An automatic driving device generates a control plan for autonomously driving a vehicle using map data. The automatic driving device determines an acquisition status of the map data. The automatic driving device generates the control plan using the map data. The automatic driving device changes the control plan according to the acquisition status of the map data.

A method for determining a transportation mode acquires magnetometer and speed data from a mobile device, correlates the magnetometer to the speed data in groupings, and performs spectral analysis on the groups of magnetometer data. Energy calculated for each of a set of frequency components obtained from the spectral analysis is compared to a baseline value to generate a difference, and a transportation mode type is assigned to the vehicle based on the difference.

A method including generating a curvilinear coordinate system from a current position of the vehicle. The method further includes generating a probability distribution from the curvilinear coordinate system and predicting a future vehicle behavior of the vehicle based on the probability distribution.

A method and a system for lane change prediction. The method includes collecting raw driving data, extracting a plurality of feature sets from the collected raw driving data, and obtaining corresponding lane change information. The lane change information indicates a status of lane change of a vehicle under each of the extracted feature sets. The method further includes automatically labeling each of the extracted plurality sets of features with the obtained corresponding lane change information. The method further includes training a lane change prediction model with the labeled plurality sets of features. Examples of the present disclosure further describe methods, systems, and vehicles for applying the lane change prediction model.

A distributed computing system for determining road surface traction capacity for roadways located in a common spatio-temporal zone includes a plurality of vehicles that each include a plurality of sensors and systems that collect and analyze a plurality of parameters related to road surface conditions in the common spatio-temporal zone. The distributed computing system also includes one or more central computers in wireless communication with each of the plurality of vehicles. The one or more central computers execute instructions to determine a road surface traction capacity value for the common spatio-temporal zone.

Disclosed is a method of providing active services based on big data using a remote start device of a vehicle. The method includes the steps of: collecting information related to the vehicle and a driver; deriving a behavior prediction value for predicting driver's behavior based on the collected information; operating an active service determination unit when the derived behavior prediction value meets a preset condition; determining, by the active service determination unit, proposal of an active service to the driver based on the collected vehicle-related information; determining a type of the active service and a time of providing the active service; transmitting proposal of the determined active service to a driver terminal to be displayed; and starting execution of the determined active service according to a change in the state of the driver terminal.

Graphs are powerful structures made of nodes and edges, Information can be encoded in the nodes and edges themselves, as well as the connections between them. Graphs can be used to create manifolds which in turn can be used to efficiently train more robust AI systems. Systems and methods for graph-based AI training in accordance with embodiments of the invention are illustrated. In one embodiment, a graph interface system including a processor, and a memory configured to store a graph interface application, where the graph interface application directs the processor to obtain a set of training data, where the set of training data describes a plurality of scenarios, encode the set of training data into a first knowledge graph, generate a manifold based on the first knowledge graph, and train an AI model by traversing the manifold.

A vehicle control system is provided with: a database configured to store therein, for each vehicle, vehicle data including a plurality of types of information about vehicle operation; a group divider configured to divide the vehicle data of a plurality of vehicles into groups each including similar driving characteristics; a specifier configured to specify to which of the groups a host vehicle belongs, from a running history of the host vehicle; an extractor configured to extract the vehicle data of a vehicle with higher evaluation regarding a predetermined evaluation item, which can be evaluated by using the vehicle data, than that of the host vehicle, from the group specified by the specifier; and a controller configured to control a running aspect of the host vehicle such that it approaches to a running aspect performed on the basis of the vehicle operation indicated by the vehicle data extracted by the extractor.

A control device for a vehicle configured to travel in a one-pedal mode in which driving and braking are controlled in response to operations on only an accelerator pedal is configured to control a braking force of the vehicle by using deceleration maps in which decelerations in a plurality of traveling directions are set for any points based on traveling history data, and calculate, during traveling in the one-pedal mode, a deceleration level based on deceleration information associated with a current traveling direction and a current position of the vehicle among pieces of deceleration information included in the deceleration maps.

A driverless vehicle system comprises a processor that is configured to communicate information related to attributes of a focus autonomous vehicle (FAV) to an other peer vehicle (PV) and/or a central repository system (CRS). The processor is further configured to communicate information about a corrective action by at least one of the FAV and a previously contacted vehicle to the CRS or to a further peer vehicle that is within a predefined region.