Abstract: An approach is provided for creating underground drone routes. The approach, for example, involves querying digital map data for at least one underground and/or interior passageway to reach a destination of the drone. The digital map data includes location data for a plurality of entry points, a plurality of exit points, or a combination thereof to the network of underground and/or interior passageways. The approach also involves generating a route to the destination via the at least one underground passageway based on the location data.

Abstract: A disambiguation system for an autonomous vehicle is described herein that disambiguates a traffic light framed by a plurality of regions of interest. The autonomous vehicle includes a localization system that defines the plurality of regions of interest around traffic lights captured in a sensor signal and provides an input to a disambiguation system. When the captured traffic lights are in close proximity, the plurality of regions of interest overlap each other such that a traffic light disposed in the overlapping region is ambiguous to an object detector because it is framed by more than one region of interest. A disambiguation system associates the traffic light with the correct region of interest to disambiguate a relationship thereof and generates a disambiguated directive for controlling the autonomous vehicle. Disambiguation can be achieved according to any of an edge-based technique, a vertex-based technique, and a region of interest distance-based technique.

Abstract: Techniques are disclosed for methods and systems for automating the operation of vehicle lifts in the servicing of automotive vehicles. The lifts may be motorized mobile column lifts and/or fixed lifts, including two-post lifts with swing-arms and a variety of drive-on lifts. Motorized mobile lifts have a motorized transport mechanism. A guidance system first assigns available motorized mobile lifts to the axled wheels of a vehicle and then directs their transport mechanism for transporting them to their engagement locations. It also guides the engagement of both the motorized mobile lifts and the fixed lifts in the service center. A number of technologies may be used for this purpose, including sensors onboard the vehicles and/or the lifts and/or the service center. A computer vision pipeline may also be utilized to assist in the process. Machine learning may also be employed. Techniques are also extended to autonomous vehicles as well as interfacing with fleet management software.

Abstract: An approach is provided for mapping underground and/or interior passageways for drone routing. The approach, for example, involves determining location data for entry points, exit points, or a combination thereof to the underground and/or interior passageways. The entry points facilitate an entry of a drone into the plurality of underground and/or interior passageways, and the exit points facilitate an exit of the drone from the plurality of passageways. The approach also involves associating the location data with a geographic database. The geographic database further includes digital map data representing the plurality of underground passageways and is used to determine a route through the underground and/or interior passageways for the drone.

Abstract: Techniques for optimizing a scan pattern of a LIDAR system including a bistatic transceiver include receiving first SNR values based on values of a range of the target, where the first SNR values are for a respective scan rate. Techniques further include receiving second SNR values based on values of the range of the target, where the second SNR values are for a respective integration time. Techniques further include receiving a maximum design range of the target at each angle in the angle range. Techniques further include determining, for each angle in the angle range, a maximum scan rate and a minimum integration time. Techniques further include defining a scan pattern of the LIDAR system based on the maximum scan rate and the minimum integration time at each angle and operating the LIDAR system according to the scan pattern.

Abstract: The disclosure relates to a method for capturing a traffic lane. A traffic lane data set is evaluated to capture an abrupt change of the traffic lane. The traffic lane data set is divided into a new traffic lane data set that represents a new traffic lane boundary and an old traffic lane data set that represents an old traffic lane boundary. A difference data set is determined between the old traffic lane data set and the new traffic lane data set. The difference data set is added to the new traffic lane data set to form a resulting data set, wherein the difference data set is weighted with a plurality of weighting factors.

Abstract: A misfire detection system and method for a vehicle utilize a controller to obtain a crankshaft speed signal indicative of a rotational speed of an engine crankshaft connected to a device that mitigates vibrational disturbances at the crankshaft caused by misfires of the engine, detect that a first firing event of the engine is a first misfire based on the crankshaft speed signal, monitor a vibrational response of the crankshaft, detect that a consecutive second firing event of the engine is a second misfire based on a first modified crankshaft speed signal and the first set of thresholds, and in response to detecting the second misfire, reset the monitoring of the vibrational response of the crankshaft including modifying the amplitude of the crankshaft speed signal to obtain a second modified crankshaft speed signal and comparing the second modified crankshaft speed signal to a set of thresholds.

Abstract: An aerodynamic control system for a ground vehicle comprises a LiDAR module including at least one LiDAR sensor configured to obtain wind data upstream of the ground vehicle; a computing device; an aerodynamic device controller; and an aerodynamic device including a control surface. The computing device is configured to receive the wind data from the LiDAR module and generate output signals based on the wind data. The aerodynamic device controller is configured to receive the output signals from the computing device and generate control signals to control the aerodynamic device to adjust aerodynamic properties of the ground vehicle based at least in part the wind data. Changes to the configuration of the control surface may include increasing or decreasing a deflection angle of the at least one aerodynamic device. The aerodynamic device may include, e.g., a pneumatically actuated aerodynamic device or an electro-mechanically actuated aerodynamic device.

Abstract: Saliency training may be provided to build a saliency database, which may be utilized to facilitate operation of an autonomous vehicle. The saliency database may be built by minimizing a loss function between a saliency prediction result and a saliency mapper result. The saliency mapper result may be obtained from a ground truth database, which includes image frames of an operation environment where objects or regions within respective image frames are associated with a positive saliency, a neutral saliency, or a negative saliency. Neutral saliency may be indicative of a detected gaze location of a driver corresponding to the object or region at a time prior to the time associated with a given image frame. The saliency prediction result may be generated based on features extracted from respective image frames, depth-wise concatenations associated with respective image frames, and a long short-term memory layer or a recurrent neural network.

Abstract: Aspects of the disclosure relate to processing remotely captured sensor data. A computing platform having at least one processor, a communication interface, and memory may receive, via the communication interface, from a user computing device, sensor data captured by the user computing device using one or more sensors built into the user computing device. Subsequently, the computing platform may analyze the sensor data received from the user computing device by executing one or more data processing modules. Then, the computing platform may generate trip record data based on analyzing the sensor data received from the user computing device and may store the trip record data in a trip record database. In addition, the computing platform may generate user record data based on analyzing the sensor data received from the user computing device and may store the user record data in a user record database.

Abstract: A system and methods for monitoring the integrity of navigation measurement information are disclosed. One method includes receiving a plurality of navigation measurement values, computing a first set and second set of estimates of the navigation measurement values, comparing the first set to the second set, and if the second set is statistically consistent with the first set, computing a plurality of sub-sets of the second set of estimates, computing a sub-solution for each sub-set of the second set of estimates, and computing an integrity value for each sub-solution.

Abstract: Changes in energy of an aerial vehicle that are unrelated to any operational changes in the aerial vehicle may be associated with energy sources or sinks naturally present at a location. Air flows generated due to contrasts in surface temperatures or terrain features at locations may cause energy levels of aerial vehicles to rise or fall. Locations of changes in energy may be recorded and used to generate a map or other representation of energy within an area. The map or other representation may be used in selecting optimal routes for aerial vehicles within the area. Additionally, a machine learning system may be trained using maps or representations of energy within areas and images of such areas. An image of an area may be provided to a trained machine learning system as an input, and a representation of energy within the area may be generated based on an output.

Abstract: An autonomous vehicle is described herein. The autonomous vehicle includes a lidar sensor system. The autonomous vehicle additionally includes a computing system that executes a lidar segmentation system, wherein the lidar segmentation system is configured to identify objects that are in proximity to the autonomous vehicle based upon output of the lidar sensor system. The computing system further includes a deep neural network (DNN), where the lidar segmentation system identifies the objects in proximity to the autonomous vehicle based upon output of the DNN. The computing system is further configured to align a heightmap to lidar data output by the lidar sensor system based upon output of the DNN. The lidar segmentation system can identify objects in proximity to the autonomous vehicle based upon the aligned heightmap.

Abstract: A vehicle having a drive motor is provided. The vehicle includes a controller that changes the inclination of a drive motor torque command based on a demand torque of a driver or a temperature of a drive motor. A motor controller then operates the drive motor to change the motor torque changes based on the inclination of the motor torque command.

Abstract: Embodiments for managing drones by one or more processors are described. A condition related to the operation of a drone in a selected area is detected. A set of drone operating parameters associated with the operation of the drone in the selected area is changed based on the detecting of the condition. A signal representative of the changing of the set of drone operating parameters is generated.

Abstract: In order to detect a vehicle accident in which a vehicle and an object crash into one another, wherein a motion variable assigned to the collision is so low that at least one active occupant protection system provided for accidents in the vehicle is not activated by the crash, it is provided, with respect to the collision event, that signals and/or data formed by sensors of the vehicle are processed in such a manner that the signals and/or data are filtered, feature data are formed based on the filtered signals and/or data, and the collision event is assigned to a classification in a classification database based on the feature data.

Abstract: An operating system for a working machine includes drones having GNSS receivers, and working machines having take-off and landing ports and is configured so that positional information on the working machines is acquired by the GNSS receivers of the drones to be placed on the take-off and landing ports.

Abstract: In a method of operating a payload-carrying vehicle having a system configured to provide torque to ground contacting elements, the method includes, repeatedly measuring a force applied by a user to the vehicle; determining a direction and a magnitude of the measured force; determining a respective amount of torque to apply to each of the ground contacting elements as a function of the determined direction and magnitude; and providing the respective determined amount of torque to each of the ground contacting elements.

Abstract: An autonomous vehicle automatically implements an intention aware lane change with a safety guaranteed lane biased strategy. To make a lane change, the autonomous vehicle first navigates within the current lane to near the edge of the current lane, to a position offset by a bias. By navigating to the edge of the lane, the autonomous vehicle provides a physical and virtual notification, in addition to a turn signal, that it is the intention of the vehicle to change into the lane adjacent to the edge of the lane in which the vehicle has navigated to. After performing a safety check and waiting for a minimum period of time during which vehicles in the adjacent lane can be assumed to have been warned or been put on notice of the lane change, the autonomous vehicle navigates into the adjacent lane.

Abstract: A vehicle may have an emergency simulation mode, for pre-experiencing operating logic provided in the case of emergency to be caused while driving in a vehicle which is actually driven, and a driving method thereof. The vehicle having an emergency simulation mode may include an input unit for allowing a driver to input a command for selecting a simulation mode for emergency, a controller connected to the input unit and configured for storing a database for a plurality of emergencies to be caused in the vehicle, establishing operating logic of a simulation mode and a real mode for each emergency, and selecting operating logic for each emergency depending on the command received from input unit or a sensing value sensed by the vehicle, and an operation unit which is operated according to the operating logic selected by the controller.