Abstract: Methods and systems for forming a fleet and positioning vehicles in the fleet are disclosed. The system comprises a data transmission interface and a data processing unit. The data processing unit sends data to and receives data from the data transmission interface. The data processing unit determines an itinerary of each of a group of vehicles requesting to join a fleet. The data processing unit compares the itinerary of all vehicles of the group of vehicles. The data processing unit determines a second vehicle to form a fleet with a first vehicle from the group of vehicles. The data transmission interface communicates to the first vehicle a proposal to form a fleet with the second vehicle. The data processing unit determines if the first vehicle accepts the proposal, and if yes, determines instructions for the first vehicle how to join the fleet.

Abstract: Various technologies described herein pertain to generating an occupancy grid movie for utilization in motion planning for the autonomous vehicle. The occupancy grid movie can be generated for a given time and can include time-stepped occupancy grids for future times that are at predefined time intervals from the given time. The time-stepped occupancy grids include cells corresponding to regions in an environment surrounding the autonomous vehicle. Probabilities can be assigned to the cells specifying likelihoods that the regions corresponding to the cells are occupied at the future times. Moreover, cached query objects that respectively specify indices of cells of a grid occupied by a representation of an autonomous vehicle at corresponding orientations are described herein. An occupancy grid for the environment surrounding the autonomous vehicle can be queried to determine whether cells of the occupancy grid are occupied utilizing a cached query object from the cache query objects.

Abstract: A system and method of executing a user-defined notification task, and wherein the method includes: receiving a user-defined notification task at the vehicle via one or more user interfaces, wherein the user-defined notification task specifies a trigger event and a notification action, the trigger event being selectable from the plurality of predefined trigger events via the one or more user interfaces, and the notification action being configurable via selection of one or more notification settings via the plurality of notification settings; in response to receiving the user-defined notification task at the vehicle, configuring one or more vehicle system modules to monitor for an occurrence of the trigger condition of the user-defined notification event; and in response to detecting the occurrence of the trigger event of the user-defined notification task, executing the notification action so that a vehicle user is notified of the occurrence of the trigger event.

Abstract: An assembly for a vehicle to provide load distribution between the body of the vehicle and a battery contained in the vehicle includes a pair of body rockers, the body rockers being spaced apart and being substantially parallel to each other, a plurality of body cross bars that extend between the pair of body rockers, the plurality of body cross bars being spaced apart, substantially parallel to each other, and substantially perpendicular to the body rockers, and a plurality of battery cross bars that extend between the pair of body rockers, the plurality of battery cross bars being spaced apart, substantially parallel to each other, and substantially perpendicular to the body rockers, portions of the battery being located between adjacent battery cross bars. The plurality of battery cross bars, the plurality of body cross bars and the body rockers are configured to delay initiation of rocker plastic deformation.

Abstract: A battery enclosure shaped and sized to accept and surround a battery includes an outer case defining an aperture and having a base forming a bottom of the battery enclosure, the case having a first wall connected to a second wall, the second wall connected to a third wall, and a fourth wall portion connected to the first and third walls, each of the first, second, third, and fourth walls extending orthogonally from the base. The battery enclosure including a separable outer lid shaped to fit around the aperture of the case. The outer case and the outer lid having a material having thermal conductivity of less than about 0.3 W/mK, the battery enclosure has an air inlet selectively providing airflow to the battery enclosure and an air outlet selectively providing airflow from the battery enclosure, the outer case has a first thickness, the outer lid portion has a second thickness.

Abstract: A method of manufacturing a crankshaft includes the steps of: (1) forming a crankshaft blank via a first half and a second half; (2) measuring a plurality of surface variations between a predetermined surface in a first region and a corresponding predetermined surface in a second region of the crankshaft blank; (3) calculating centering offset data based on the plurality of surface variations; (4) machining a pair center holes based on the centering offset data; (5) machining a counterweight and a journal relative to the pair of center holes to produce a partially machined crankshaft; (5) milling and grinding the partially machined crankshaft to produce a finished machined crankshaft; and (6) rotating the finished machined crankshaft typically on the outermost main journals in a final balancing machine and then modifying the counterweights to eliminate undesirable vibration generated during the rotation and engine operation.

Abstract: Described herein are systems, methods, and computer-readable media for generating and training a high precision low bit convolutional neural network (CNN). A filter of each convolutional layer of the CNN is approximated using one or more binary filters and a real-valued activation function is approximated using a linear combination of binary activations. More specifically, a non-1×1 filter (e.g., a k×k filter, where k>1) is approximated using a scaled binary filter and a 1×1 filter is approximated using a linear combination of binary filters. Thus, a different strategy is employed for approximating different weights (e.g., 1×1 filter vs. a non-1×1 filter). In this manner, convolutions performed in convolutional layer(s) of the high precision low bit CNN become binary convolutions that yield a lower computational cost while still maintaining a high performance (e.g., a high accuracy).

Abstract: The present application generally relates to a method and apparatus for generating an action policy for controlling an autonomous vehicle. In particular, the method and apparatus include a memory operative to store a map data, a sensor operative to provide a location, a yaw rate sensor operative to measure a yaw rate, a processor for receiving the yaw rate, and a processor for determining a yaw rate calibration bias in response to the yaw rate, the location, and the map data, and a vehicle controller for controlling a vehicle in response to the yaw rate calibration bias.

Abstract: The present application generally relates to a method and apparatus for obtaining crash or near crash related data in a motor vehicle. In particular, the system is operative to determine a proximity to a railway crossing in response to a vehicle location and a map, to detect an object using a radar, to confirm the presence of the object using a visual detecting system in response to the proximity to the railway crossing being less than a threshold distance, to generate a vehicle control signal in response to confirming the presence of the object using the visual detecting system, and to control an assisted driving equipped vehicle in response to the vehicle control system.

Abstract: Systems and methods are provided for preventing a loss of throughput data connectivity from one or more active autonomous vehicles of the fleet communicating with a back office network by: collecting an average aggregate of the throughput data from the one or more active AVs communicating with the back office network; updating a set of records in a throughput data table corresponding to a plurality of mapped AV routes for the one or more active AVs, by processing a throughput data table record in the temporary buffer of updated throughput data to eliminate identified duplicate or out-of-date throughput data recorded in the throughput data table; and determining, by the back office network, whether one or more of the AV route segments or the final drop-off location exhibits the effect of an instance of the loss of throughput data connectivity between the AV and the back office network.

Abstract: In exemplary embodiments, methods, communication systems, and vehicle systems are provided. In one exemplary embodiment, a vehicle system is provided that includes: (a) a fleet of vehicles; and (b) a remote server that is remote from the fleet of vehicles, the remote server including: (i) a transceiver configured to receive, over a wireless communication network, a communication with a request for a command to be performed by the fleet of vehicles; and (ii) a processor configured to: (A) identify a plurality of vehicles of the fleet of vehicles subject to the command; and (B) provide instructions for each of the plurality of vehicles to perform a vehicle action corresponding to the command.

Abstract: Systems and method are provided for controlling a vehicle. In one embodiment, a method includes: initiating, by a controller onboard the vehicle, a first laser pulse from a first laser device; initiating, by a controller onboard the vehicle, a second laser pulse from a second laser device, wherein the initiating the second laser pulse is based on a phase shift angle; receiving, by the controller onboard the vehicle, first return data and second return data as a result of the first laser pulse and the second laser pulse; interleaving, by the controller onboard the vehicle, the first return pulse and the second return pulse to form a point cloud; and controlling, by the controller onboard the vehicle, the vehicle based on the point cloud.

Abstract: In exemplary embodiments, methods, systems, and vehicles are provided for controlling operation of a vehicle in a fuel economy mode. In one embodiment, a vehicle is includes a battery, a generator, and a control system for controlling operation of the vehicle in a fuel economy mode, the control system including: (i) one or more current sensors configured to measure a battery current of the battery; and (ii) a processor coupled to the one or more current sensors and configured to at least facilitate controlling operation of the battery and the generator in the fuel economy mode utilizing a dynamic voltage threshold that is adjusted based on a comparison of the battery current with a baseload current threshold.

Abstract: Systems and methods to mitigate an effect of an errant signal on an image sensor of a vehicle involve collecting light and separating the light to obtain signals at different wavelengths. A method includes determining an intensity of the light at each of the different wavelengths, and identifying the errant signal based on the intensity of the light exceeding a threshold value at an errant signal wavelength among the different wavelengths. The errant signal is mitigated using the controller.

Abstract: A tunable film apparatus is provided. The apparatus includes: a first and second layer, a linear polarizer disposed in front of the first layer, liquid crystal elements disposed between the first and second layer; and a tuner configured to cause temporal averaging of a light received through the linear polarizer.

Abstract: A system to enable restricted area entrance, including a memory configured to include one or more executable instructions; a controller configured to execute the executable instructions; a vehicle including a vehicle controls device, the vehicle configured to communicate with the controller, the vehicle controls device configured to command the vehicle to autonomously perform rideshare task(s); and the executable instructions enable the controller to receive vehicle reservation information from a mobile computing device; generate first and second vehicle identification aspects from the received vehicle reservation information, where the first and second vehicle identification aspects can be compared and, when the first and second vehicle identification aspects are determined to correspond via the comparison, an access operator can operate an access gate to enable restricted area entrance; and communicate the first vehicle identification aspect to the vehicle and the second vehicle identification aspect to the

Abstract: An intake manifold of an automobile vehicle includes a manifold body connected to a cylinder head. A runner is in communication with the cylinder head. A plenum is in communication with the runner. An inner dividing wall is positioned between and partially separates the runner and the plenum while allowing communication between the plenum and the runner over a dividing wall end of the inner dividing wall. An orifice opening extends through the inner dividing wall providing a drain path from the plenum to the runner. The orifice drains a fluid collecting in the plenum to the runner.

Abstract: A vehicle, system and method of mapping the environment is disclosed. The system includes a sensor and a processor. The sensor is configured to obtain a detection from an object in an environment surrounding the vehicle. The processor is configured to compute a plurality of radial components and a plurality of angular components for a positive inverse sensor model (ISM) of an occupancy grid, select a radial component corresponding to a range of the detection from the plurality of radial components and selecting an angular component corresponding to an angle of the detection from the plurality of angular components, multiply the selected radial component and the selected angular component to create an occupancy grid for the detection, and map the environment using the occupancy grid.

Abstract: Systems and methods are provided for generating a map for use in controlling a vehicle. In one embodiment, a method includes: receiving, by a processor, aerial image data depicting an environment; processing, by the processor, the aerial image data with a plurality of trained deep learning models to produce a predicted radar map; and controlling the vehicle based on the predicted radar map.

Abstract: Systems and methods are provided for limit cycle detection and cessation. A control system generates a drive signal with at least one drive component. An actuator effects a response to the drive signal and a sensor measures the response. Characteristics of the drive signal and of the drive components are accessed by a controller. The characteristics are compared to a predetermined set of characteristics. When the characteristics fall within the predetermined set of characteristics, a magnitude of at least one of the characteristics is evaluated. When the magnitude exceeds a predetermined value indicative of the limit cycle, an action is undertaken to stop the limit cycle.