Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to receive radar data from an ultrawideband radar in a passenger compartment of a vehicle, determine a starting-time for a time-window based on a second derivative of the radar data, identify a motion inside the passenger compartment based on the radar data received during the time-window, and actuate a component of the vehicle based on the identification of the motion.

Abstract: A method for a metric determination includes extracting one or more features from a plurality of images and classifying the plurality of images based on the extracted one or more features to form one or more clusters of images, wherein the classifying is performed at least in part based on machine learning. Hypothesis testing is performed on the one or more clusters of images based on one or more production factors and variations are identified in the one or more features resulting from the hypothesis testing. One or more production metrics are determined based on the identified variations.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive a plurality of radar data streams from a respective plurality of ultrawideband (UWB) radars in a passenger compartment of a vehicle, generate a combined radar data stream by averaging the radar data streams together, measure a biometric characteristic of an occupant of the passenger compartment based on the combined radar data stream, and actuate a component of the vehicle based on the biometric characteristic.

Abstract: A power management system for a vehicle includes a power source, switching circuitry, and a first converter electrically interposing the power source and the switching circuitry. The first converter has a first power output threshold. A second converter electrically interposes the power source and the switching circuitry. The second converter has a second power output threshold lower than the first power output threshold. Control circuitry is configured to, in response to a key-off state of the vehicle, control the switching circuitry to supply power to at least one load, compare the power drawn from the second converter by the at least one load to the second power output threshold, and communicate an output to limit the power drawn from the second converter by the at least one load in response to the comparison.

Abstract: A first vehicle including a detection unit, a transceiver and a processor is disclosed. The detection unit may be configured to detect a distance between the first vehicle and a second vehicle located adjacent to the first vehicle. The transceiver may be configured to receive a second vehicle door dimension. The processor may be configured to compare the distance with the second vehicle door dimension, and determine that the second vehicle door dimension may be greater than the distance. Responsive to determining that the second vehicle door dimension may be greater than the distance, the processor may control an operation of a first vehicle component.

Abstract: A vehicle-bumper assembly includes a vehicle bumper and a rod having a first end fixed to the vehicle bumper and a second end spaced from the first end along an elongated axis of the rod. A collar is fixed to the rod between the first end of the rod and the second end of the rod, the collar including a pyrotechnically-activated release releasable from the rod. A spring is retained on the rod between the collar and the vehicle bumper.

Abstract: An electrified vehicle and associated method for controlling an electrified vehicle having an electric machine powered by a traction battery include an autoencoder trained with training data indicative of a remaining driving range of the traction battery. The trained autoencoder processes vehicle operating data to generate a reference data record and determines a value indicative of a similarity between the vehicle operating data and the reference data record. The autoencoder generates an output data record if the value indicative of the similarity is below a predetermined threshold value. The output data record may be used to display an alert or message to a vehicle occupant and/or control the vehicle to reduce power consumption to increase vehicle driving range.

Abstract: A Controller Area Network (CAN) message is received from an application emulator. Based on a first file that includes, for each of a plurality of CAN message names, an ECU event identifier, an ECU event included in the CAN message is determined. Based on a second file that maps the ECU event to a hardware abstraction layer (HAL) property, a hardware abstraction layer is invoked; the CAN message is sent to the HAL, which responds to the CAN message.

Abstract: Systems and methods for managing cathode stoichiometry of an electrochemical cell are disclosed. A system may include a fuel cell, a compressor for supplying air to the fuel cell and an oxygen sensor proximate to or downstream of an outlet of a cathode chamber of the fuel cell. An operation speed of the compressor or flow rate of the air may be adjusted by, for example, a controller after receiving data from the sensor regarding the amount of residual oxygen. For example, the operation speed/flow rate may be increased or decreased to achieve a cathode stoichiometry of about 1.00.

Abstract: A robotic gripper apparatus for an automated additive manufacturing production system (AAMPS) includes a pair of gripping assemblies. Each gripping assembly is moveable in a transverse direction between a first position in which the gripping assembly engages an AAMPS workpiece and a second position in which the gripping assembly is disengaged from the AAMPS workpiece. Each gripping assembly includes a gripping element that defines an interface slot configured to receive the AAMPS workpiece. The interface slot is defined by a pair of transversely extending edges of the gripping element and a longitudinal edge of the gripping element disposed between the pair of transversely extending edges.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to, in response to one of a vehicle feature of a vehicle being active or the vehicle being in a preset geographic area, control acceleration and braking of the vehicle based on input from an input device of the vehicle according to a low-speed mode; and in response to the low-speed mode being inactive, control acceleration and braking of the vehicle not according to the low-speed mode. In the low-speed mode, acceleration occurs upon receiving input from the input device. In the low-speed mode, braking occurs upon not receiving input from the input device.

Abstract: A sensor assembly includes a housing, a sensor unit attached to the housing, and an elastomeric flap. The sensor unit includes a shell defining a vertical axis. The shell is rotatable around the axis relative to the housing. The shell includes a lower edge and extends upward along the axis from the lower edge. The housing includes an aperture centered on the axis. The aperture defines an airflow outlet from the housing radially inside the aperture relative to the axis. The sensor unit defines an airflow inlet radially inside the lower edge relative to the axis and positioned to receive airflow from the aperture. The aperture and the lower edge define a fixed gap extending around the axis. The flap is fixed to one of the housing or the sensor unit, and the flap extends across the fixed gap toward the other one of the housing or the sensor unit.

Abstract: Disclosed herein are systems, methods, and computer program products for operating a sensor system. The methods comprise: receiving, by a computing device, a track for an object; classifying, by the computing device, the track as an infant track or a mature track based on a type of sensor detection used to generate the track, a total number of cycles in which the lidar detections were generated, a total number of sensor detections included in the track, an object type associated with the track, an object speed, and/or a distance between the object and the sensor system; using, by the computing device, radar data to modify a speed of the track in response to the track being classified as an infant track.

Abstract: A computer that includes a processor and a memory, the memory including instructions executable by the processor to execute a multi-task learning (MTL) neural network that includes multi-task layers and single-task layers, and that is configured to receive an image as input to a first one of the multi-task layers and to output respective predictions for each of a plurality of tasks from respective ones of the single-task layers. Activation tensors can be output from the multi-task layers and can be provided as input to the single-task layers.

Abstract: A method for vehicle-to-vehicle charging includes identifying a plug-in hybrid electric vehicle (PHEV) for charging based on a determination that the PHEV's engine will start prior to the PHEV's battery being charged from an external power source. The method can include identifying a battery electric vehicle (BEV) to provide charging to the identified PHEV and transmitting location information to at least one of the PHEV or the BEV for navigating to the location of the other of the PHEV or the BEV. An electrical connection between the BEV and the PHEV is verified and a BEV to PHEV charging process is actuated.

Abstract: A recommendation system including a transceiver and a processor is disclosed. The transceiver may be configured to receive charging station information. The charging station information may include information associated with real-time waiting times and presence of fast chargers at a plurality of charging stations located in a geographical area. The processor may be configured to obtain a trigger signal, and estimate a vehicle charging time associated with each charging station based on the charging station information responsive to obtaining the trigger signal. The processor may further determine a recommended charging station, from the plurality of charging stations, based on the vehicle charging time. The processor may additionally output recommended charging station information responsive to determining the recommended charging station.

Abstract: A vehicle including a transceiver and a processor is disclosed. The transceiver may be configured to receive a charging station location. The processor is configured to determine that the vehicle is in a key-off mode. Responsive to determining that the vehicle is in the key-off mode, the processor may determine at least one of a vehicle State of Charge (SOC) level or a vehicle distance from the charging station location based on a current vehicle location. The processor may further determine that a predefined condition is met based on the at least one of the vehicle SOC level or the vehicle distance. Responsive to a determination that the predefined condition is met, the processor may select a vehicle feature from a plurality of vehicle features based on historical usage pattern of the plurality of vehicle features in the key-off mode, and enable a high-power mode of the vehicle feature.

Abstract: An electric vehicle charging recommendation system is disclosed. The system comprises a transceiver and a processor. The transceiver is configured to receive a request from a user interface associated with a vehicle user. The request includes one or more of vehicle route information and vehicle State of Charge (SoC) level. The processor is configured to generate a geofence, and obtain real-time operator charging amounts from charging station operators located in the geofence. The processor is further configured to determine that a charging demand in the geofence is less than a predetermined threshold value, and activate a first mode when the charging demand is less than the predetermined threshold value. The processor is further configured to generate a first list of recommended charging stations based on the real-time operator charging amounts responsive to the activation of the first mode, and transmit the first list to the user interface.

Abstract: A roof rack sub-assembly for a motor vehicle has a roof element, a body side component, a support foot for supporting a roof cross-beam which extends above the roof element in an assembly state of the roof rack sub-assembly and an anchor element for at least indirectly connecting the support foot to the body side component. In order to optimize the assembly of a roof rack in a vehicle with a glass roof, the body side component has a lock portion having a lock opening, wherein the anchor element can be guided with a key portion through the lock opening along a closure axis into an introduction position and can be rotated out of the introduction position about the closure axis into a locking position in which the key portion engages with the lock portion in the direction of the closure axis in a positive-locking manner.

Abstract: A charging management system including a transceiver and a processor is disclosed. The transceiver may be configured to receive vehicle inputs associated with a plurality of vehicles located in a geographical area. The processor may be configured to estimate a probability of vehicle charging at a charging station located in the geographical area for each vehicle based on the vehicle inputs. The processor may further estimate a count of vehicles, from the plurality of vehicles, having respective probabilities of vehicle charging at the charging station greater than a predefined probability threshold. Further, the processor may cause the charging station to operate in a charge limit operational mode when the count of vehicles exceeds a predefined estimated count threshold. The charging station may be configured to limit an amount of charge transferred to a vehicle when the charging station operates in the charge limit operational mode.