Abstract: A system and method for vehicle wheel detection is disclosed. A particular embodiment can be configured to: receive training image data from a training image data collection system; obtain ground truth data corresponding to the training image data; perform a training phase to train one or more classifiers for processing images of the training image data to detect vehicle wheel objects in the images of the training image data; receive operational image data from an image data collection system associated with an autonomous vehicle; and perform an operational phase including applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and produce vehicle wheel object data.

Abstract: An example method for performing multi-sensor collaborative calibration on a vehicle includes obtaining, from at least two sensors located on a vehicle, sensor data items of an area that comprises a plurality of calibration objects; determining, from the sensor data items, attributes of the plurality of calibration objects; determining, for the at least two sensors, an initial matrix that describes a first set of extrinsic parameters between the at least two sensors based at least on the attributes of the plurality of calibration objects; determining an updated matrix that describes a second set of extrinsic parameters between the at least two sensors based at least on the initial matrix and a location of at least one calibration object; and performing autonomous operation of the vehicle using the second set of extrinsic parameters and additional sensor data received from the at least two sensors.

Abstract: A system and method for using human driving patterns to detect and correct abnormal driving behaviors of autonomous vehicles are disclosed. A particular embodiment includes: generating data corresponding to a normal driving behavior safe zone; receiving a proposed vehicle control command; comparing the proposed vehicle control command with the normal driving behavior safe zone; and issuing a warning alert if the proposed vehicle control command is outside of the normal driving behavior safe zone. Another embodiment includes modifying the proposed vehicle control command to produce a modified and validated vehicle control command if the proposed vehicle control command is outside of the normal driving behavior safe zone.

Abstract: Systems and methods for deploying emergency roadside signaling devices are disclosed. In one aspect, system for an autonomous vehicle includes one or more signaling devices configured to visually notify other vehicles when placed on or near a roadway, and an object placing device configured to place the one or more signaling devices. The system further 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: determine that the autonomous vehicle has experienced a malfunction, and provide instructions to the object placing device to place the one or more signaling devices on or near the roadway.

Abstract: Systems and methods for deploying emergency roadside signaling devices are disclosed. In one aspect, a control system for an object placing device of 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 signal comprising instructions to activate the object placing device; and provide instructions to the object placing device to place a plurality of signaling devices in accordance with predetermined criteria.

Abstract: A system and method for proximate vehicle intention prediction for autonomous vehicles are disclosed. A particular embodiment is configured to: receive perception data associated with a host vehicle; extract features from the perception data to detect a proximate vehicle in the vicinity of the host vehicle; generate a trajectory of the detected proximate vehicle based on the perception data; use a trained intention prediction model to generate a predicted intention of the detected proximate vehicle based on the perception data and the trajectory of the detected proximate vehicle; use the predicted intention of the detected proximate vehicle to generate a predicted trajectory of the detected proximate vehicle; and output the predicted intention and predicted trajectory for the detected proximate vehicle to another subsystem.

Abstract: The disclosed technology enables automated parking of an autonomous vehicle. An example method of performing automated parking for a vehicle comprises obtaining, from a plurality of global positioning system (GPS) devices located on or in an autonomous vehicle, a first set of location information that describes locations of multiple points on the autonomous vehicle, where the first set of location information are associated with a first position of the autonomous vehicle, determining, based on the first set of location information and a location of the parking area, a trajectory information that describes a trajectory for the autonomous vehicle to be driven from the first position of the autonomous vehicle to a parking area, and causing the autonomous vehicle to be driven along the trajectory to the parking area by causing operation of one or more devices located in the autonomous vehicle based on at least the trajectory information.

Abstract: Systems and methods for autonomous lane level navigation are disclosed. In one aspect, a control system for an autonomous vehicle includes a processor and a computer-readable memory configured to cause the processor to receive a partial high-definition (HD) map that defines a plurality of lane segments that together represent one or more lanes of a roadway, the partial HD map including at least a current lane segment. The processor is also configured to generate auxiliary global information for each of the lane segments in the partial HD map. The processor is further configured to generate a subgraph including a plurality of possible routes between the current lane segment and the destination lane segment using the partial HD map and the auxiliary global information, select one of the possible routes for navigation based on the auxiliary global information, and generate lane level navigation information based on the selected route.

Abstract: A system includes an autonomous vehicle (AV) comprising a sensor, a control subsystem, and an operation server. The control subsystem receives sensor data comprising location coordinates of the AV from the sensor. The operation server detects an unexpected event from the sensor data, comprising at least one of an accident, an inspection, and a report request. The operation server receives a message from a user comprising a request to access particular information regarding the AV and location data. The operation server associates the AV with the user if the location coordinates of the AV match location data of the user. The operation server establishes a communication path between the user and a remote operator for further communications.

Abstract: A system and method for fisheye image processing can be configured to: receive fisheye image data from at least one fisheye lens camera associated with an autonomous vehicle, the fisheye image data representing at least one fisheye image frame; partition the fisheye image frame into a plurality of image portions representing portions of the fisheye image frame; warp each of the plurality of image portions to map an arc of a camera projected view into a line corresponding to a mapped target view, the mapped target view being generally orthogonal to a line between a camera center and a center of the arc of the camera projected view; combine the plurality of warped image portions to form a combined resulting fisheye image data set representing recovered or distortion-reduced fisheye image data corresponding to the fisheye image frame; generate auto-calibration data representing a correspondence between pixels in the at least one fisheye image frame and corresponding pixels in the combined resulting fisheye image

Abstract: An autonomous vehicle can classify and prioritize agent of interest (AOI) objects located around the autonomous vehicle to manage computational resources. An example method performed by an autonomous vehicle includes determining, based on a location of the autonomous vehicle and based on a map, an area in which the autonomous vehicle is operated, determining, based on sensor data received from sensors located on or in the autonomous vehicle, attributes of objects located around the autonomous vehicle, where the attributes include information that describes a status of the objects located around the autonomous vehicle, selecting, based at least on the area, a classification policy that includes a plurality of rules that are associated with a plurality of classifications to classify the objects, and for each of the objects located around the autonomous vehicle: monitoring an object according to a classification of the object based on the classification policy.

Abstract: A vehicle position and velocity estimation system based on camera and LIDAR data is disclosed. An embodiment includes: receiving input object data from a subsystem of a vehicle, the input object data including image data from an image generating device and distance data from a distance measuring device, the distance measuring device comprising one or more LIDAR sensors; determining a first position of a proximate object near the vehicle from the image data; determining a second position of the proximate object from the distance data; correlating the first position and the second position by matching the first position of the proximate object detected in the image data with the second position of the same proximate object detected in the distance data; determining a three-dimensional (3D) position of the proximate object using the correlated first and second positions; and using the 3D position of the proximate object to navigate the vehicle.

Abstract: Disclosed are devices, systems and methods for using a rotating camera for vehicular operation. One example of a method for improving driving includes determining, by a processor in the vehicle, that a trigger has activated, orienting, based on the determining, a single rotating camera towards a direction of interest, and activating a recording functionality of the single rotating camera, where the vehicle comprises the single rotating camera and one or more fixed cameras, and where the single rotating camera provides a redundant functionality for, and consumes less power than, the one or more fixed cameras.

Abstract: A method includes receiving a series of road images from a side-view camera sensor of the autonomous driving vehicle. For each object from objects captured in the series of road images, a series of bounding boxes in the series of road images is generated, and a direction of travel or stationarity of the object is determined. The methods and apparatus also include determining a speed of each object for which the direction of travel has been determined and determining, based on the directions of travel, speeds, or stationarity of the objects, whether the autonomous driving vehicle can safely move in a predetermined direction. Furthermore, one or more control signals is sent to the autonomous driving vehicle to cause the autonomous driving vehicle to move or to remain stationary based on determining whether the autonomous driving vehicle can safely move in the predetermined direction.

Abstract: Techniques are described for compensating for movements of sensors. A method includes receiving two sets of sensor data from two sets of sensors, where a first set of sensors are located on a roof of a cab of a semi-trailer truck and a second set of sensor data are located on a hood of the semi-trailer truck. The method also receives from a height sensor a measured value indicative of a height of the rear of a rear portion of the cab of the semi-trailer truck relative to a chassis of the semi-trailer truck, determines two correction values, one for each of the two sets of sensor data, and compensates for the movement of the two sets of sensors by generating two sets of compensated sensor data. The two sets of compensated sensor data are generated by adjusting the two sets of sensor data based on the two correction values.

Abstract: Techniques are described for determining an occurrence of theft in a vehicle. An example processor implemented method comprises receiving, by a computer located in an autonomous vehicle and at a first time, a first torque value that indicates a first amount of torque applied by an engine of the autonomous vehicle to drive the autonomous vehicle, receiving, at a second time that is later in time than the first time, a second torque value that indicates a second amount of torque applied by the engine of the autonomous vehicle, determining that a difference between a first value and a second value is greater than a pre-determined value, where the first value and the second value are functions of at least the first torque value and at least the second value respectively, and displaying, in response to the determining, a message that indicates a theft detection in the autonomous vehicle.

Abstract: Techniques for performing multi-sensor calibration on a vehicle are described. A method includes obtaining, from each of at least two sensors located on a vehicle, sensor data item of a road comprising a lane marker, extracting, from each sensor data item, a location information of the lane marker, and calculating extrinsic parameters of the at least two sensors based on determining a difference between the location information of the lane marker from each sensor data item and a previously stored location information of the lane marker.

Abstract: A prediction-based system and method for trajectory planning of autonomous vehicles are disclosed.

Abstract: A redundant hardware and software architecture can be designed to enable vehicles to be operated in an autonomous mode while improving the reliability and/or safety of such vehicles. A system for redundant architecture can include a set of at least two redundant sensors coupled to a vehicle and configured to provide timestamped sensor data to each of a plurality of computing unit (CU) computers. The CU computers can process the sensor data simultaneously based on at least a time value indicative of an absolute time or a relative time and based on the timestamped sensor data. The CU computers provide to a vehicle control unit (VCU) computer at least two sets of outputs configured to instruct a plurality of devices in a vehicle and cause the vehicle to be driven.