A parking assist apparatus is configured to: detect a level difference existing around the vehicle; determine whether the detected level difference is a passing target level difference required to be passed without avoidance or an avoidance target level difference required to be avoided; and control a notification apparatus to output, toward an inside of a compartment of the vehicle, a notification indicating a passing plan of the passing target level difference in response to the detected level difference, which exists on a traveling route to be traveled by the vehicle within a parking area for parking purpose, being determined as the passing target level difference. The notification apparatus is controlled to output the notification indicating the passing plan of the passing target level difference in a notification mode that distinguishes the passing target level difference from the avoidance target level difference.

A method for controlling a flow of traffic on a roundabout, wherein the flow of traffic is controlled by a traffic control unit by which road users that have entered the roundabout and/or are approaching the roundabout in order to enter it are networked in a network and communicate by way of messages, and wherein, in order to enter, a road user transmits a message containing a request to the traffic control unit provides for entry by the respective road user to be preceded by the flow of traffic that is on the roundabout being determined on the basis of the messages, wherein a message containing a control signal is generated for the respective entering road user in order to communicate whether and/or along which route the road user can travel on the roundabout.

Disclosed is route planning using a worst-case risk analysis and, if needed, a best-case risk analysis of GNSS coverage. The worst-case risk analysis identifies cuboids or 2d regions through which a vehicle can be routed with assurance that adequate GNSS coverage will be available regardless of the time of day that the vehicle travels. The best-case risk analysis identifies cuboids or 2d regions through which there is adequate coverage at some times during the day. In case path finding using the worst-case risk analysis fails, a best-case risk analysis can be requested and used to find alternate potential path(s). Time dependent forecast data that covers regions along the alternate potential path(s) can be requested and used to route vehicles, including autonomous drones, from starting points to destinations. This includes generation, distribution and use of risk analysis data, implemented as methods, systems and articles of manufacture.

A method of directing traffic flow includes receiving, by a processor, navigation information from a vehicle in a multi-edge communication network, and receiving, by the processor, a status of an edge node traffic control device of the multi-edge communication network. The edge node traffic control device is configured to regulate traffic flow on a path segment. The method includes determining, by the processor, a navigation command based on the navigation information and the status, and outputting, by the processor, the navigation command to the vehicle through the multi-edge communication network.

A vehicle control system includes: an on-board control module, configured to control driving of the vehicle according to a control instruction sent by a vehicle dispatching command platform; a vehicle state module, configured to collect state information of the vehicle; an environment sensing module, configured to collect first road environment information of the vehicle; a UAV scanning module, configured to collect second road environment information of the vehicle; a data center module, configured to generate fusion information according to the state information, the first road environment information, and the second road environment information; a map module, configured to generate a driving route map of the vehicle according to the fusion information; and a vehicle dispatching command platform, configured to generate the control instruction according to the fusion information and the driving route map.

Techniques are disclosed herein for providing guidance for autonomous vehicles in areas of low network connectivity, such as rural areas. According to an embodiment, a guidance system receives a request to exchange data with a vehicle within a specified radius thereof over a wireless connection (e.g., a radio frequency protocol-based connection). The data is stored by the guidance system and is indicative of navigation information within the specified radius. The guidance system transmits the stored data to the vehicle. The guidance system also receives, from the vehicle, data indicative of navigation information for a path previously passed by the vehicle.

Embodiments herein include a method executable by a processor coupled to a memory. The processor is local to a vehicle can operable to determine initial location and direction information associated with the vehicle at an origin of a trip request. The processor receives one or more frames captured while the vehicle is traveling along a navigable route relative to the trip request and estimates an execution time for each of one or more computations respective to an analyzing of the one or more frames. The processor, also, off-loads the one or more computations to processing resources of a cloud-based system that is in communication with the processor of the vehicle in accordance with the corresponding execution times.

Methods and devices for generating data for controlling a Self-Driving Car (SDC) are disclosed. The method includes: (i) acquiring a predicted object trajectory for an object, (ii) acquiring a set of anchor points along the lane for the SDC, (iii) for each one of the set of anchor points, determining a series of future moments in time when the SDC is potentially located at the respective one of the set of anchor points, thereby generating a matrix structure including future position-time pairs, (iv) for each future position-time pair in the matrix structure, using the predicted object trajectory for determining a distance between a closest object to the SDC as if the SDC is located at the respective future position-time pair, and (v) storing the distance between the closest object to the SDC in association with the respective future position-time pair in the matrix structure.

Methods and devices for generating data for controlling a Self-Driving Car (SDC) are disclosed. The method includes: (i) acquiring a predicted object trajectory for an object, (ii) acquiring a set of anchor points along the lane for the SDC, (iii) for each one of the set of anchor points, determining a series of future moments in time when the SDC is potentially located at the respective one of the set of anchor points, thereby generating a matrix structure including future position-time pairs, (iv) for each future position-time pair in the matrix structure, using the predicted object trajectory for determining a distance between a closest object to the SDC as if the SDC is located at the respective future position-time pair, and (v) storing the distance between the closest object to the SDC in association with the respective future position-time pair in the matrix structure.

Systems, methods, and other embodiments described herein relate to automatically learning parking preferences for a driver and generating parking recommendations. In one embodiment, a method includes generating training data based at least in part on: 1) trajectory data indicating a trajectory of a vehicle during a plurality of parking events, each in which a driver of the vehicle selected a parking candidate from among a plurality of parking candidates, and 2) attribute data indicating attributes of each of the plurality of parking candidates, removing, from the training data, data associated with at least one available parking candidate based on one or more conditions that indicate the driver did not consider the at least one available parking candidate, and training a decision model, based on remaining training data, to estimate a preferred parking candidate for the driver from among a set of available parking candidates.