Abstract: A method for mitigating an adversarial attack includes receiving input data. The input data includes sensor data from a plurality of sensors and map data. The method further includes monitoring, in real time, an environment around an autonomous vehicle to identify a region that is possibly subject to an adversarial attack and determining a probability of the adversarial attack in the region. The method further includes determining whether the probability of the adversarial attack in the region that is possibly subject to the adversarial attack is greater than a predetermined threshold and, in response, planning a motion of the autonomous vehicle by taking into account the adversarial attack to generate a planned motion. The method further includes controlling a host vehicle to move in accordance with the planned motion.

Abstract: A method includes receiving sensed vehicle-state data, actuation-command data, and surface-coefficient data from a plurality of remote vehicles, inputting the sensed vehicle-state data, the actuation-command data, and the surface-coefficient data into a self-supervised recurrent neural network (RNN) to predict vehicle states of a host vehicle in a plurality of driving scenarios, and commanding the host vehicle to move autonomously according to a trajectory determined using the vehicle states predicted using the self-supervised RNN.

Abstract: A LIDAR-to-LIDAR alignment system includes a memory and an autonomous driving module. The memory stores first and second points based on outputs of first and second LIDAR sensors. The autonomous driving module performs a validation process to determine whether alignment of the LIDAR sensors satisfy an alignment condition. The validation process includes: aggregating the first and second points in a vehicle coordinate system to provide aggregated LIDAR points; based on the aggregated LIDAR points, performing (i) a first method including determining pitch and roll differences between the first and second LIDAR sensors, (ii) a second method including determining a yaw difference between the first and second LIDAR sensors, or (iii) point cloud registration to determine rotation and translation differences between the first and second LIDAR sensors; and based on results of the first method, the second method or the point cloud registration, determining whether the alignment condition is satisfied.

Abstract: A high pressure die casting (HPDC) system for casting ultra-large single-piece castings for vehicles. The HPDC system includes a clear feeding path from at least one ingate to a predetermined thicker section of a mold cavity, a last to solidify ingate having an equivalent or larger feeding modulus than the highest feeding modulus of the other ingates, and thermal management elements. The clear feeding path, last to solidify ingate, and thermal management elements ensure sufficient supplemental molten metal flow to the thicker portion of the mold cavity to accommodate for shrinkage of the thicker portion of an ultra large casting during the casting and solidification process.

Abstract: A system for control of an automated device includes a control system configured to operate a device during an operating mode corresponding to a first state in which the control system automatically controls operation, the operating mode prescribing that a user monitor the device operation during automated control, and a scheduling module configured to, during the operating mode, receive a request for the user to temporarily stop monitoring in order to perform a task unrelated to the device operation, allocate a time period during which automated control is maintained and the user stops monitoring, the time period including a non-monitoring period having a duration based on a minimum amount of time for the task, and put the device into a temporary state at initiation of the allocated time period during which the user stops monitoring and automated control is maintained.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: receive sensor data representing a perceived driving environment, select a reinforcement learning agent from a plurality of reinforcement learning agents based on a challenge score calculated using the sensor data and a desired driving style, and generate, via the selected reinforcement learning agent, a driving action based on the sensor data.

Abstract: A bipolar capacitor assisted battery includes a bipolar capacitor including a first capacitor, and a second capacitor. The second capacitor is connected in series with the first capacitor. A lithium ion battery is connected in parallel to the bipolar capacitor.

Abstract: A system includes an electronic device including a circuit having a semiconductor switch, and a switching control system operably connected to the semiconductor switch. The switching control system is configured to control a switching speed of the semiconductor switch based on a received voltage by altering at least one of a gate resistance and a gate capacitance of the semiconductor switch.

Abstract: An apparatus for assembling a conductor assembly for a PEM fuel cell includes an application module for applying first and second stripes of an adhesive onto a rolled-out segment of GDL material, wherein the first and second stripes run along respective first and second longitudinal edges of the GDL material defining an applied segment. A cutting module cuts the applied segment to form one or more cut segments each having a respective primary surface on which respective portions of the stripes are carried. A laminating module laminates a subgasket between two cut segments, wherein the subgasket has a window bounded by a window periphery, and the two cut segments are oriented with their primary surfaces facing and covering the window with their respective portions of the first and second stripes being in contact with the window periphery.

Abstract: A battery cell includes a case and an electrode stack disposed within the case. The battery cell includes an anode including a first conductive tab, a cathode including a second conductive tab, and a separator. The battery cell further includes two electrical connections, each attached to one of the first conductive tab or the second conductive tab and to one of a negative terminal and a positive terminal, respectively. The anode, the cathode, and the separator each include a common perimeter including a first portion matching a shape of an interior surface of the case and a second portion including a cut-out configured to recede from the interior surface. The second portion of the anode, the cathode, and the separator are aligned and create a region between the stack and the interior surface. The tabs and electrical connections are disposed within the region.

Abstract: A method of performing a probability tree analysis. The method includes identifying a plurality of nodes in a probability tree with each of the plurality of nodes having a probability vector. At least one node structural value is calculated for each of the plurality of nodes. The at least one node structural value quantifies an entropy of a subtree extending from a corresponding one of the plurality of nodes. The at least one node structural value is assigned to a corresponding one of the plurality of nodes. An analyzed probability tree is output including the at least one node structural value assigned to the corresponding one of the plurality of nodes.

Abstract: A method of analyzing a decision for an automated system. The method includes receiving a vector having a length. A plurality of distribution vectors is created each having a length that matches the length of the vector. Divergence calculations are performed with the vector and each of the plurality of distribution vectors. A minimum output value determined by the divergence calculations is calculated. A minimizing distribution vector is identified from the plurality of distribution vectors that corresponds to the minimum output value from the divergence calculations. A conclusiveness of a decision is determined based on the vector in view of the minimizing distribution vector.

Abstract: Systems and methods for manufacturing a product include at least one fabricating system to create a substrate with a lattice structure. A form receives the substrate. The form defines a cavity around the substrate. A forming system delivers a material into the cavity of the form so that the material flows into the lattice structure interweaving the material with the substrate to create a feature on the substrate from the material that is locked to the substrate by the lattice structure.

Abstract: Aspects of integrated hydrogen fuel cell injection units herein use additive manufacturing to form a single part. A space between a body and an ejector nozzle/venturi tube system forms an attenuation volume. The heat exchanger is integrated within the attenuation volume, saving space. The ejector nozzle/venturi tube, and the stack anode inlet to the fuel cell, are arranged through the heat exchanger and allow an injector at the base of the body to selectively emit hydrogen into the anode of the fuel cell. This architecture obviates the need for many O-rings and bolts used in present fuel injection systems using existing manufacturing techniques that may be unduly large and unwieldy and that may cause hydrogen leakage at different connection points.

Abstract: Systems and methods for securing a product joint with a lattice structure. A system includes at least one fabricating system to create a connector with the lattice structure. A force system applies a force to the connector so that a material of the product flows into the lattice structure interweaving the material with the lattice structure to secure the joint by the lattice structure.

Abstract: A system and method for estimation method for determining a location of a vehicle digital key wallet includes selecting, by a user, whether to store a digital key wallet in a cloud storage or within a secure telematics unit contained within a vehicle. The digital key wallet is used to initiate an event within the vehicle. A backoffice server stores data including a radio intelligence database and a rule-based vehicle pattern matrix. The digital key wallet is switched to a fallback device based on the status of a communication link with the secure telematics unit, the radio intelligence database, and the rule-based vehicle pattern matrix.