Autonomous driving computing systems in autonomous vehicles can include semiconductor chips with varying degrees of heat dissipation. The semiconductor chips are mounted on a printed circuit board, which together may be packaged in an enclosure assembly. The enclosure assembly may be mounted in the autonomous vehicle. Having a compact or low-profile enclosure assembly, and the harsh operating environment of the autonomous vehicle may pose a challenge for cooling the semiconductor chips and design of the enclosure assembly. Some cooling mechanisms can be difficult to manufacture, assemble, and/or service. An impeller-based intake subassembly can be combined with an air guidance plate that has a hollow structure that can direct air from the intake subassembly towards the printed circuit board through exhaust slots extending from the hollow structure, and air pathways to direct the air across the printed circuit board from the exhaust slots towards an impeller-based exhaust subassembly.

An example method includes (a) obtaining an object detection from a perception system that describes an object in an environment of the autonomous vehicle; (b) obtaining, from a reference dataset, a label that describes a reference position of the object in the environment; (c) determining a plurality of component divergence values respectively for a plurality of divergence metrics, wherein a respective divergence value characterizes a respective difference between the object detection and the label; (d) providing the plurality of component divergence values to a machine-learned model to generate a score that indicates an aggregate divergence between the object detection and the label, wherein the machine-learned model includes a plurality of learned parameters defining an influence of the plurality of component divergence values on the score; (e) evaluating a quality of a match between the object detection and the label based on the score.

An example method includes (a) obtaining sensor data descriptive of an environment of an autonomous vehicle; (b) obtaining a plurality of travel way markers from map data descriptive of the environment; (c) determining, using a machine-learned object detection model and based on the sensor data, an association between one or more travel way markers of the plurality of travel way markers and an object in the environment; and (d) generating, using the machine-learned object detection model, an offset with respect to the one or more travel way markers of a spatial region of the environment associated with the object.

A passive vehicular heatstroke prevention system monitors carbon dioxide (CO.sub.2) and infrared (IR) energy levels to determine whether a child is present inside a closed vehicle, and, if so, monitors the temperature in the vehicle and, if the temperature in the vehicle exceeds at least one preset critical value, automatically lowers the temperature in the vehicle and contacts the driver/caregiver and/or emergency personnel. The system detects the presence of a child in the closed vehicle by detecting a critical level of carbon dioxide in the air within the vehicle, while monitoring the interior vehicle temperature and takes corrective action to prevent the temperature from exceeding a preset value, such as by activating the vehicle's air conditioning unit and lowering the vehicle's windows, as well as contacting the driver/caregiver and/or emergency personnel.

The disclosure relates to methods, systems, and apparatuses for virtual sensor data generation and more particularly relates to generation of virtual sensor data for training and testing models or algorithms to detect objects or obstacles. A method for generating virtual sensor data includes simulating, using one or more processors, a three-dimensional (3D) environment comprising one or more virtual objects. The method includes generating, using one or more processors, virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining, using one or more processors, virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth comprises a dimension or parameter of the one or more virtual objects. The method includes storing and associating the virtual sensor data and the virtual ground truth using one or more processors.

The disclosure relates to methods, systems, and apparatuses for virtual sensor data generation and more particularly relates to generation of virtual sensor data for training and testing models or algorithms to detect objects or obstacles, such as wheel stops or parking barriers. A method for generating virtual sensor data includes simulating a three-dimensional (3D) environment comprising one or more objects. The method includes generating virtual sensor data for a plurality of positions of one or more sensors within the 3D environment. The method includes determining virtual ground truth corresponding to each of the plurality of positions, wherein the ground truth includes information about at least one object within the virtual sensor data. The method also includes storing and associating the virtual sensor data and the virtual ground truth.

The described aspects and implementations enable privacy-respecting detection, separation, and localization of sounds in vehicle environments. The techniques include obtaining, using audio detector(s) of a vehicle, a sound recording that includes a plurality of elemental sounds (ESs) in a driving environment of the vehicle, and processing, using a sound separation model, the sound recording to separate individual ESs of the plurality of ESs. The techniques further include identifying a content of individual ESs and causing a driving path of the vehicle to be modified in view of the identified content of the individual ESs. Further techniques include rendering speech imperceptibly by redacting temporal portions of the speech, using sound recognition models to identify and discard recordings of speech, and driving at speeds that exceed threshold speeds at which speech becomes imperceptible from noise masking.

The invention relates to a method and to a device, in particular a control and evaluation unit, for recognizing a water passage or a high water level for a vehicle, which has, as a drive, an internal combustion engine having an exhaust train, in which the functionality of an emission control system is monitored or controlled by at least one exhaust sensor and the exhaust sensor is operated at least intermittently at high temperatures and has thermal shock susceptibility by design. According to the invention, a water recognition criterion is determined based on one or a plurality of distance sensors and, at critical values of the water level which are predicted or have already been reached, protective measures are initiated for the emissions control system of the vehicle or for the exhaust sensor or exhaust sensors arranged in the exhaust duct. Damage to exhaust sensors or to components of the emissions control system as a result of the severe cooling upon contact with water can thus be minimized. In addition, misinformation of the exhaust sensors due to a thermal shock and a possible accompanying malfunction can also be recognized by said anticipatory protective measures and correspondingly suppressed.

The invention relates to a method for operating a motor vehicle, in which by at least one ultrasonic sensor, operated in the active operation mode, of an ultrasonic sensor device of the motor vehicle ultrasonic waves are emitted into an environmental region of the motor vehicle, wherein the motor vehicle as hybrid vehicle is equipped with an internal combustion engine (and an electric drive machine and in the active operation mode of the ultrasonic sensor arranged on a rear part of the motor vehicle the motor vehicle at least temporarily is operated by means of the electric drive machine. The invention also relates to a motor vehicle.

A system and method for coordination between at least two participating vehicles for peer-to-peer trade of the vehicles' positions including a local device on the participating vehicle that measures and transmits at least one output signal; a computing device configured to receive the at least one output signal from the device and display the at least one output signal in real-time; a graphical user interface on the computing device that allows a system administrator to view and customize options for monitoring the at least one output signal; and a hosted server that initiates a peer-to-peer trade of the participating vehicle's position based on determination of a multitude of factors, wherein the local device and the computing device are communicatively connected to each other via a communications network, and wherein the participating vehicle is human-driven, partially-automated, or fully-automated.