Abstract: Techniques for performing a sensor calibration using sequential data is disclosed. An example method includes receiving, from a first camera located on a vehicle, a first image comprising at least a portion of a road comprising lane markers, where the first image is obtained by the camera at a first time; obtaining a calculated value of a position of an inertial measurement (IM) device at the first time; obtaining an optimized first extrinsic matrix of the first camera by adjusting a function of a first actual pixel location of a location of a lane marker in the first image and an expected pixel location of the location of the lane marker; and performing autonomous operation of the vehicle using the optimized first extrinsic matrix of the first camera when the vehicle is operated on another road or at another time.

Abstract: Devices, systems, and methods for integrated predictive dynamic control of a vehicle powertrain in an autonomous vehicle are described. An example method for controlling a vehicle includes generating, based on performing an optimization on a blended smooth wheel domain fuel consumption map subject to a modified torque availability constraint, one or more wheel domain control commands, converting the one or more wheel domain control commands to one or more powertrain-executable engine domain control commands, and transmitting the one or more powertrain-executable engine domain control commands to a powertrain of the vehicle, the powertrain configured to operate a plurality of gears, wherein the one or more powertrain-executable engine domain control commands enable the vehicle to track a reference kinematic trajectory associated with a vehicle speed driving plan within a predetermined tolerance.

Abstract: Disclosed are devices, systems and methods for processing an image. In one aspect a method includes receiving an image from a sensor array including an x-y array of pixels, each pixel in the x-y array of pixels having a value selected from one of three primary colors, based on a corresponding x-y value in a mask pattern. The method may further include generating a preprocessed image by performing preprocessing on the image. The method may further include performing perception on the preprocessed image to determine one or more outlines of physical objects.

Abstract: An integrated housing assembly can be mounted on a roof of a vehicle, such as a semi-trailer truck. The integrated housing assembly includes a main enclosure that includes four sides, a top panel, and a bottom panel. One of the four sides is a front panel that is inclined towards the ground. The main enclosure includes one or more cavities. A front panel of the integrated housing assembly includes one or more openings to allow cameras or sensors to be placed within the one or more cavities and behind the one or more opening. The cameras or sensors cameras can be clamped at a downward angle within multiple lock apparatus. The angled front panel and the inclined cameras or sensors within the lock apparatus allow the cameras or sensors to obtain images or sensor data from one or more regions of interest at some distance from the front of the vehicle.

Abstract: A system and method for generating simulated vehicles with configured behaviors for analyzing autonomous vehicle motion planners are disclosed. A particular embodiment includes: receiving perception data from a plurality of perception data sensors; obtaining configuration instructions and data including pre-defined parameters and executables defining a specific driving behavior for each of a plurality of simulated dynamic vehicles; generating a target position and target speed for each of the plurality of simulated dynamic vehicles, the generated target positions and target speeds being based on the perception data and the configuration instructions and data; and generating a plurality of trajectories and acceleration profiles to transition each of the plurality of simulated dynamic vehicles from a current position and speed to the corresponding target position and target speed.

Abstract: A system and method for path planning of autonomous vehicles based on gradient are disclosed. A particular embodiment includes: generating and scoring a first suggested trajectory for an autonomous vehicle; generating a trajectory gradient based on the first suggested trajectory; generating and scoring a second suggested trajectory for the autonomous vehicle, the second suggested trajectory being based on the first suggested trajectory and a human driving model; and outputting the second suggested trajectory if the score corresponding to the second suggested trajectory is within a score differential threshold relative to the score corresponding to the first suggested trajectory.

Abstract: A method of operating an autonomous vehicle includes detecting, based on an input received from a sensor of an autonomous vehicle that is being navigated by an on-board computer system, an occurrence of a driving event, making a determination by the on-board computer system, upon the detecting the occurrence of the driving event, whether or how to alter the path planned by the on-board computer system according to a set of rules, and performing further navigation of the autonomous vehicle based on the determination until the driving event is resolved. The driving event may include a presence of an object in a shoulder area of the road. The driving event may include accumulation of more than a certain number of vehicles behind the autonomous vehicle. The driving event may include a slow vehicle ahead of the autonomous vehicle. The driving event may include a do-not-change-lane zone is within a threshold.

Abstract: Techniques are described for estimating road friction between a road and tires of a vehicle. A method includes receiving, from a temperature sensor on a vehicle, a temperature value that indicates a temperature of an environment in which a vehicle is operated, determining a first range of friction values that quantify a friction between a road and tires of a vehicle based on a function of the temperature value and an extent of precipitation in a region that indicate a hazardous driving condition, obtaining, from the first range of friction values, a value that quantifies the friction between the road and the tires of the vehicle, where the value is obtained based on a driving related behavior of the vehicle, and causing the vehicle to operate on the road based on the value obtained from the first range of friction values.

Abstract: An integrated housing assembly can be mounted on a roof of a vehicle, such as a semi-trailer truck. The integrated housing assembly includes a main enclosure that includes four sides, a top panel, and a bottom panel. One of the four sides is a front panel that is inclined towards the ground. The main enclosure includes one or more cavities. A front panel of the integrated housing assembly includes one or more openings to allow cameras or sensors to be placed within the one or more cavities and behind the one or more opening. The cameras or sensors cameras can be clamped at a downward angle within multiple lock apparatus. The angled front panel and the inclined cameras or sensors within the lock apparatus allow the cameras or sensors to obtain images or sensor data from one or more regions of interest at some distance from the front of the vehicle.

Abstract: Disclosed are devices, systems, and methods for a LiDAR mirror assembly mounted on a vehicle, such as an autonomous or semi-autonomous vehicle. For example, a LiDAR mirror assembly may include a base plate mounted on a hood of a vehicle, where the base plate is coupled to one end of a support arm. The opposite end of the support arm is attached to a housing. The housing includes a top housing enclosure coupled to a bottom housing platform, where a sensor and a mirror is coupled to the housing, and where the sensor is at least partially exposed through an opening in the top housing enclosure. The opening for the sensor is situated near an end of the housing furthest away from the base plate.

Abstract: Systems and methods for projecting a three-dimensional (3D) surface to a two-dimensional (2D) surface for use in autonomous driving are disclosed. In one aspect, a control system for an autonomous vehicle includes a processor and a computer-readable memory in communication with the processor and having stored thereon computer-executable instructions to cause the processor to: receive a 3D map including a plurality of objects, determine a base point in the 3D map, shift the objects in the 3D map based on the base point, project the objects in the shifted 3D map to a 2D map, and output the 2D map.

Abstract: Methods, systems and apparatus for autonomous vehicle path planning and path navigation are described. One example system includes an offline server configured to generate a library of optimal paths for navigating a geographic area, wherein the geographic area is represented as a grid node map and an orientation grid bin map and wherein the optimal paths correspond to paths between pairs of grid node pairs in the grid node map based on optimization criteria, a storage device on the autonomous vehicle for storing the library of optimal paths, and an online server located on the autonomous vehicle configured to access information from the library of optimal paths from the storage device based on a current position and a current heading of the autonomous vehicle, and navigating the autonomous vehicle through the geographic area based on the information.

Abstract: Devices, systems and methods for controlling an exterior and dashboard lights of an autonomous vehicle are described. One example of a method for controlling one or more exterior lights includes receiving, from an autonomous driving system (ADS) of the vehicle, an input to control one or more exterior lights that are part of a lighting system of the vehicle, and transmitting, based on the input, a message to a controller area network (CAN) bus of the lighting system, the message being further based on a driver command upon a determination that a driver-initiated message is received. In an example, the lighting system of the vehicle further comprises a plurality of dashboard lights.

Abstract: A launchpad is sized and shaped to accommodate an autonomous vehicle (AV) that includes at least one vehicle sensor. The launchpad includes one or more launchpad sensors located on or around the launchpad. A control subsystem receives launchpad sensor data from the launchpad sensor(s) and AV sensor data from the vehicle sensor(s). In response to the request for departure of the AV, the control subsystem determines, based at least in part upon the launchpad sensor data, whether the launchpad is free of obstructions that would prevent departure from the launchpad and determines, based at least in part upon the AV sensor data, whether the region in front of the AV is clear of obstructions that would prevent movement away from the launchpad. If both the launchpad and the region in front of the AV are free of obstructions, the AV is permitted to begin driving autonomously.

Abstract: A workflow management system is described to manage tasks to be performed with vehicles. The workflow management system includes a workflow management server and a computer located in a vehicle. The workflow management server generates and sends to the computer a record that describes a task to be performed with a vehicle. The task may include collecting sensor data from one or more sensors on the vehicle, or performing a vehicle driving test using an updated operating system to be used by the vehicle. The record can include a starting location and a destination of a route on which the vehicle is to perform the task. The computer receives the record, executes an operating system of the vehicle to perform the task, determines that the task is completed, and sends to a database a record status information that indicates that the task is completed.

Abstract: Techniques are described for transitioning control of a steering system from an autonomous mode in a vehicle to a driver-controlled mode where the driver can control the steering wheel of the steering system. A method includes receiving values that describe an amount of torque and a direction of torque in response to a torque applied to a steering wheel of a steering system operated in an autonomous mode, determining that the values are either greater than or equal to a threshold value or are less than or equal to a negative of the threshold value, determining that the values are measured over a period of time greater than or equal to a pre-determined amount of time, and transitioning the steering system from being operated in the autonomous mode to being operated in a driver-controlled mode in which the steering system is under manual control.

Abstract: A system and method for lateral vehicle detection is disclosed. A particular embodiment can be configured to: receive lateral image data from at least one laterally-facing camera associated with an autonomous vehicle; warp the lateral image data based on a line parallel to a side of the autonomous vehicle; perform object extraction on the warped lateral image data to identify extracted objects in the warped lateral image data; and apply bounding boxes around the extracted objects.

Abstract: Techniques are described for an autonomous vehicle to provide the autonomous vehicle's health-related information, identification information, and/or inspection information to a device that may be used by law enforcement or a government agency or a third-party so that the autonomous vehicle can comply with government regulations and can continue to operate on the road.

Abstract: A power management system is disclosed for managing power in a vehicle. The system may include a power distribution unit (PDU) communicably coupled to a power controller unit located in the vehicle. The power controller unit comprises a microcontroller configured to: receive, from the PDU, a temperature value that indicates a temperature of the PDU, one or more voltage values from the one or more voltage sensors, or one or more current values from the one or more current sensors, perform a determination that the temperature value, the one or more voltage values, or the one or more current values are below one or more of their respective pre-determined threshold values, and send, after the determination, a health status message to a computer located in the vehicle, where the health status message indicates that the PDU is operating in a safe operating condition.

Abstract: A system and method for occluding contour detection using a fully convolutional neural network is disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image by semantic segmentation; learning an array of upscaling filters to upscale the feature map into a final dense feature map of a desired size; applying the array of upscaling filters to the feature map to produce contour information of objects and object instances detected in the input image; and applying the contour information onto the input image.