A method may include obtaining one or more inputs in which each of the inputs describes at least one of: a state of an autonomous vehicle (AV) or a state of an object; and identifying a prediction context of the AV based on the inputs. The method may also include determining a relevancy of each object of a plurality of objects to the AV in relation to the prediction context; and outputting a set of relevant objects based on the relevancy determination for each of the plurality of objects. Another method may include obtaining a set of objects designated as relevant to operation of an AV; selecting a trajectory prediction approach for a given object based on context of the AV and characteristics of the given object; predicting a trajectory of the given object using the selected trajectory prediction approach; and outputting the given object and the predicted trajectory.

The present disclosure is related to a server side route providing device which includes a storage unit which stores map information and dynamic information related to travel of a target vehicle; a data receiving unit which receives information transmitted from the target vehicle; a processor which updates the map information and the dynamic information using the received information, and generates at least an optimal path for each lane to be transmitted to a target vehicle or field-of-view information for autonomous driving in which sensing information is combined with the optimal path, by using the map information and the dynamic information; and a data transmitting unit which transmits, to the target vehicle, at least one of the optimal path or the field-of-view information for autonomous driving.

A parking assist device capable of parking assistance that ensures high accuracy of a parking location is provided. A parking assist device that assists in performing an operation of parking a vehicle includes a parking-allowing location calculation unit that before the vehicle stops at a parking-allowing location, calculates and updates the parking-allowing location a plurality of times, and a parking route calculation unit that calculates a parking route. The parking route calculation unit sets a minimum turning radius for calculating the parking route, based on the amount of a shift between the parking-allowing location not updated and the parking-allowing location having been updated, and calculates the parking route, using the minimum turning radius. The minimum turning radius is set larger than the minimum value of a turning radius unique to the vehicle.

An acquisition unit acquires data regarding a travel trajectory of another vehicle from the other vehicle. A specifying unit specifies an intersection position between the travel trajectory of the other vehicle and a travel trajectory of a self-vehicle. A setting unit setts a region based on the intersection position and the travel trajectory of the other vehicle as a monitoring region when performing driving assistance. A determination unit determines whether or not to update the monitoring region based on a result of comparison between first data that is the data used to set the monitoring region and second data that is the data acquired from the other vehicle traveling in the monitoring region. The setting unit updates the monitoring region based on the second data in a case where the determination unit determines to update the monitoring region.

A method, apparatus and computer program product are provided for predicting autonomous transition regions using historical information. In this regard, historical autonomous transition data is accessed. The historical autonomous transition data is associated with vehicles that transition from respective autonomous levels while traveling along one or more road segments associated with a first geographic area. Furthermore, one or more features of the historical autonomous transition data associated with the first geographic area is identified. A machine learning model is then trained based on the one or more features associated with the first geographic area.

The present disclosure provides a data acquisition method, apparatus, device and computer readable storage medium. According to the embodiments of the present disclosure, determination is made as to whether a preset stable driving condition is met based on acquired driving scene data of the driving scene where the vehicle is currently located, and acquired driving behavior data; if the preset stable driving condition is met, the driving scene data and the driving behavior data are acquired at a frequency lower than a preset sampling frequency. As a result, it is possible to reduce data redundancy in similar scenes and similar diving modes, reduce the amount of data, reduce occupation of the storage resources and transmission resources and facilitate subsequent analysis, and it is possible to implement the dynamic acquisition of driving scene data and driving behavior data by scenes and modes.

In a vehicle control system, a sampling period change unit changes a sampling period such that the sampling period is made shorter, when a driving state of the vehicle becomes to have a higher possibility of accident as a result of driving control of the vehicle than when the driving state of the vehicle becomes to have a lower possibility of accident. A data storage control unit stores in an eMMC control instruction data stored in a temporary storage buffer in a non-volatile memory by sampling at the sampling period set by the sampling period change unit.

A method for automating a driving function. The method includes an activation of a process controlling the driving function is triggered using an activation condition modelled by a trigger, and the process is temporally controlled by an activation manager during the controlling of the driving function.

A method for the safe execution of a function provided by a motor vehicle. The method includes receiving infrastructure data signals, which represent infrastructure data, which are intended for a function provided by a motor vehicle, receiving safety condition signals, which represent at least one safety condition that must be fulfilled so that the function based on the infrastructure data may be executed, checking whether the at least one safety condition is fulfilled, ascertaining whether the function based on the infrastructure data may be executed, based on a result of the check, generating result signals, which represent a result of the ascertainment, and outputting the generated result signals. A device, a computer program and a machine-readable storage medium are also described.

Disclosed are systems and techniques for using blockchain technology to maintain and validate a vehicle ledger. The technique includes receiving, at a master node in the system, a request to update a vehicle ledger associated with a first vehicle node comprising the system. If first criteria are met, the system updates the vehicle ledger, including: generating an updated version of the vehicle ledger using vehicle data stored in a master ledger associated with the master node, and transmitting the updated version of the vehicle ledger to the first vehicle node. If the first criteria are not met, the system forgoes updating the vehicle ledger. The vehicle data corresponds to a first vehicle associated with the first vehicle node. The master ledger is implemented using a blockchain that contains vehicle records for vehicles associated with the system. The blockchain includes a first block including vehicle data corresponding to the first vehicle.