Techniques for generating simulations for evaluating a performance of a controller of an autonomous vehicle are described. A computing system may evaluate the performance of the controller to navigate the simulation and respond to actions of one or more objects (e.g., other vehicles, bicyclists, pedestrians, etc.) in a simulation. Actions of the objects in the simulation may be controlled by the computing system (e.g., by an artificial intelligence) and/or one or more users inputting object controls, such as via a user interface. The computing system may calculate performance metrics associated with the actions performed by the vehicle in the simulation as directed by the autonomous controller. The computing system may utilize the performance metrics to verify parameters of the autonomous controller (e.g., validate the autonomous controller) and/or to train the autonomous controller utilizing machine learning techniques to bias toward preferred actions.

The invention relates to a control device for a driver assistance system, wherein the control device comprises a sensor interface via which the control device can be connected to at least one sensor module to receive data from the at least one sensor module, a power processor which is adapted to detect objects and to provide object data based on the data from the at least one sensor module, and a system interface via which the control device can be connected to a higher-level control device of the driver assistance system for forwarding object data provided by the power processor.

A system for controlling an intelligent network vehicle is provided, and the system comprises a sensor group configured to obtain sensor information; a sensing and positioning module configured to obtain sensing information and positioning information based on the sensor information; a planning and control module configured to determine vehicle planning control information based on the sensing information and the positioning information; a safety control module configured to determine safety control information based on the sensing information and the positioning information; a function assessment module configured to determine a vehicle state assessment result; a risk assessment module configured to determine a risk assessment result; a logical arbitration module configured to determine vehicle execution information by arbitrating the vehicle planning control information and the safety control information; and an execution module configured to control the vehicle driving based on the vehicle execution information.

Systems and methods are provided for vehicle navigation. In one implementation, a system may comprise at least one processor. The processor may be programmed to receive images representative of an environment of the host vehicle and analyze the images to identify a first object and a second object. The processor may determine a first predefined navigational constraint implicated by the first object and a second predefined navigational constraint implicated by the second object, wherein the first and second predefined navigational constraints cannot both be satisfied, and the second predefined navigational constraint has a priority higher than the first predefined navigational constraint. The processor may determine a navigational action for the host vehicle satisfying the second predefined navigational constraint, but not satisfying the first predefined navigational constraint and, cause an adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.

A method for predicting a failure of a power control unit of a vehicle is provided. The method includes obtaining data from a plurality of sensors of the power control unit of a vehicle subject to simulated multi-load conditions, implementing a machine learning algorithm on the data to obtain machine learning data, obtaining new data from the plurality of sensors of power control unit of the vehicle subject to real multi-load conditions, implementing the machine learning algorithm on the new data to obtain test data, predicting a failure of the power control unit based on a comparison between the test data and the machine learning data.

In one embodiment, a control command is generated by an autonomous controller of the ADV. Feedback is sensed that corresponds to the control command. A difference is determined between a) the control command, and b) the feedback corresponding to the control command. If the difference is meets a threshold, then a fault response is generated.

Disclosed embodiments relate to adjusting vehicle Electronic Control Unit (ECU) software versions. Operations may include receiving a prompt to adjust an ECU of a vehicle from executing a first version of ECU software to a second version of ECU software; configuring, in response to the prompt and based on a delta file corresponding to the second version of ECU software, the second version of ECU software on the ECU in the vehicle for execution; and configuring, in response to the prompt, the first version of ECU software on the ECU in the vehicle to become non-executable.

A method of determining a target path according to a source electronic control unit (ECU) mounted on a vehicle is provided. The method includes obtaining state information of a plurality of paths connecting the source ECU with a destination ECU, selecting the target path for target data from among the plurality of paths based on the state information, and transmitting the target data to the destination ECU through an ECU located on the selected target path, the state information including information about at least one of power consumption of an ECU located on the paths, a temperature of the ECU located on the paths, a latency of the paths, and a transmission success rate of the paths.

According to one example there is provided a method comprising selecting a first location from a set of locations and analysing, by a processor, data collected from a first vehicle located within a first distance of the first location. A first value representative of a first performance parameter of the first vehicle is generated. A second value representative of a second performance parameter of the first vehicle is generated. At least one of the first and second values is compared with a first threshold and, when one of the first and second values is greater than the first threshold, a safety alert is issued greater than (in some examples, less than).

A method can include perturbing an electric motor of a hybrid powerplant having the electric motor and a fuel powered engine. The method can include measuring a frequency response of the powerplant due to the perturbing of the electric motor to determine a health of the powerplant and/or one or more components thereof.