The technology relates to determining whether a vehicle operating in an autonomous driving mode is experiencing an anomalous condition, for instance due to a loss of tire pressure, a mechanical failure, or a shift or loss of cargo. The actual current pose of the vehicle is compared to an expected pose of the vehicle, where the expected pose is based on a model of the vehicle. If a pose discrepancy is identified, the anomalous condition is determined from information associated with the pose discrepancy. The vehicle is then able to take corrective action based on the nature of the anomalous condition. The corrective action may include making a real-time driving change, modifying a planned route, alerting a remote operations center, or communicating with one or more other vehicles.

When it is determined that there is a likelihood of occurrence of an abnormality in a supercharger, a maximum engine rotation speed and a maximum MG2 rotation speed are changed to a low rotation speed side and operating points of an engine and a rotary machine are controlled such that an engine rotation speed and an MG2 rotation speed are respectively within ranges which do not exceed the changed maximum rotation speeds. Accordingly, even when the supercharger does not operate normally and an abnormal increase in a supercharging pressure occurs, it is possible to curb a high-rotation state of the engine rotation speed and the MG2 rotation speed. As a result, even when an abnormal increase in the supercharging pressure occurs, it is possible to curb a decrease in durability of components.

A method for controlling an actuator. The method includes generating, in response to receiving a torque command signal from a first controller, an actuator control signal. The method also includes selectively controlling the actuator based on the actuator control signal. The method also includes, in response to identifying a fault associated with the first controller: generating, responsive to a determination that a partition associated with a second controller includes a fallback indicator, a fallback actuator control signal; and selectively controlling the actuator based on the fallback actuator control signal.

Systems of an autonomous vehicle and the operations thereof are provided. Autonomous vehicles may rely on data inputs, processes, and output commands. Errors due to translation errors, failed or faulty equipment, connections, and other components may cause a dynamic vehicle path to approach a dynamic safe zone or vice versa. If so, a warning message may be sent and processed by the motion control system, when the vehicle is responding to commands correctly, or actuator control, when the vehicle is not responding to commands correctly. Should a safe zone be redrawn to exclude the vehicle's path, a failure message is sent to the appropriate system for mitigation.

Devices, systems and methods for using system-level malfunction indicators to monitor the operation and resiliency of the autonomous driving system components are described. One example of a method for diagnosing a fault in a component of an autonomous vehicle includes receiving, from an electrical sub-component of the component, an electrical signal, receiving, from an electronic sub-component of the component, a message, and determining, based on the electrical signal and the message, an operational status of the component.

A method for testing at least one vehicle component of a vehicle includes placing a steering system of the vehicle in at least one test operating state, the steering system including a control unit which is at least one of electrically and electronically connected to a steering input unit to provide a steering torque in a normal operating state. The method further includes actuating an actuator of the steering system in the at least one operating state to carry out at least one driving maneuver to test the at least one vehicle component without an active steering demand on a manual steering control of the steering input unit.

A model of a system of an intelligent vehicle is trained and optimized using system operation data of the intelligent vehicle in a normal running state. The system operation data of the intelligent vehicle in a running state is collected in real time. Sensor data of the system operation data is de-noised, and feature extraction and screening are performed for a fatal sensor fault to reconstruct the system operation data. The reconstructed system operation data is inputted into the trained model to output system state data of the intelligent vehicle in the running state. The system state data is compared with a set threshold. If the system state data exceeds the set threshold, an actuator corresponding to the system state data is determined to have a fault. In addition, a system for a fault diagnosis of the intelligent vehicle is further provided.

Provided is a vehicle control device which makes it possible, in a redundant configuration, to make use of a normally operating part in a failed system. A vehicle control device having a redundant configuration includes a task switching function unit configured to switch tasks to be executed when an abnormality is detected. The task switching function unit being configured to, when a diagnostic function unit determines that an abnormality has occurred in a unit of a host system, cause the unit of the failed system to stop calculation of control variable, and stop drive control for a control object, and then execute calculation other than the calculation of the control variable of the host system, and the drive control for an electric motor, so that the calculation unit of the failed system can take over at least a part of calculation of a normal system or another on-vehicle device.

A one-pedal control method and system for an autonomous vehicle, are configured for accelerating or decelerating a vehicle by use of a foldable accelerator pedal system when a foldable brake pedal system is broken down when a driver manually drives the autonomous vehicle or the mode is switched from an autonomous driving mode to a manual driving mode, and configured for implementing a fail-safe function by use of an integrated safety function of software.

A vehicle control apparatus includes a first control unit and a second control unit each configured to perform travel control of a vehicle based on a recognition result of an external recognition device group configured to obtain external information of the vehicle and a detection result of a vehicle information detection unit configured to obtain state information of an actuator group of the vehicle. In a case in which functional degradation of at least one of the external recognition device group, the actuator group, and the vehicle information detection unit is detected, based on the recognition result and the detection result, the first control unit determines contents of vehicle control in fallback control for restricting a travel control function of the vehicle and determines whether to execute the fallback control by one of the first control unit and the second control unit.