Abstract: A computer includes a processor and a memory storing instructions executable by the processor to predict a time to failure of a vehicle component according to a damage model generated from vehicle operating data, based on the predicted time to failure, retrieve a schematic of the vehicle component and input the schematic to an additive printer to manufacture a replacement vehicle component, and replace the vehicle component with the replacement vehicle component according to maintenance instructions that, based at least in part on the predicted time to failure, specify a time and location to replace the vehicle component.

Abstract: Systems, methods, and devices for verifying an identity of a user of a vehicle. The method includes receiving user authentication data from a vehicle sensor and generating a transaction token comprising the user authentication data. The method includes transmitting the transaction token to a blockchain database. The method includes receiving a message from the blockchain database comprising one or more of: a request for additional user authentication data; or an indication that a rider authentication server has verified the identity of the user.

Abstract: An assembly includes a roof rail. The assembly includes a vehicle seat having a seatback. The assembly includes an airbag supported by the roof rail. The airbag is inflatable vehicle-inboard from the roof rail to an inflated position. The airbag surrounds the seatback when the airbag is in the inflated position.

Abstract: An air register assembly for a vehicle includes a barrel and vanes operably coupled to the barrel. A knob assembly is operably coupled to the barrel and the vanes. The knob assembly includes a support body, at least one absorbent basket selectively coupled to the support body, and a cover selectively coupled over the at least one absorbent basket. The cover is configured to rotate between an opened position and a closed position. The opened position is configured to provide fluid communication with the at least one absorbent basket via apertures defined by the cover.

Abstract: A vehicle includes a cabin interior, a steering wheel assembly comprising a steering column, a steering wheel and an actuator configured to move the steering handle amongst a plurality of positions, and at least one sensor for sensing a user proximate to the vehicle and generating sensed data based on the sensed user. The vehicle also includes a controller determining one or more characteristics of the user from the sensed data and controlling the actuator to actuate the steering wheel to one of the plurality of positions based on the determined one or more characteristics of the user.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive an image frame from a camera, generate a feature map from the image frame, generate a depth map from the feature map, classify an object in the image frame based on the feature map, and estimate a distance to the object based on the depth map and based on an input to generating the feature map.

Abstract: A vehicle includes a seatbelt retractor. The seatbelt retractor includes a housing. The seatbelt retractor includes a spool having a first end and a second end each rotatably supported by the housing. The spool is elongated on an axis from the first end to the second end. The seatbelt retractor includes a torsion bar having a first end fixed to the first end of the spool and a second end operatively engaged with the housing. The torsion bar has a central cavity. The seatbelt retractor includes a heating filament disposed in the central cavity.

Abstract: Upon detecting a lane-change trigger to move an ego vehicle from a current lane to a target lane, a target vehicle is identified in the target lane. Then a set of candidate trajectories is built for the lane-change maneuver by, for each of the target vehicles in the target lane: determining a set of constraints for a lane-change maneuver based on current data collected in the ego vehicle, including speed and distance constraints for the ego vehicle, and adding to the set of candidate trajectories, from a stored set of trajectories, a candidate trajectory for the lane-change maneuver that satisfies the constraints for the lane-change maneuver. Upon determining that the set of candidate trajectories has been built for each of the target vehicles, an optimal trajectory is selected from the set of candidate trajectories. A longitudinal acceleration of the ego vehicle is commanded based on the optimal trajectory.

Abstract: A method of joining at least two substrates includes welding the at least two substrates together with a multi-step welding process. The multi-step welding process includes: reducing a mismatch between the at least two substrates by melting on both sides of the at least two substrates to form a melted portion that does not overlap a joint line between the at least two substrates with a first welding step; and increasing melt volume and penetration depth of the melted portion between the at least two substrates with a second welding step.

Abstract: Systems and methods are described for monitoring a high voltage electrical system in a vehicle. An interface circuit is configured to provide isolation between a high voltage component of the vehicle and a control module. The interface circuit comprises a high voltage constant current source, a voltage threshold detector and an electrical isolation circuit. The high voltage constant current source is configured to receive an input at a first voltage from the high voltage component. The voltage threshold detector is configured to receive an output from the high voltage constant current source and to output a signal to indicate whether the voltage of the high voltage component is at, or below, a desired voltage.

Abstract: A method includes obtaining state information from one or more sensors of a digital twin. The method includes determining an action at the first routing control location based on the state information, where the action includes one of a pallet merging operation and a pallet splitting operation, and determining a consequence state based on the action. The method includes calculating a transient production value based on the consequence state and a transient objective function, calculating a steady state production value based on the consequence state and a steady state objective function, and selectively adjusting one or more reinforcement parameters of the reinforcement learning system based on the transient production value and the steady state production value.

Abstract: A computer-implemented logistics method of arranging delivering of items to recipients situated at different recipient locations, comprising: recording items received at a distribution centre, clustering the records according to location of the recipient, locating a hub position for each cluster, further clustering the records, creating an individual schedule for each agent with events and locations and timings for the events, and instructing the agent to deliver the items by providing individual schedule information.

Abstract: A vehicle includes a fuel-cell system having a fuel cell, a purge valve, and a drain line extending from the purge valve. A controller is programmed to open the purge valve according to a baseline purge routine when the drain line slopes away from the purge valve, and open the purge valve according to an enhanced purge routine when the drain line slopes towards the purge valve.

Abstract: Autonomous vehicle trailer loading with smart trailer are disclosed herein. An example method includes receiving a request to activate a self-loading procedure for an autonomous vehicle, executing the self-loading procedure by an autonomous vehicle controller, the self-loading procedure including causing the autonomous vehicle to navigate to a transportation platform, determining a visual identifier of the transportation platform using output from a sensor platform of the autonomous vehicle, and causing the autonomous vehicle to navigate onto or into the transportation platform and park at a parking spot of the transportation platform designated for the autonomous vehicle.

Abstract: A vehicle includes a dashboard having a lower portion that defines a recess. The lower portion has a bottom surface and a recess surface. The bottom surface is adjacent to the recess surface, and the recess surface of the lower portion defines the recess. The vehicle also includes a desk operably coupled to the dashboard and movable between an undeployed position and a deployed position. In the undeployed position, the desk is received within the recess and an underside surface of the desk is generally flush with the bottom surface of the lower portion of the dashboard. In the deployed position, the position of the desk is further vehicle-rearward than the position of the desk in the undeployed position.

Abstract: A cargo management system for a cargo area of a vehicle includes a first retention feature and a second retention feature. The first retention feature is formed in a first panel structure of the cargo area and adapted to support a first end of a support member. The second retention feature is formed in an opposing second panel structure of the cargo area and adapted to support an opposed second end of the support member. The first and second retention features are configured to inhibit movement of the support member in a longitudinal direction of the vehicle while also allowing the support member to move laterally past one of the first and second retention features into a space defined by a respective panel structure.

Abstract: Methods and systems are provided for estimation of a road roughness index (RRI) and adjusting vehicle operation based on the metric. In one example, a method may include estimating the RRI as a function of a pitch energy and a roll energy of the vehicle travelling on the road. In response to the RRI being higher than a threshold, engine operation such as EGR flow rate may be adjusted.

Abstract: A mechanical device for grasping an object without a power source includes a receiver and at least one grabber assembly secured to the receiver. The grabber assembly includes first and second arms with proximal end portions and distal end portions, hooks disposed at the distal end portions, and a mechanical linkage disposed near the proximal end portion of the first arm and the second arm. The mechanical linkage kinematically couples the first arm to the second arm. Displacement of the first arm or the second arm against the object causes movement of the mechanical linkage and thus movement of the second arm or first arm, respectively.

Abstract: Chemical formulations for chemical products can be represented by digital formulation graphs for use in machine learning models. The digital formulation graphs can be input to graph-based algorithms such as graph neural networks to produce a feature vector, which is a denser description of the chemical product than the digital formulation graph. The feature vector can be input to a supervised machine learning model to predict one or more attribute values of the chemical product that would be produced by the formulation without actually having to go through the production process. The feature vector can be input to an unsupervised machine learning model trained to compare chemical products based on feature vectors of the chemical products. The unsupervised machine learning model can recommend a substitute chemical product based on the comparison.