Abstract: The present disclosure relates to a device for monitoring a lighting unit which has a plurality of lighting sub-units, wherein for each lighting sub-unit or for each group of lighting sub-units includes a monitoring unit with a detector, which is configured to monitor a light output of the lighting sub-unit or group. The detector is further configured to monitor a trigger signal for controlling the lighting sub-unit or group and a power consumption of the lighting sub-unit or group, wherein a monitoring collector unit is arranged and coupled to all monitoring units in order to determine a total output from the data recorded by them.

Abstract: A method comprises identifying a set of radar data captured by at least one autonomous vehicle when the at least one autonomous vehicle was positioned in a lane of a roadway, and respective ground truth localization data of the at least one autonomous vehicle; filtering one or more objects identified via the set of radar data in accordance with an attribute of the one or more objects; generating a map layer to be included within a high definition map; identifying second set of radar data captured by a second autonomous vehicle when the at least one autonomous vehicle was positioned in the lane of the roadway, and respective ground truth localization data of the at least one autonomous vehicle; and localizing the second autonomous vehicle by executing a matching protocol to match an object within the second set of radar data with an object within the map layer.

Abstract: Systems for adjusting travel patterns for autonomous vehicles are disclosed. The system includes a plurality of sensor nodes positioned on a roadway, where each sensor node is operably coupled to at least one distinct sensor node. The system also includes an autonomous vehicle (AV) computing device(s) in electronic communication with the plurality of sensor nodes. The AV computing device(s) adjusts travel patterns for an autonomous vehicle on the roadway by detecting a first sensor node of the plurality of sensor nodes and obtaining positional data for the first sensor node and each subsequent sensor node. The computing device(s) then generate a modified travel pattern for the autonomous vehicle based on positional data for each sensor node, and/or accessibility status for each sensor node. Additionally, the computing device adjusts an initial travel pattern of the autonomous vehicle on the roadway to the modified travel pattern.

Abstract: The system related to a gated camera stereo system, a red-clear-clear-blue (RCCB) camera, at least one memory, and at least one processor communicatively coupled with the at least one memory. The processor is configured to: control the gated camera stereo system to emit a pulse of light at a predetermined wavelength, control a detector of the gated camera stereo system to capture light reflected from a scene after a preset time delay, The processor embeds depth data into two-dimensional gated images using a gate function based upon the captured light by the detector of the gated camera stereo system, control the RCCB camera to capture passive high dynamic range (HDR) images, extract features corresponding to the gated images and the passive HDR images, and fuse the extracted features corresponding to the gated images and the passive HDR images by cross-spectral matching for depth estimation.

Abstract: A computer-implemented method is disclosed. The method includes receiving, at an application server from an autonomous vehicle, telematics data, and based upon analysis of the received telematics data, determining, by the application server, that the autonomous vehicle needs to be rescued. The method includes verifying, by the application server, a health status of a communication connection with the autonomous vehicle. The method includes based upon the health status of the communication connection with the autonomous vehicle, performing, by the application server, a plurality of checks to identify one or more problems with a plurality of modules of the autonomous vehicle, and based upon the plurality of checks indicating no failure corresponding to the plurality of modules of the autonomous vehicle, dispatching a service vehicle to a location of the autonomous vehicle to rescue the autonomous vehicle.

Abstract: One or more processors of an autonomous vehicle can determine a surrogate trajectory for navigating the autonomous vehicle towards a target trajectory; generate a curvature target for the autonomous vehicle based on the surrogate trajectory, a lateral error, and a velocity of the autonomous vehicle, the curvature target defined in part by at least three points; and navigate the autonomous vehicle according to the curvature target.

Abstract: A system includes an in-vehicle controller configured to mount to a vehicle and connect to the drive system of the vehicle, and a remote control configured to send signals to the in-vehicle controller. The remote control includes an input device that is configured to receive commands from a user relating to operation of the vehicle to couple a trailer to the vehicle or decouple the trailer from the vehicle while the user is outside the vehicle and the vehicle and trailer are in a field of view of the user. The signals are based on the user commands and are configured to cause the in-vehicle controller to move the vehicle forward or backward; steer the vehicle; stop movement of the vehicle; and stop movement of the trailer.

Abstract: A method, comprises identifying a set of image data captured by at least one autonomous vehicle when the at least one autonomous vehicle was positioned in a lane of a roadway, and respective ground truth localization data of the at least one autonomous vehicle; determining a plurality of lane width values for the set of image data; labeling the set of image data with the plurality of lane width values, the plurality of lane width values representing a width of a lane in which the at least one autonomous vehicle was positioned; and training using the labeled set of image data, a machine learning model, such that the machine learning model is configured to predict a new lane width value for a new lane as output.

Abstract: A system for detecting and reporting cargo lost from a vehicle is disclosed. The system includes a plurality of sensors, and a cargo loss detection system including a processor and a memory device storing instructions that when executed by the processor configure the processor to: (i) receive, from the plurality of sensors, sensor data representing a plurality of cargo loss-related conditions; (ii) determine a cargo loss event has occurred based on a combination of more than one cargo loss-related conditions of the plurality of cargo loss-related conditions; and (iii) transmit a lost cargo detection signal to an external receiver.

Abstract: A blind zone visualization system for an autonomous vehicle is described. The system includes at least one visual sensor mounted on a roof of the autonomous vehicle and at least one mirror mounted on a hood of the autonomous vehicle. The at least one mirror redirects a portion of a field of view (FOV) of the at least one sensor into a volume of space in front of the autonomous vehicle. The system also includes at least one processor programmed to execute computer-readable instructions that cause the at least one processor to receive sensor data output from the at least one visual sensor and representative of the volume of space, detect, from the sensor data, no obstacle is present in the volume of space, and transmit a first signal to a control system of the autonomous vehicle to control the autonomous vehicle to travel forward through the volume of space.

Abstract: A steering angle detection assembly for measuring a steering angle of an autonomous vehicle is provided. The steering angle detection assembly includes at least one camera, at least one marker, and one or more processors in communication with at least one memory device. The steering angle detection assembly is operable to cause the at least one camera to capture one or more images of the marker. The steering angle detection assembly is operable to determine a position of the at least one marker in the one or more images and determine a steering angle of the autonomous vehicle.

Abstract: A system for determining a center of gravity of a trailer is described. The trailer includes a front portion, a rear portion, and a first side and a second side extending between the front and rear portion. The system includes one or more sensors, each having a field-of-view, associated with a vehicle and a processing device in communication with the one or more sensors. The processing device is configured to execute instructions stored in a memory to perform operations.

Abstract: Aspects of this technical solution can include generating, by a processor, a first metric corresponding to a first signal from one or more first sensors, the first sensor configured to detect a position of a fifth-wheel hitch of a vehicle with the fifth-wheel hitch in a first position, generating, by the processor, a second metric corresponding to a second signal from a drive assembly, the drive assembly configured to reposition of the fifth-wheel hitch, generating, by the processor and based on the first and second metrics, a third metric, the third metric corresponding to a second position of the fifth-wheel hitch with a predetermined load balancing configuration and transmitting, by the processor and responsive to a determination that the second position of the fifth-wheel hitch corresponds to a predetermined load balancing configuration of the vehicle, the third metric to the drive assembly.

Abstract: A perception system including at least one processor configured to perform operations including (i) identifying at least two construction markers on a road surface based upon analysis of sensor data from a plurality of sensors; (ii) based upon the identification of at least two construction markers, determining a starting point of a construction zone; (iii) for each construction marker identified past the starting point in the construction zone, (a) connecting each construction marker with a corresponding leading construction marker; (b) inserting each construction marker and a respective connection with the corresponding leading construction marker into a graph or a map; and (c) based upon each construction marker and the respective connection inserted into the graph or map, updating a drivable surface and a reference path; and (iv) upon not detecting a new construction marker past the starting point in the construction zone, determining the construction zone has ended is disclosed.

Abstract: A system for monitoring a load distribution of an autonomous vehicle is provided. The system includes a processor in communication with a memory device. The processor is configured to receive weight data from a grid of weight sensors disposed on a cargo bed surface of the autonomous vehicle, generate a weight distribution map of the cargo bed surface based on the received weight data, the weight distribution map including an array of weight values, and control operation of the autonomous vehicle based in part on the generated weight distribution map.

Abstract: Systems and methods for training and executing machine learning models to generate lane index values are disclosed. A method includes identifying a set of image data captured by at least one autonomous vehicle when the at least autonomous vehicle is positioned in a lane of a roadway and respective ground truth localization data; determining a plurality of lane index values for the set of image data based on the ground truth localization data; labeling the set of image data with the plurality of lane index values, the lane index values representing a number of lanes from a leftmost or rightmost lane to the lane in which the at least one autonomous vehicle was positioned; and training, using the labeled set of image data, a plurality of machine learning models that generate a left lane index value and a right lane index value as output.

Abstract: A method for producing a suitable distance between an autonomous vehicle and a second vehicle. The method includes recording data of an environment including the second vehicle driving ahead of the autonomous vehicle along a direction of travel, the data being recorded by a sensor system positioned relative to the autonomous vehicle in the direction of travel and in communication with a computing unit. The method includes detecting a potentially dangerous situation by the sensor system based on a distance between the autonomous vehicle and the second vehicle. The method includes adjusting the autonomous vehicle to maintain the suitable between the autonomous vehicle and the second vehicle.

Abstract: A method of controlling an autonomous vehicle, including: collecting perception data representing a perceived environment of the vehicle using a perception system on board the autonomous vehicle; comparing the perception data collected with digital map data; and modifying operation of the vehicle based on an amount of difference between the perception data and the digital map data.

Abstract: An autonomous vehicle including a network of sensors including a plurality of acoustic sensors and a plurality of visual sensors, at least one processor, and at least one memory storing instructions is disclosed. The instructions, when executed by the at least one processor, cause the at least one processor to: (i) generate spatial beamforming maps locating a sound source based upon acoustic signals received at the plurality of acoustic sensors; (ii) identify a type of an object generating the acoustic signals received at the plurality of acoustic sensors based upon comparison of the acoustic signals with a plurality of acoustic signals and respective objects stored in a dataset; and (iii) generate feature maps for an application in an autonomous vehicle driving by enhancing visualization maps generated based upon visual signals received by the plurality of visual sensors.

Abstract: Systems and methods for training artificial intelligence models based on sequences of image data are disclosed. The techniques described herein include generating, using an artificial intelligence model, a respective classification and a respective bounding box for an object depicted in each image of a sequence of images captured during operation of an autonomous vehicle; tracking the object in the sequence of images based on the respective bounding box of each image of the sequence of images and a tracking identifier corresponding to the object; determining a correction to the respective classification of an image of the sequence of images responsive to tracking the object in the sequence of images; and training the artificial intelligence model based on the correction.