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 precipitation index estimation apparatus includes a data collection unit and an estimation processing unit. The data collection unit is configured to collect rainfall amount data detected by a rainfall amount sensor in one or more vehicles positioned on a predetermined road link within a predetermined period. The estimation processing unit is configured to estimate a precipitation index indicating an intensity of precipitation on the predetermined road link within the predetermined period, based on the collected rainfall amount data.

A method and a system for providing a personal transportation service using an autonomous vehicle, including: receiving a request for the personal transportation service from a terminal of a user; analyzing a call pattern of the user for the autonomous vehicle; and determining a recommended autonomous vehicle to provide the personal transportation service to the user based on the analysis result of the call pattern are provided.

Path specific rolling resistance is determined in a method including: receiving, from a first source, first rolling resistance data of a first set of road surface portions of a corresponding first set of times; receiving, from a second source, second rolling resistance data of a second set of road surface portions of a corresponding second set of times; determining, using any of the first rolling resistance data and the second rolling resistance data, a path specific rolling resistance for a given path including one or more of the road surface portions selected from the first and second set of road surface portions; and providing at least one target vehicle with the path specific rolling resistance or a derivative of the path specific rolling resistance.

An advanced driver assistance system (ADAS) and method for a vehicle include a light intensity detection system configured to detect a set of light density changes proximate to a face of a driver of the vehicle, a vehicle-to-everything (V2X) communication system, a global navigation satellite system (GNSS) system, and a controller configured to detect a current glare condition based on the set of detected light density changes from the light intensity detection system, share, using the V2X communication system, the detected current glare condition and the corresponding GNSS location, based on the sharing and another set of parameters, determine whether the vehicle is likely to experience a future glare condition during a future period, and in response to determining that the vehicle is likely to experience the future glare condition during the future period, at least one remedial action.

A system for monitoring a driver comprises that a first sensor configured to detect first physical condition information of the driver, a second sensor configured to detect first driving state information of a vehicle; and a controller configured to determine whether a physical condition of the driver is abnormal on the basis of the first physical condition information, and determine whether a driving pattern of the driver is abnormal on the basis of the first driving state information.

Systems and methods for determining and using fleet-specific vehicle operator performance for a set of vehicle operators are disclosed. A fleet of vehicles may be operated by a set of vehicle operators. Exemplary implementations may obtain trip information or service information that include values for driver performance metrics pertaining to individual vehicle operators; determine the fleet-specific vehicle operator performance by aggregating information included in the obtained trip and/or service information; determine particular metric values for a particular vehicle operator; compare the determined fleet-specific vehicle operator performance with the determined particular metric values; based on the comparison, generate and/or provide one or more notifications to at least one of the particular vehicle operator, a stakeholder of the fleet of vehicles, and a remote computing server. In some implementations, a system may recommend taking a particular action, including but not limited to scheduling a break for the particular vehicle operator.

Systems and methods for determining and using deviations from driver-specific vehicle performance expectations for a particular vehicle operator are disclosed. Exemplary implementations may obtain trip information or service information that include values for driver performance metrics pertaining to a particular vehicle operator; determine the driver-specific performance expectations by aggregating information included in the obtained trip information; determine particular metric values for a current trip; compare the determined driver-specific performance expectations with the particular metric values for the current trip; determine deviations based on the comparisons; determine whether to recommend an action based on the deviations; and generate and/or provide one or more notifications to at least one of the particular vehicle operator, a stakeholder of the fleet of vehicles, and a remote computing server.

Technologies and techniques for the lateral control of a vehicle. Environment data of a vehicle is detected when travelling a route, and stored environment data, detected when travelling the route by a plurality of other vehicles not currently travelling the route, is received. The plausibility of the stored environment data is checked on the basis of the environment data detected. Lateral control of the vehicle is executed on the basis of the environment data checked for plausibility. The present disclosure also relates to an arrangement for the lateral control of a vehicle.

The present disclosure describes a method for monitoring operations of an automated driving system (ADS) of a vehicle. For each monitored operation the method includes: determining a geographical position of the vehicle; determining an intended path of the vehicle; and determining one or more intended parameters associated with performing a driving manoeuvre of said vehicle from the determined geographical position along the intended path. For each monitored operation the method further includes: obtaining one or more parameters associated with performing the driving manoeuvre of said vehicle from said determined geographical position; and retrieving, from a statistical model, data indicative of a statistical distribution related to one or more corresponding intended and/or obtained parameters for said intended path. Based on said retrieved data, determining whether there is an anomaly associated with said monitored operation; and taking at least one action of a set of predefined actions if an anomaly is determined.