Abstract: A self-driving safety evaluation method, including determining RB based on a risk value of a vehicle in a shadow driving mode in a first measurement unit, where RB is a risk value of the vehicle in the shadow driving mode in a plurality of measurement units, and determining RC based on a risk value of the vehicle in a self-driving mode based on a preset route in the first measurement unit, where RC is a risk value of the vehicle in the self-driving mode based on the preset route in the measurement units, where RB and RC are used to determine whether safety of the vehicle in the self-driving mode meets a requirement.

Abstract: A method and device for mitigating passenger-related item loss in a travel-for-hire context are disclosed. An item within a vehicle passenger region is identified, and the identified item is associated with an identified passenger. A presence of the identified item is detected within the vehicle cabin passenger region in response to detecting an exit of the identified passenger, and an announcement message is generated based on the presence of the identified item within the vehicle cabin passenger region.

Abstract: A vehicle-mounted device upgrade method and a related device. The method may be applied to a vehicle-mounted system, a vehicle-mounted control device and one or more to-be-upgraded vehicle-mounted devices, and the method may include: obtaining, by the vehicle-mounted control device, a vehicle-mounted upgrade package, where the vehicle-mounted upgrade package includes a plurality of upgrade files, and each upgrade file is used to upgrade at least one to-be-upgraded vehicle-mounted device; performing, by the vehicle-mounted control device, security verification on the plurality of upgrade files; and sending, by the vehicle-mounted control device, a target upgrade file to a target to-be-upgraded vehicle-mounted device that is to be upgraded by using the target upgrade file, where the target upgrade file is an upgrade file on which security verification succeeds in the plurality of upgrade files. According to this application, the vehicle-mounted device can be securely and efficiently upgraded.

Abstract: A driving intention determining method includes obtaining status information of traffic targets in a driving environment, where the traffic targets include a traffic target in a moving state and traffic targets in a static state, and status information of the traffic targets in a static state includes at least indication information of a traffic sign and road boundary information, determining a risk field of the driving environment based on the status information of the traffic targets in the driving environment, for any other vehicle in the driving environment, determining a driving track of the other vehicle in the driving environment based on the risk field, and determining driving intention of the other vehicle based on the driving track of the other vehicle in the driving environment.

Abstract: Embodiments disclose a vehicle-mounted device upgrade method and a related device. The method may be applied to an intelligent vehicle, the intelligent vehicle includes a vehicle-mounted control device, and the method may include: receiving, by the vehicle-mounted control device, a first partial key sent by the communications device; restoring, by the vehicle-mounted control device, a first key by using the first partial key and a second partial key that is stored on the vehicle-mounted control device; and performing, by the vehicle-mounted control device, secure processing on a first upgrade file by using the first key, to obtain the securely processed first upgrade file, where the secure processing includes generating first message authentication code (MAC), and the securely processed first upgrade file includes the first upgrade file and the first MAC. According to this application, the vehicle-mounted device can be securely and efficiently upgraded.

Abstract: A self-driving safety evaluation method, including determining RB based on a risk value of a vehicle in a shadow driving mode in a first measurement unit, where RB is a risk value of the vehicle in the shadow driving mode in a plurality of measurement units, and determining RC based on a risk value of the vehicle in a self-driving mode based on a preset route in the first measurement unit, where RC is a risk value of the vehicle in the self-driving mode based on the preset route in the measurement units, where RB and RC are used to determine whether safety of the vehicle in the self-driving mode meets a requirement.

Abstract: A method and device for mitigating passenger-related item loss in a travel-for-hire context are disclosed. An item within a vehicle passenger region is identified, and the identified item is associated with an identified passenger. A presence of the identified item is detected within the vehicle cabin passenger region in response to detecting an exit of the identified passenger, and an announcement message is generated based on the presence of the identified item within the vehicle cabin passenger region.

Abstract: A vehicle positioning method and apparatus, where the vehicle positioning method includes obtaining measurement information within preset angle coverage at a current frame moment using a measurement device, determining, based on the measurement information, current road boundary information corresponding to the current frame moment, determining first target positioning information based on the current road boundary information, determining road curvature information based on the current road boundary information and historical road boundary information, and outputting the first target positioning information and the road curvature information.

Abstract: A vehicle-mounted device upgrade method and a related device. The method may be applied to a vehicle-mounted system, a vehicle-mounted control device and one or more to-be-upgraded vehicle-mounted devices, and the method may include: obtaining, by the vehicle-mounted control device, a vehicle-mounted upgrade package, where the vehicle-mounted upgrade package includes a plurality of upgrade files, and each upgrade file is used to upgrade at least one to-be-upgraded vehicle-mounted device; performing, by the vehicle-mounted control device, security verification on the plurality of upgrade files; and sending, by the vehicle-mounted control device, a target upgrade file to a target to-be-upgraded vehicle-mounted device that is to be upgraded by using the target upgrade file, where the target upgrade file is an upgrade file on which security verification succeeds in the plurality of upgrade files. According to this application, the vehicle-mounted device can be securely and efficiently upgraded.

Abstract: A system for reducing analog noise in a noisy channel, comprising: an interface configured to receive analog channel output comprising a stream of noisy binary codewords of a linear code; and a computation component configured to perform the following: for each analog segment of the analog channel output of block length: calculating an absolute value representation and a sign representation of a respective analog segment, calculating a multiplication of a binary representation of the sign representation with a parity matrix of the linear code, inputting the absolute value representation and the outcome of the multiplication into a neural network for acquiring a neural network output, and estimating a binary codeword by component-wise multiplication of the neural network output and the sign representation.

Abstract: A system for reducing analog noise in a noisy channel, comprising: an interface configured to receive analog channel output comprising a stream of noisy binary codewords of a linear code; and a computation component configured to perform the following: for each analog segment of the analog channel output of block length: calculating an absolute value representation and a sign representation of a respective analog segment, calculating a multiplication of a binary representation of the sign representation with a parity matrix of the linear code, inputting the absolute value representation and the outcome of the multiplication into a neural network for acquiring a neural network output, and estimating a binary codeword by component-wise multiplication of the neural network output and the sign representation.

Abstract: A driving intention determining method includes obtaining status information of traffic targets in a driving environment, where the traffic targets include a traffic target in a moving state and traffic targets in a static state, and status information of the traffic targets in a static state includes at least indication information of a traffic sign and road boundary information, determining a risk field of the driving environment based on the status information of the traffic targets in the driving environment, for any other vehicle in the driving environment, determining a driving track of the other vehicle in the driving environment based on the risk field, and determining driving intention of the other vehicle based on the driving track of the other vehicle in the driving environment.

Abstract: A method and device for mitigating passenger-related item loss in a travel-for-hire context are disclosed. An item within a vehicle passenger region is identified, and associated the identified item with a passenger identified by a passenger identifier. A vehicle cabin inventory database is updated with an entry based on the identified item associated with the passenger identifier. A presence of the identified item is detected within the vehicle cabin passenger region when a passenger exit event occurs, and message data is generated including the entry that relates to the identified item based on the presence of the identified item within the vehicle cabin passenger region.

Abstract: The empty vs. non-empty status of a cargo container is detected based on boundary analysis of a wide-angle image obtained by a monocular vision system. The wide-angle image is warped to remove distortion created by the vision system optics, and the resulting image is edge-processed to identify the boundaries of the container floor. If package boundaries are detected within the floor space, or a large foreground package is blocking the floor boundaries, the cargo status is set to non-empty. If floor boundaries are detected and no package boundaries are detected within the floor space, the cargo status is set to empty.

Abstract: Occupant displacement corresponding to sensed acceleration in a crash event is determined and used to enable and disable deployment of supplemental restraints based on crash severity. The determined occupant displacement is compared to a first threshold calibrated to discriminate against disturbances due to rough roads and other non-crash events, and a second threshold calibrated to discriminate against non-deployment crash events. Deployment of supplemental restraints based on crash severity is enabled only when the determined displacement is between the first and second thresholds.

Abstract: Impacts with a vehicle body panel are detected by sensing airflow inboard of the vehicle body panel. The airflow can be measured by heated element sensor, a Pitot tube sensor, a venturi sensor or other airflow-responsive sensor. For side impact detection, the sensor is located in a door or pillar on the side of the vehicle; for frontal impact detection, the sensor may be located behind the front bumper. Multiple sensors mounted in distributed locations can be used to determine the location and extent of an impact.

Abstract: A deployment method for a supplemental restraint system having multiple distributed acceleration sensors dynamically classifies each crash event based on relationships among the acceleration signals. A severity threshold is selected based on the instant crash classification, and a measure of crash severity is compared to the selected severity threshold to determine if the restraints should be deployed. The measure of crash severity is determined by computing individual measures of crash severity for the various frontal acceleration sensors and selecting the highest of the individual measures.

Abstract: The collision of a vehicle with a pedestrian is detected by the presence of a foreign object in a sensing zone above the hood of the vehicle within a prescribed time of an initial impact with the bumper of the vehicle. The initial impact is detected with an acceleration sensor disposed in or near the front bumper and the sensing zone is defined by object detection sensors disposed on the hood or behind the windshield of the vehicle. Vehicle speed is used to discriminate against events that occur while the vehicle is stationary or moving very slowly.

Abstract: A supplemental restraint deployment method utilizes measured vehicle speed and acceleration and the output of a closing velocity sensor that detects the presence and closing rate of an approaching object prior to contact with the vehicle. The closing velocity and vehicle speed are utilized for classification of an impending crash event, where the deployment options vary depending on the crash classification. In the ensuing crash event, a classification-dependent algorithm is executed to determine if, when and what level of restraint deployment is warranted based on measures of actual crash severity. Additionally, the algorithm is reset when the calculated change in vehicle velocity reaches the initial closing velocity.

Abstract: The empty vs. non-empty status of a cargo container is detected based on boundary analysis of a wide-angle image obtained by a monocular vision system. The wide-angle image is warped to remove distortion created by the vision system optics, and the resulting image is edge-processed to identify the boundaries of the container floor. If package boundaries are detected within the floor space, or a large foreground package is blocking the floor boundaries, the cargo status is set to non-empty. If floor boundaries are detected and no package boundaries are detected within the floor space, the cargo status is set to empty.