A method, an electronic device and a computer-readable storage medium for testing an autonomous driving system which relate to the technical field of autonomous driving are proposed. An embodiment for testing the autonomous driving system includes: obtaining scenario description information of a testing scenario; analyzing the scenario description information, and determining a scenario risk, a scenario probability and a scenario complexity corresponding to the testing scenario; obtaining a scenario weight of the testing scenario according to the scenario risk, scenario probability and scenario complexity; determining a test period corresponding to the scenario weight, where the test period is used for the autonomous driving system being tested in the testing scenario. The technical solution may reduce the testing pressure of the autonomous driving system and improve the testing efficiency of the autonomous driving system.

A method is for assisting with the driving of vehicles traveling on a road by an assistance system including a sensor installed along sections of the road and an electronic processor. The method includes reception by the processor of a request indicating a road portion and requesting information on the state of the portion, determination by the processor, as a function of the requested information and the road portion, of the configuration among several determined configurations, of the sensor, sending by the processor to the sensor of a command indicating the configuration, sending the processor data delivered by the sensor in the configuration, and sending by the processor of the information determined as a function of the data.

Technologies disclosed relate to a remote intervention system for the operation of a vehicle, which can be an autonomous vehicle, a vehicle that includes driver assist features, a vehicle used for ride sharing services or the like. The system includes a vehicle sending a request for remote intervention to a remote operator when the operation of the vehicle is suspended. The request for remote intervention can include a request for object identification or a request for decision confirmation. The vehicle can update vehicle operation based in part on vehicle-based sensor data and a response to the remote intervention request from the remote operator. The remote operator can be a human operator or an AI operator.

An autonomous driving control system, comprising a main control system and a backup control system. The main control system comprises a main control module and main execution modules, and the backup control system comprises a backup control module and backup execution modules; the main control module monitors an operating status of the main control system in real time; the main control module further sends, when detecting that a failure occurs in the main control system, a failure notification to the backup control module, and sends a response termination control instruction to each of the main execution modules, the response termination control instruction being a control instruction for instructing each of the main execution modules not to respond to any control over a vehicle; and the backup control module controls, after receiving the failure notification, the backup execution modules to start to execute a backup control instruction.

A vehicle communication, power, and guidance system for use in guiding and communicating with a land vehicle along a roadway, the system comprising: one or more reference devices positioned along the roadway, each of the reference devices further comprising: a memory device for storing fixed values for one or more vehicle and traffic related parameters; and one or more transmission modules for transmitting said fixed values for one or more vehicle and traffic related parameters; a vehicle mounted device comprising: a receiving module for receiving transmitted signals from the transmission module of said reference devices; and a processing module for processing the received signals and a transmitter module to transmitting signals to the reference device to communicate with one or more controllers of the vehicle to guide and control movement of the vehicle along the roadway.

Techniques for determining distortion in a map caused by measurement errors are discussed herein. For example, such techniques may include implementing a model to estimate map distortion between the map frame and the inertial frame. Data such as sensor data, map data, and vehicle state data may be input into the model. A map distortion value output from the model may be used to compensate vehicle operations in a local region by approximating the distortion as linearly varying about the region. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on the trajectory.

An apparatus for providing a notification of control authority transition in a vehicle is provided. The apparatus includes a speaker configured to output a sound notification, a vibration motor configured to output a vibration notification, and a control circuit configured to be electrically connected with the speaker and the vibration motor. The control circuit is configured to output a first notification using the speaker during a first time interval, when a situation to transfer control authority for the vehicle occurs, output a second notification using the speaker and the vibration motor during a second time interval, after the first time interval elapses, and output a third notification using the speaker and the vibration motor during a third time interval, after the second time interval elapses.

Provided are methods for vehicle scenario mining for machine learning methods, which can include determining a set of attributes associated with an untested scenario for which a machine learning model of an autonomous vehicle is to make planned movements. The method includes searching a scenario database for the untested scenario based on the set of attributes. The scenario database includes a plurality of datasets representative of data received from an autonomous vehicle sensor system in which the plurality of datasets is marked with at least one attribute of the set of attributes. The method further includes obtaining the untested scenario from the scenario database for inputting into the machine learning model for training the machine learning model. The machine learning model is configured to make the planned movements for the autonomous vehicle. Systems and computer program products are also provided.

A method may include obtaining input information relating to an environment in which an autonomous vehicle (AV) operates, the input information describing at least one of: a state of the AV, an operation of the AV within the environment, a property of the environment, or an object included in the environment. The method may include identifying a first object in the vicinity of the AV based on the obtained input information. The method may include determining a first object rule corresponding to the first object, the first object rule indicating suggested driving behavior for interacting with the first object. The method may include determining a first decision that follows the first object rule and sending an instruction to a control system of the AV, the instruction describing a given operation of the AV responsive to the first object rule according to the first decision.

The present teaching relates to system, method, medium for in-situ perception in an autonomous driving vehicle. A plurality of types of sensor data acquired continuously by a plurality of types of sensors deployed on the vehicle are first received, where the plurality of types of sensor data provide information about surrounding of the vehicle. Based on at least one model, one or more items are tracked from a first of the plurality of types of sensor data acquired by one or more of a first type of the plurality of types of sensors, wherein the one or more items appear in the surrounding of the vehicle. At least some of the one or more items are then automatically labeled on-the-fly via either cross modality validation or cross temporal validation of the one or more items and are used to locally adapt, on-the-fly, the at least one model in the vehicle.