This on-vehicle system is to be mounted in a vehicle and is provided with an electronic control device and an externality recognition sensor. The externality recognition sensor is equipped with a sensing unit for acquiring pre-processing externality information through sensing operations. The on-vehicle system is further equipped with: a condition calculation unit that, on the basis of a vehicle position, a vehicle traveling direction, and map information, calculates a processing condition in which information specifying an area on a map is associated with processing priority of the pre-processing externality information acquired by the externality recognition sensor; and a processing object determination unit that, on the basis of the pre-processing externality information and the processing condition, creates externality information having a smaller amount of information compared with the pre-processing externality information.

In a vehicle control device, environmental information is acquired which is information about an environment in which a vehicle is placed. The environmental information precludes an obstacle around the vehicle. A possibility is estimated for potential proximity of the vehicle to the obstacle. A behavior of a predicted target moving object including the vehicle and at least one moving object around the vehicle is predicted based on the estimated possibility. A responsibility is determined for a potential accident that is assumed in response to the vehicle traveling on a candidate route that the vehicle travels.

A computer-implemented method for navigating a host vehicle may include receiving an image frame acquired by an image capture device associated with the host vehicle; identifying in the image frame a representation of a target vehicle; determining an orientation indicator associated with the target vehicle; based on the determined orientation indicator, identifying a candidate region of the acquired image frame where a representation of a vehicle door of the target vehicle is expected in an open door condition; extracting the candidate region from the image frame; providing the candidate region to an open door detection network; determining a navigational action for the host vehicle in response to an indication from the open door detection network that the candidate region includes a representation of a door of the target vehicle in an open condition; and causing an actuator associated with the host vehicle to implement the navigational action.

A distributed method and system for collision avoidance between vulnerable road users (VRUs) and vehicles is provided. The method and system provide for pedestrian-to-vehicle (P2V) collision avoidance, in the field of intelligent transportation technology and data analytics with an artificial intelligence (AI) algorithm distributed among edge and cloud systems. The distribution of data analytics is weighted between edge and cloud systems: the cloud system referring to a Neural Network computational algorithm embedded in a distant server, and the edge system referring to a user equipment (UE) mobile terminal having a P2V collision avoidance applicative algorithm. The described technology can provide P2V danger notifications relating to the field of road safety, and pertaining to collision avoidance, before accidents happen. The described technology relates to precautions collision avoidance notifications using past, current, and predicted trajectories of VRUs and vehicles, based on an AI algorithm distributed among edge and cloud systems.

A system for vehicle forward collision avoidance through a low speed limit area includes a position providing device, a sensor, and a vehicle controller. The position providing device is configured to provide information on a position of a host vehicle. The sensor is configured to detect whether an object is present in vicinity of the host vehicle. The vehicle controller is configured to: set a dangerous area based on a dangerous rank by detecting through the sensor, in a driving caution area, a motionless vehicle or a pedestrian; correct sensitivity of the sensor to be higher than an original sensitivity, after setting the dangerous area; and correct forward collision avoidance performance of the host vehicle to be increased from an original performance, when the position of the host vehicle is detected in the driving caution area through the position providing device.

Systems and methods for navigational map version management are disclosed. In one aspect, a map management server includes a processor and a computer-readable memory having stored thereon a navigational map including a plurality of units, each of the units covering an area and including a plurality of objects within or adjacent to roadways within the area. The processor is configured to receive update data for the navigational map, the update data including object data to update the navigational map. The processor is also configured to create a released version of the navigational map that includes one or more updated units. The processor is further configured to provide the released version of the navigational map to an autonomous vehicle.

In various examples, a multi-sensor fusion machine learning model—such as a deep neural network (DNN)—may be deployed to fuse data from a plurality of individual machine learning models. As such, the multi-sensor fusion network may use outputs from a plurality of machine learning models as input to generate a fused output that represents data from fields of view or sensory fields of each of the sensors supplying the machine learning models, while accounting for learned associations between boundary or overlap regions of the various fields of view of the source sensors. In this way, the fused output may be less likely to include duplicate, inaccurate, or noisy data with respect to objects or features in the environment, as the fusion network may be trained to account for multiple instances of a same object appearing in different input representations.

System, methods, and other embodiments described herein relate to a training system to train a driver about occurrences of anomalous driving events of automated vehicle systems. In one embodiment, a method includes determining, upon receiving a selection of a vehicle behavior from one or more anomalous driving events and a detected state change signal, whether the vehicle behavior affects one or more entities. The method includes assessing a state of the one or more entities to simulate the vehicle behavior according to a safety standard. The method includes triggering simulation of the vehicle behavior if the state satisfies a threshold. The method includes simulating the vehicle behavior by at least controlling the vehicle to simulate the vehicle behavior during automated driving of the vehicle.

An embodiment of an antenna includes first and second transmission lines, first antenna elements, and second antenna elements. The first transmission line is configured to guide a first signal such that the first signal has a characteristic of a first value, and the second transmission line is configured to guide a second signal such that the second signal has the same characteristic but of a second value that is different than the first value. The first antenna elements are each disposed adjacent to the first transmission line and are each configured to radiate the first signal in response to a respective first control signal, and the second antenna elements are each disposed adjacent to the second transmission line and are each configured to radiate the second signal in response to a respective second control signal. Such an antenna can have better main-beam and side-lobe characteristics, and a better SIR, than prior antennas.

A speed control method for controlling the speed of an autonomous vehicle provided with at least one autonomous driving module and one geolocation module, the vehicle being capable of following a route, which is predefined and segmented according to at least one segmentation comprising of a plurality of segments, each associated with: an interval of geolocation data; and a set of values for nominal maximum travel speed of the autonomous vehicle, each speed value being associated with a distinct time slot; the method comprising: the acquisition, from the on-board geolocation module, of an instantaneous geolocation data item of the autonomous vehicle associated with a time instant; as a function of the instantaneous geo-location data item and the time instant, the determination, of the segment currently being traversed and/or to be traversed, and of the associated nominal maximum speed value.