Abstract: A computing system that can receive an object search request from a user indicating a request to search for a specific object in an area traversed by one or more autonomous vehicle. The object search request can include a set of physical characteristics of the specific object. The computing system can then transmit a signal to an autonomous vehicle indicating a request for the autonomous vehicle to search for the specific object. The signal can cause the autonomous vehicle to transmit an image, selected based on a physical characteristic of the object, to the computing system. The computing system can then generate a score indicative of a difference between one or more physical characteristic of the object in the image and the specific object. The computing system can then selectively transmit the image to a mobile device operated by the user based on the score.

Abstract: Various technologies described herein pertain to detecting sensor data to be annotated for autonomous vehicle perception algorithm training. A label identifying a type of an object is assigned to an object at a particular location in an environment based on sensor data generated by a sensor system of an autonomous vehicle for a given time. The label is assigned based on a confidence score assigned to the type of the object by a computer-implemented perception algorithm. The computer-implemented perception algorithm assigns the confidence score to the type of the object based on the sensor data corresponding to the particular location in the environment for the given time. An output of a heuristic is generated based on the label and/or the confidence score, and the output of the heuristic is used to control whether to cause the sensor data for the given time to be annotated.

Abstract: The subject disclosure relates to techniques for selecting points of an image for processing with LiDAR data. A process of the disclosed technology can include steps receiving an image data comprising an image object comprised of a plurality of image pixels, calculating a number of image pixels corresponding with the image object, receiving Light Detection and Ranging (LiDAR) point cloud data comprising a plurality of LiDAR data points corresponding with the image data collected from the camera sensor, and calculating a number of LiDAR data points corresponding with the image object. Systems and machine-readable media are also provided.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each vehicle orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations, for example by comparing these representations to previously stored information about the sensor targets and generating a correction based on differences, the correction applied to post-calibration sensor data.

Abstract: A process for correcting longitudinal roll from an offset load using active roll control within a vehicle is provided. The process includes, within a computerized controller using axle-based control to control a suspension system, operating programming to control pneumatic pressure supplied to each of a plurality of air spring devices within the suspension system to execute a vehicle leveling event including one of adjusting a height of the vehicle or maintaining the height of the vehicle. The process further includes operating programming to, simultaneously with the controlling the pneumatic pressure, utilize a plurality of active sway bars to provide an offset torque to the vehicle body. Each of the plurality of active sway bars is associated with one of a plurality of axles. Providing the offset torque is based upon a number of moles of air in each of the plurality of air spring devices and reducing the longitudinal roll.

Abstract: Various technologies described herein pertain to detecting sensor data to be annotated for autonomous vehicle perception algorithm training. A label identifying a type of an object is assigned to an object at a particular location in an environment based on sensor data generated by a sensor system of an autonomous vehicle for a given time. The label is assigned based on a confidence score assigned to the type of the object by a computer-implemented perception algorithm. The computer-implemented perception algorithm assigns the confidence score to the type of the object based on the sensor data corresponding to the particular location in the environment for the given time. An output of a heuristic is generated based on the label and/or the confidence score, and the output of the heuristic is used to control whether to cause the sensor data for the given time to be annotated.

Abstract: The subject disclosure relates to techniques for enabling secured access to vehicles. A process of the disclosed technology can include steps for determining, via at least one system status monitor, that at least one vehicle system of a vehicle is in a suboptimal operating condition, determining that the at least one vehicle system with the suboptimal operating condition is in control of at least one other vehicle system, and disabling automatically the at least one other vehicle system.

Abstract: An autonomous vehicle receives geographic location data defined via a mobile computing device operated by a user. The geographic location data is indicative of a device position of the mobile computing device. The autonomous vehicle also receives image data generated by the mobile computing device. The image data is indicative of a surrounding position nearby the device position. The surrounding position is selected from an image captured by a camera of the mobile computing device. A requested vehicle position (e.g., a pick-up or drop-off location) is set for a trip of the user in the autonomous vehicle based on the geographic location data and the image data. A route from a current vehicle position of the autonomous vehicle to the requested vehicle position for the trip of the user in the autonomous vehicle is generated. Moreover, the autonomous vehicle can follow the route to the requested vehicle position.

Abstract: A multi-tasking end effector system includes a base frame connected to a robot arm of a robot. A first shaft is rotatably supported on the base frame. A first pin-wheel assembly is rotatably mounted to the shaft at a first end of the base frame. Multiple first die assemblies are mounted to the first pin-wheel assembly. A second pin-wheel assembly is rotatably mounted to the shaft at a second end of the base frame. Multiple second die assemblies are mounted to the second pin-wheel assembly and individually oriented in mirror image configuration to one of the multiple first die assemblies. An index motor rotates the first shaft and co-rotates paired and mirror image die assemblies. First and second tab-bending actuators mounted to the base frame are operated to bend opposed cell tabs of a battery cell positioned between the first and second pin-wheel assemblies.

Abstract: In an exemplary embodiment, a method for determining a route using route segment characterizations is disclosed. The method includes receiving, by a processor, a destination. The method further includes determining, by the processor, one or more routes to the destination from a first location. The method further includes dividing, by the processor, each of the one or more routes into one or more route segments. The method further includes characterizing, by the processor, each of the one or more route segments according to propulsion resources available to a vehicle. The method further includes providing, by the processor, an optimized route from the one or more routes based on the characterization of the one or more route segments.

Abstract: The present technology provides a system that can update aspects of an authoritative map portion stored on an autonomous vehicle using low-resolution data from the at least one sensor of the autonomous vehicle, and therefore avoids the need for dispatching the special purpose mapping vehicle for these updates. The captured low-resolution data can be compared with the high-resolution map portion to determine that the sensor data reflects a feature in a way that is inconsistent with how that feature is represented in the authoritative map portion. The sensor data can then be used to relabel the authoritative map portion.

Abstract: The present application generally relates to network timing synchronization in the presence of link faults including apparatus and methods In various embodiments, a method includes generating a time synchronization signal, transmitting the time synchronization signal from a first switch to a second switch via a first link and from the first switch to a third switch via a second link, detecting a link failure of the first link, and transmitting the time synchronization signal from the second switch to the third switch via a third link in response to the link failure.

Abstract: An alignment member includes a first body member having a first end and a second end longitudinally opposite the first end, a second body member having a first end and a second end longitudinally opposite the first end, the second body member coupled to the first body member such that the first and second body members define a longitudinal axis of the alignment member, a first base member coupled to the second body member, a second base member rotatably coupled to the first base member, and a locking mechanism configured to engage with the first base member. The first base member rotates relative to the second base member to position the alignment member from a first position to a second position and the locking mechanism engages with the first base member to retain the alignment member in the second position.

Abstract: A workpiece accumulator system for a stamping machine includes linear actuators, nesting blocks, exit rails, and a first controller. The nesting blocks are disposed on moveable members of the linear actuators and arranged to vertically stack workpieces being fabricated by the stamping machine. The first controller communicates with a second controller that controls the stamping machine. The first controller controls the linear positions of the linear actuators to retract the nesting blocks from an initial position to accommodate placement of the one of the plurality of workpieces in a stack on the nesting blocks. The linear actuators are controlled to retract the nesting blocks to fully retracted positions to place the plurality of workpieces in the stack onto the exit rails when a quantity of the plurality of workpieces in the stack is equal to a desired quantity.

Abstract: A method for estimating a state of a battery pack using a controller having battery state estimator (BSE) logic includes receiving or delivering a constant baseline current via the battery pack. Current oscillations having time-variant frequency content are selectively injected into the baseline current via the controller in response to a predetermined condition. The baseline current and the current oscillations combine to form a final current. The method includes estimating a battery parameter via the BSE logic concurrently with the current oscillations to generate an estimated battery parameter, and estimating the present state of the battery pack via the controller using the estimated battery parameter. An electrical system includes a rotary electric machine that is electrically connected to and driven by the battery pack, and a controller configured to execute the method.

Abstract: Methods are provided for joint performance validation and include preparing a coupon from a blank by bending the blank to have a pair of legs disposed at substantially ninety degrees relative to each other. Another coupon is prepared by forming an opening in a segment of another blank and bending the segment approximately ninety degrees. The segment is disposed adjacent an end of the second blank. A test sample is prepared by joining the coupons together at a joint with a leg attached to the segment approximately at a center of the leg. The test sample is subjected to a force test to generate data for the performance validation.

Abstract: In an accordance with an exemplary embodiment, an energy director is provided for use in ultrasonic welding, the energy director including: a first raised region extending upward from a surface of a base of a component to be welded; and a second raised region extending upward from the first raised region; wherein the first raised region is disposed underneath the second raised region, such that when material of the second raised region melts, the material of the first raised region is not melted and maintains an adhesive bond line thickness.

Abstract: System and method for explaining driving behavior actions of autonomous vehicles. Combined sensor information collected at a scene understanding module is used to produce a state representation. The state representation includes predetermined types of image representations that, along with a state prediction, are used by a decision making module for determining one or more weighted behavior policies. A driving behavior action is selected and performed based on the determined one or more behavior policies. Information is then provided indicating why the selected driving behavior action was chosen in a particular driving context of the autonomous vehicle. In one or more embodiments, a user interface is configured to depict the predetermined types of image representations corresponding with the driving behavior action performed via the autonomous vehicle.

Abstract: A vehicle including a hybrid battery pack includes a first battery pack and a second battery pack. The first battery pack has a higher energy density than the second battery pack. The second battery pack has a higher power density than the first battery pack. A power inverter module is connected between the hybrid battery pack and a motor generator unit (MGU) that is connected to a powertrain of the vehicle. The power inverter module is configured to regulate power flow between the hybrid battery pack and the MGU. A battery management module is configured to: control switching of the power inverter module; selectively charge and discharge at least one of the first battery pack and the second battery pack; and selectively charge the first battery pack with power from the second battery pack.

Abstract: A battery control system includes T contactor paths connected in parallel between a battery and a load, where T is an integer greater than one. Each of the T contactor paths includes a first contactor and a second contactor connected in series with the first contactor. Each of the T contactor paths includes at least one of a first voltage sensor configured to sense a first voltage between the first contactor and the second contactor; and a current sensor configured to sense current flowing through the first contactor and the second contactor. A second voltage sensor is configured to sense a second voltage at one end of the T contactor paths. A third voltage sensor is configured to sense a third voltage at an opposite end of the T contactor paths.