configured to control the in-vehicle camera, and a passenger information detection unit configured to detect information about the passenger. The passenger information detection unit measures the number of passengers and the camera controller stops an operation of the in-vehicle camera in a case where the number of passengers is one.

Systems and methods are directed to using machine learning in determining vehicle status and/or rider status associated with a service trip. In one example, a computer-implemented method for providing a vehicle trip check includes obtaining sensor data from one or more sensors positioned within a cabin of a vehicle, the sensor data being descriptive of objects located within the cabin of the vehicle. The method further includes inputting the sensor data to a machine-learned trip check model, and includes receiving, as an output of the machine-learned trip check model, trip check analysis data. The method further includes determining, based on the trip check analysis data, that the trip check analysis data meets one or more predetermined criteria. The method further includes in response to determining that the trip check analysis data meets the one or more predetermined criteria, generating a trip control signal associated with operation of the vehicle.

A method for providing personal stowage using a highly or fully automatically operated vehicle includes receiving a request signal, which includes information about a desired provisioning location for providing a personal stowage, ascertaining the location of the requested personal stowage, and transmitting a provisioning signal to an automatically operated vehicle for providing the personal stowage at the provisioning location using the automatically operated vehicle.

Embodiments may relate to a vehicle comprising: a sensor to identify, based on an audio or visual condition, the occurrence of a condition related to a passenger of the vehicle. The vehicle may further include a processor coupled with the sensor. The processor may be configured to identify, in a user profile of the first passenger of the vehicle, a pre-identified action. The processor may further be configured to perform, or facilitate the performance of, the pre-identified action by the vehicle based on the occurrence of the audio or visual condition. Other embodiments may be described or claimed.

A passenger transportation system includes: an abnormality determination unit configured to determine whether or not a passenger feeling unwell is present in a vehicle; a transportation planning unit configured to determine, when it is determined that the passenger feeling unwell is present, a medical facility to which the passenger feeling unwell is transported and a via-point where normal passengers are dropped off; and a vehicle control unit configured to control the vehicle to travel so as to transport the passenger feeling unwell to the medical facility via the via-point.

The disclosure provides for a method for determining a pullover spot for a vehicle. The method includes using a computing device to detect information related to a system of the vehicle or an environment surrounding the vehicle using a sensor of a vehicle and determine a local failure of the vehicle based on the information. The computing device may then be used to determine that the vehicle should pullover before completing a current trip related to transporting a passenger or good by comparing vehicle requirements for the trip with the local failure and determine a pullover spot by identifying a first area for the vehicle to park in part based on a second area being available for a second vehicle to pick up the passenger or good. The computing device may operate the vehicle to the pullover spot and transmit a request for a second vehicle.

Aspects of the disclosure relate to evaluating pullovers for autonomous vehicles. In one instance, a set of potential pullover locations within a predetermined distance of a destination may be identified. Whether any of the potential pullover locations of the set include one or more of a plurality of predetermined types of regions of interest where a vehicle should not park for an extended period of time may be determined. A pullover location is identified based on the determination. The identified pullover location may be compared to a pullover location identified by autonomous vehicle control software in order to evaluate the pullover location identified by the autonomous vehicle control software.

Systems and methods for adapting various autonomous vehicle settings to protect personal information based on the composition of passengers in a vehicle. In particular, sensitive user information is intelligently parsed out or generalized based on user preference and the presence of unknown passengers. In some examples, sensitive user information is routed to more secure channels such as a mobile device application or a personalized display. In some implementations, the position of passengers within a vehicle is determined to identify which displays are in each passenger's field of view. Additionally, pick-up and drop-off locations can be scrambled to nearby destinations to obscure a home address, work address, or other identifiable address information.

Vehicles, systems and methods for improving traffic flow and roadway safety including an autonomous vehicle programmed to automatically interfere with at least a second vehicle in order to protect the second vehicle or occupants or property within the second vehicle. The vehicle includes a Safety Mode where the vehicle sacrifices itself to protect other vehicles, and a Passenger Mode where the vehicle exhibits priority over other vehicles which other vehicles sacrifice themselves for the benefit of the Passenger Mode vehicle. In further disclosure an autonomous vehicle includes crumple zones in non-traditional locations to more effectively protect vehicles in crashes. A computer-implemented method, system, and/or computer program product controls the autonomous vehicle configured to automatically position itself in a collision or interference with another vehicle in order to minimize force impacts upon other vehicles.