Abstract: A system includes a processor and a memory storing instructions executable by the processor to actuate a component upon determining that a hydrophobic coating of a surface is degraded based on a comparison of a characteristic of a liquid droplet with a threshold value.

Abstract: A sensor apparatus includes a sensor window; a first nozzle adjacent to the sensor window and oriented to blow across the sensor window, the first nozzle positioned below the sensor window and in a first horizontal direction away from the sensor window, the first nozzle being slot-shaped with a first length and a first thickness; and a second nozzle adjacent to the first nozzle and oriented to blow across the sensor window, the second nozzle positioned below the sensor window and in the first horizontal direction away from the sensor window, the second nozzle being slot-shaped with a second length and a second thickness. The second nozzle is farther from the sensor window in the first horizontal direction than the first nozzle, and the first length of the first nozzle is greater than the second length of the second nozzle.

Abstract: An assembly includes an inlet tube and an outlet tube. The assembly includes a solenoid assembly having a plunger movable between an open position in which fluid is permitted to flow from the inlet tube to the outlet tube and a closed position in which fluid is inhibited from flowing from the inlet tube to the outlet tube, the solenoid assembly having an induction coil surrounding the plunger. The assembly includes a Hall effect sensor that detects a magnetic field of the solenoid assembly. The assembly includes a computer in communication with the Hall effect sensor, the computer having a processor and memory that stores instructions executable by the processor to identify a resistance of the induction coil based on data from the Hall effect sensor, and to determine whether the plunger is at the closed position based on the identified resistance of the induction coil.

Abstract: An assembly includes an inlet tube. The assembly includes a first outlet tube. The assembly includes a solenoid assembly having a plunger movable between an open position in which fluid is permitted to flow from the inlet tube to the outlet tube and a closed position in which fluid is inhibited from flowing from the inlet tube to the outlet tube. The solenoid assembly has a spring urging the plunger to the closed position. The solenoid assembly has a strain gage fixed to the spring. A strain detected by the strain gage indicates whether the plunger is at the closed position.

Abstract: An assembly includes an inlet tube and an outlet tube. The assembly includes a solenoid assembly having a plunger movable between an open position in which fluid is permitted to flow from the inlet tube to the outlet tube and a closed position in which fluid is inhibited from flowing from the inlet tube to the outlet tube. The solenoid assembly has a spring urging the plunger to the closed position. The assembly includes a first pressure sensor positioned to be compressed when the plunger is moved toward the open position. Pressure detected by the first pressure sensor indicates whether the plunger is at the open position. The assembly includes a second pressure sensor positioned to be compressed when the plunger is moved toward the closed position. Pressure detected by the second pressure sensor indicates whether the plunger is at the closed position.

Abstract: A sensor assembly includes a first sensor window defining a first plane, a second sensor window fixed relative to the first sensor window and defining a second plane different than the first plane, and a nozzle positioned to deliver fluid to the first and second sensor windows. The nozzle is translatable along a first axis, rotatable about the first axis, and rotatable about a second axis transverse to the first axis.

Abstract: Systems, methods, and computer-readable media are disclosed for automated multimodal delivery. Example methods may include determining information associated with the delivery; determining, based on at least a first portion of the information, that a first confidence level indicative of a delivery capability using a first vehicle is above a first threshold; and determining, based on at least a second portion of the information, a second confidence level indicative of a delivery preference for delivery using the first vehicle relative to a second vehicle.

Abstract: Data about operating parameters external to a vehicle can be input to a neural network that outputs at least one profile defining at least one of a cleaning protocol or a cooling protocol for a vehicle sensor, wherein the operating parameters include one or more of current weather conditions, future weather conditions, images indicative of a current weather condition, city infrastructure, duration of a route to be traversed, a time period to traverse the route, and vehicle location. Operation of at least one of a cleaning device or a cooling device can be initiated according to the at least one of the cleaning protocol or the cooling protocol when the operating parameters to the at least one profile.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to input strain data measuring mechanical strain on a vehicle camera and operation data of a vehicle component, the operation data describing at least one of an output or a state of the vehicle component, to a machine learning program that outputs a displacement of the vehicle camera from a neutral position based on the strain data and the operation data. The instructions further include instructions to identify a transformation matrix that transforms data from the vehicle camera to a coordinate system of the vehicle camera in the neutral position based on the output displacement of the vehicle camera, to apply the transformation matrix to data collected by the vehicle camera to generate transformed data, and to actuate one of the vehicle component or a second vehicle component based on the transformed data.

Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to identify a contaminant on a lens of a sensor upon determining a force applied to the lens based on an electric current exceeding a threshold and to actuate a cleaning component to remove the contaminant from the lens.

Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to identify a sensor of a vehicle with a robotic arm, capture a plurality of images of the sensor with an unmanned aerial vehicle, and actuate the robotic arm to perform maintenance on the sensor upon inputting the plurality of images to an image recognition program and obtaining output that the sensor requires maintenance.

Abstract: Systems and methods for exterior signage evaluation are disclosed herein. An example method includes receiving images of an exterior signage area of an exterior surface of a first vehicle, the images being obtained by the first vehicle, a second vehicle camera or an infrastructure camera, determining current environmental conditions around the first vehicle, processing the images of the exterior signage area using the current environmental conditions, wherein processing includes comparing an expected appearance of the exterior signage area with an actual appearance of the exterior signage area to determine a visual appearance quality of the exterior signage area, and presenting a message on a display that includes the visual appearance quality.

Abstract: A system, comprising a computer that includes a processor and a memory, the memory storing instructions executable by the processor to input second vehicle sensor data received via one or more of vehicle-to-vehicle (V-to-V) and vehicle-to-infrastructure (V-to-I) networking into a generative query neural network (GQN) trained to generate second vehicle viewpoint data and predict a path for a second vehicle based on the second vehicle viewpoint data with a reinforcement learning deep neural network (RLDNN). The computer can be further programmed to obtain a confidence for the predicted second vehicle path from a Bayesian framework applied to the RLDNN and determine a first vehicle path based on the predicted second vehicle path and the confidence.

Abstract: The present disclosure relates to a system and a method for addressing an error in a localization system that includes monitoring a plurality of sensors of a driver assistance system in real-time, with each sensor generating a data stream. The method further includes identifying a sensor having an anomalous data stream and calculating a primary localization and a backup localization. The primary localization calculation includes the anomalous data stream and the backup localization calculation does not include the anomalous data stream. Further, the method includes executing an action when the backup localization error estimate exceeds a threshold.

Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to predict a user arrival time based on data of a user and a user origin location, deactivate a propulsion of the vehicle upon arriving at the user origin location, and deactivate one or more additional vehicle components based on the user arrival time.

Abstract: A sensor system includes a sensor including a sensor window, a pump, a liquid nozzle aimed at the sensor window, a valve positioned and operable to control fluid flow from the pump to the liquid nozzle, and a computer communicatively coupled to the valve. The computer is programmed to, in response to detecting an obstruction on the sensor window, continuously activate the pump for a first time period; and during the first time period, operate the valve according to a preset sequence. The preset sequence includes opening and then closing the valve at least twice during the first time period.

Abstract: A sensor system includes a pump, a valve supplied from the pump, a sensor fixed relative to the pump, a nozzle supplied from the valve and aimed at the sensor, and a computer communicatively coupled to the pump, the valve, and the sensor. The computer is programmed to instruct the pump to operate; while the pump is operating, instruct the valve to close; receive data from the sensor while the pump is operating and the valve is instructed to be closed; and set a flag upon determining, based on the data received from the sensor, that the nozzle is outputting fluid onto the sensor.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to input strain data measuring mechanical strain on a vehicle camera and operation data of a vehicle component, the operation data describing at least one of an output or a state of the vehicle component, to a machine learning program that outputs a displacement of the vehicle camera from a neutral position based on the strain data and the operation data. The instructions further include instructions to identify a transformation matrix that transforms data from the vehicle camera to a coordinate system of the vehicle camera in the neutral position based on the output displacement of the vehicle camera, to apply the transformation matrix to data collected by the vehicle camera to generate transformed data, and to actuate one of the vehicle component or a second vehicle component based on the transformed data.

Abstract: A sensor system includes a sensor including a sensor window; a nozzle aimed at the sensor window; a supply line to supply fluid to the nozzle; a primary reservoir to supply fluid to the supply line; a first valve actuatable to inject fluid from a first reservoir into the supply line; a second valve actuatable to inject fluid from a second reservoir into the supply line; a third valve actuatable to inject fluid from a third reservoir into the supply line; and a computer communicatively coupled to the sensor and the valves. The computer is programmed to actuate the first valve in response to determining a first condition based on data from the sensor, actuate the second valve in response to determining a second condition based on data from the sensor, and actuate the third valve in response to determining a third condition based on data from the sensor.

Abstract: A sensor apparatus includes a cylindrical sensor window defining an axis, and a plurality of at least three tubular segments fixed relative to the sensor window. Each tubular segment is elongated circumferentially relative to the axis. The tubular segments collectively form a ring substantially centered around the axis. Each tubular segment includes a plurality of nozzles. Each nozzle includes a first opening and a second opening. Each of the first openings has a direction of discharge in a radially inward and axial direction forming a first angle with the axis, and each of the second openings has a direction of discharge in a radially inward and axial direction forming a second angle with the axis. The second angle is different than the first angle.