Abstract: An intersection navigation system includes: a complexity module configured to determine a complexity value for an intersection of two or more roads, where the complexity value for the intersection corresponds to a level of complexity for a vehicle to navigate the intersection during autonomous driving; and a driving control module configured to: during autonomous driving of a vehicle, control at least one of: steering of the vehicle; braking of the vehicle; and acceleration of the vehicle; and based on the complexity value of the intersection, selectively adjust at least one aspect of the autonomous driving.

Abstract: In accordance with an exemplary embodiment, an autonomous system is provided that includes: a tow vehicle, a trailer, and a control system. The tow vehicle has a vehicle battery. The trailer is coupled to the tow vehicle, and has a trailer battery. The control system includes a sensor and a processor. The sensor is configured to at least facilitate measuring a state of charge of the trailer battery. The processor is coupled to the sensor, and is configured to at least facilitate selectively providing current from the tow vehicle to the trailer based on the state of charge of the trailer battery.

Abstract: Systems and methods are provided for controlling a vehicle. In one embodiment, a method includes: storing, in a data storage device, a decision model, wherein the decision model predicts when to automatically perform a motivational lane change; updating, by a processor, the decision model based on data obtained in response to user input; and automatically requesting, by the processor, a lane change based on the dynamically updated model.

Abstract: A light inspection system positions an autonomous vehicle (AV) in a field of view of a camera such that the camera captures an image of a light of the AV. The light inspection system instructs a camera to capture an image of the light while the light is switched on. The light inspection system receives the captured image, determines a luminance of the light based on the image, and determines to service the light in response to the luminance of the light being below a threshold luminance.

Abstract: A method for reducing the number of neurons in a trained deep neural network (DNN) includes classifying layer types in a plurality of hidden layers; evaluating the accuracy of the DNN using a validation set of data; and generating a layer specific ranking of neurons, wherein the generating includes: analyzing, using the validation set of data for one or more of the plurality of hidden layers, the activation function for each neuron in the analyzed layers to determine an activation score for each neuron; and ranking, on a layer type basis, each neuron in the analyzed layers based on the neuron's activation score to generate a layer specific ranking of neurons. The method further includes removing a number of lower ranked neurons from the DNN that does not result in the DNN after the removal of selected lower ranked neurons to fall outside of an accuracy threshold limit.

Abstract: The present application relates to a method for performing off road adaptive cruise control in a host vehicle including controlling a vehicle speed at a first speed according to an adaptive cruise control algorithm, detecting an obstacle, using a sensor, within a host vehicle path, reducing the vehicle speed to a reduced speed in response to the detection of the obstacle, detecting a vehicle contact with the obstacle in response to a first inertial measurement unit measurement, applying a brake friction force and increasing an engine torque in response to detecting the vehicle contact with the obstacle, determining a traverse of the obstacle in response to a second inertial measurement unit measurement, and resuming the control of the vehicle speed at the first speed in response to the traverse of the obstacle.

Abstract: The present application generally relates to a method and apparatus for obtaining incident related data in a motor vehicle. In particular, the system is operative to determine a vehicle to vehicle contract event or near contact event, transmit a request for data, such as video, numeric, and telemetry data, from proximate actors via V2X communications channel, or to request the data be transmitted to a network storage location.

Abstract: The subject disclosure relates to techniques for inserting of bounding boxes around image objects. A process of the disclosed technology can include steps for receiving, from a first data set, an image comprising a first image object, processing the image to identify a pixel region associated with the first image object, and placing a first bounding box around the first image object based on the identified pixel region. In some aspects, the process further includes steps for receiving a user input comprising an indication of whether the first bounding box is accurately placed around the first image object. Systems and machine-readable media are also provided.

Abstract: A sensor assembly includes a sensor and a cover disposed adjacent to the sensor to protect the sensor. The cover has an inner cover surface and an outer cover surface opposite the inner cover surface. The inner cover surface faces the sensor, and the outer cover surface faces away from the sensor. The cover has a first end wall and a second end wall apart from the first end wall along a first direction. The sensor assembly includes a cleaning system having a wiper movable along the outer cover surface of the cover in the first direction to clean to the outer cover surface. The wiper is at least partly made of a wiper material, and the wiper material includes a hydrophilic material to facilitate removal of water from the outer cover surface of the cover.

Abstract: Systems and methods provide for routing an autonomous vehicles based on an assessment of its limitations. The autonomous vehicle can avoid problematic routes by applying a set of rules to a map, where the set of rules are associated with a feature that causes a failure of the autonomous vehicle due to an autonomous vehicle limitation. Based on the application of the set of rules, a portion of a route on the map that is associated with the feature can be identified, and an identifier can be applied to the identified portion of the route associated with the feature on a routing map. The portion of the route can be omitted from a routable graph applied to the routing map, such that the route for the autonomous vehicle is generated in accordance with the routable graph.

Abstract: A single-piece, lightweight, energy-absorbing, and impact resistant battery tray for a battery enclosure for a vehicle includes a lower floor including an impact resisting structure, upwardly sloping side walls integrally formed with the lower floor, and a peripheral flange integrally formed with the upwardly sloping side walls and including an energy absorbing structure.

Abstract: Method and apparatus are provided for a multidirectional opening storage cover. The apparatus includes a storage cover having a right side, a left side, a front side, and a rear side, a first latch on the left side of the storage cover, a second latch on the front side of the storage cover, a third latch on the right side of the storage cover, a fourth latch on the rear side of the storage cover, a first switch on the left side of the storage cover operative to disengage the first latch, second latch and fourth latch in response to an activation of the first switch by a user, and a second switch on the right side of the storage cover operative to disengage the second latch, the third latch and the fourth latch in response to an activation of the second switch by the user.

Abstract: An asymmetric whispering gallery mode resonator device is described. The resonator device includes an asymmetric whispering gallery mode resonator disk (e.g., transparent material, electrooptic material). The resonator disk includes an axial surface along a perimeter of the resonator disk, a top surface, and a bottom surface. A first midplane passes through the axial surface dividing the axial surface into symmetrical halves. The top surface and the bottom surface are substantially parallel, and a second midplane is substantially equidistant between the top surface and the bottom surface. The first midplane and the second midplane are non-coextensive. The asymmetric whispering gallery mode resonator disk can further include a first chamfered edge between the top surface and the axial surface, and a second chamfered edge between the bottom surface and the axial surface. Moreover, the resonator device includes a first electrode on the top surface and a second electrode on the bottom surface.

Abstract: A polyhedral sensor target includes multiple surfaces. A housing, such as a vehicle, may include a camera and a distance measurement sensor, such as a light detection and ranging (LIDAR) sensor. The housing may move between different positions during calibration, for instance by being rotated atop a turntable. The camera and distance measurement sensor may both capture data during calibration, from which visual and distance measurement representations of the polyhedral sensor target are identified. The camera and distance measurement sensor are calibrated based on their respective representations, for example by mapping vertices within the representations to the same location.

Abstract: A method identifies bottlenecks in a manufacturing system. The method includes: creating a flow diagram showing how parts travel through the manufacturing system, wherein the manufacturing system comprises stations and buffers; identifying work zones in the flow diagram that will be analyzed; identifying predecessors and successors for each of the work zones in the flow diagram; receiving a buffer use and station block/starve data of the manufacturing system; gathering the buffer use and station block/starve data for the predecessors and the successors previously identified by the controller; calculating a block ratio (BR) of the predecessors and the successors previously identified by the controller; calculating bottleneck indicator (BI) values for the work zones using the BR of the predecessors and the successors; making a list of the BI values from the highest to the lowest to identify a top bottleneck work zone of the work zones.

Abstract: A door for an entryway includes an exterior-facing surface, an inner structure, and a latch mechanism. The latch mechanism is connected to the inner structure and configured to be fastened or released for controlling access to the entryway. The door also includes a key-cylinder accessible from the exterior-facing surface and configured to selectively lock and unlock the latch mechanism. The door additionally includes a pawl configured to be rotated by the key-cylinder about a pivot axis, connected to the latch mechanism, and defining a pass-through aperture distal from the pivot axis. The door also includes a shield defining a shield attachment aperture and connected to the inner structure. The door further includes a security fastener to fix the shield relative to the key-cylinder at the shield attachment aperture and extending through the pass-through aperture without impeding the pawl's rotation or contacting the pawl as the pawl operates the latch mechanism.

Abstract: A method for using Synthetic Aperture Radar (SAR) to perform a maneuver in a land vehicle is provided. The method includes: receiving digitized radar return data from a radar transmission from a SAR onboard the vehicle; accumulating a plurality of frames of the digitized radar return data; applying a RADON transform to the accumulated plurality of frames of the digitized radar return data and odometry data from the vehicle to generate transformed frames of data for each three-dimensional point, wherein the RADON transform is configured to perform coherent integration for each three-dimensional point, project a radar trajectory onto each three-dimensional point, and project Doppler information onto each three-dimensional point; generating a two-dimensional map of an area covered by the radar transmission from the SAR based on the transformed frames of data for each three-dimensional point; and performing a maneuver with the land vehicle by applying the generated two-dimensional map.

Abstract: The present disclosure provides a method of making a negative electrode material for an electrochemical cell that cycles lithium ions. The method includes centrifugally distributing a precursor including silicon, lithium, and an additional metal (M) selected from the group consisting of: aluminum (Al), chromium (Cr), titanium (Ti), niobium (Nb), molybdenum (Mo), zirconium (Zr), yttrium (Y), cerium (Ce), and combinations thereof by contacting the precursor with a rotating surface in a centrifugal atomizing reactor and solidifying the precursor to form a plurality of substantially round solid electroactive particles that include Li4.4xSixMy, where x is greater than 0 to less than or equal to about 0.85 and y corresponds to a weight percent of M that is greater than or equal to 0.1 wt. % to less than or equal to about 10 wt. %.

Abstract: A negative electrode for a secondary lithium battery is provided herein, as well as a method for assembling a secondary lithium battery including the negative electrode. The negative electrode includes a current collector having a first side and an opposite second side. A first negative electrode layer is disposed on the first side of the current collector and a second negative electrode layer is disposed on the second side of the current collector. A lithium metal layer is disposed (i) between the first and second negative electrode layers or (ii) on a major facing surface of the first or second negative electrode layer. An electrolyte infiltrates the first and second negative electrode layers and is in contact with the lithium metal layer. The electrolyte establishes a lithium ion transport path between the lithium metal layer and at least one of the first or second negative electrode layers.

Abstract: The present application relates to a system and method for receiving, via a microphone array, an incoming acoustic signal including a desired signal and an undesired signal, performing a first minimum variance distortionless response beamforming operation on the incoming acoustic signal to isolate the desired signal, performing a second minimum variance distortionless response beamforming operation, by the signal processor, on the incoming acoust signal to isolate the undesired signal, filtering the desired signal to generate a filtered desired signal, combining an inverse of the filtered desired signal with the undesired signal to generate a combined undesired signal, filtering the combined undesired signal to generate a filtered combined undesired signal, combining an inverse of the combined undesired signal and the desired signal to generate an output signal, and generating a data signal in response to the output signal for transmission via a wireless network.