Abstract: Examples described herein provide a computer-implemented method that includes receiving first data from a sensor of a vehicle. The method further includes determining, by a processing device, whether an incident external to the vehicle has occurred by processing the first data using a machine learning model. The method further includes, responsive to determining that an incident external to the vehicle has occurred, initiating recording of second data by the sensor. The method further includes, responsive to determining that an incident external to the vehicle has occurred, taking an action to control the vehicle.

Abstract: A system for adaptive in-drive updating, for a vehicle travelling on a route, includes a controller adapted to obtain a pre-drive energy consumption prediction for the route, via an energy consumption predictor. An in-drive updating module is selectively executable by the controller at a timepoint during the route at which a completed portion of the route has been traversed and a remaining portion remains untraversed. The controller is adapted to obtain an actual energy consumption for segments in the completed portion of the route. The controller is adapted to obtain at least one modification factor based on a comparison of the actual energy consumption and the pre-drive energy consumption prediction for the segments in the completed portion of the route. The pre-drive energy consumption prediction for the remaining portion of the route is adjusted based on the modification factor.

Abstract: A vehicle, an antenna assembly of the vehicle, and a method of assembling the antenna is disclosed. The vehicle includes a housing having a passage formed therethrough. A circuit board is disposed within the housing. An antenna element is coupled to the circuit board and passes through the passage. A plug fills an annular volume of the passage between the antenna element and the housing.

Abstract: A method for using idle computing power of an electric vehicle includes sending the computing tasks and the task rates for performing the computing tasks to a vehicle controller of the electric vehicle and receiving an acceptance signal from the vehicle controller. The acceptance signal is indicative that the vehicle controller accepted to perform the computing tasks. The method further includes commanding a charging infrastructure to supply electrical power the electric vehicle while the vehicle controller performs the computing tasks.

Abstract: An electronic solid-state switch assembly includes a base plate and a heat exchanger; an electrically insulating layer and a direct bonded substrate affixed to the base plate; a first terminal and a second terminal; a plurality of power transistors; a plurality of gate drivers; a communication interface, a current sensor, and a snubber circuit; and a controller. The plurality of gate drivers are operatively coupled to the plurality of power transistors. The plurality of power transistors are arranged in parallel on the direct bonded substrate between the first terminal and the second terminal. The plurality of power transistors are electrically connected to the first terminal and to the second terminal. The controller is in communication with the plurality of gate drivers, the current sensor, and the communication interface. The controller is configured to control, via the plurality of gate drivers, the plurality of power transistors.

Abstract: A system processes unstructured data to identify a plurality of subsets of text in a set of text in the unstructured data and determines, for a subset from the plurality of subsets, probabilities based on a position of the subset in the set of text, a part of speech (POS) of each word in the subset, and POSs of one or more words on left and right hand sides of the subset, a number of the one or more words being selected based on a length of the set of text. The system generates a feature vector for the subset, the feature vector including the probabilities and additional features of the subset; and classifies, using a classifier, the subset into one of a plurality of classes based on the feature vector for the subset, the plurality of classes representing an ontology of a domain of knowledge.

Abstract: The subject disclosure relates to ways to resolve autonomous vehicle (AV) routes based on verbal descriptions of landmark features. In some aspects, a process of the disclosed technology includes steps for receiving speech instructions, wherein the speech instructions indicate an autonomous vehicle (AV) destination, analyzing the speech instructions to identify one or more landmarks associated with the AV destination, and determining location information corresponding with the one or more landmarks. In some aspects, the process further includes calculating a route based on the location information corresponding with the one or more landmarks. Systems and machine-readable media are also provided.

Abstract: The subject disclosure provides techniques for enriching user reviews and providing improved user recommendations using data collected by autonomous vehicles (AVs). In some aspects, a process of the disclosed technology includes steps for receiving a ride request wherein the ride request specifies a pick-up location associated with a user identifier (ID), navigating an autonomous vehicle to the pick-up location to provide ride service for a user associated with the user ID, and receiving review information from the user, wherein the review information relates to a product or service consumed by the user. In some aspects, the process can also include steps for associating the review information with the user ID, and enriching the review information using trip information associated with the user ID. Systems and computer-readable media are also provided.

Abstract: Examples described herein provide a method that includes determining whether a vehicle is operating in a first high voltage mode or a second high voltage mode. The method further includes, responsive to determining that the vehicle is operating in the first high voltage mode, providing electric power to an electric motor at a first high voltage and providing electric power to an auxiliary device at a second high voltage that is different than the first high voltage. The method further includes, responsive to determining that the vehicle is operating in the second high voltage mode, providing electric power to the electric motor at the second high voltage and providing electric power to the auxiliary device at the second high voltage.

Abstract: A rechargeable energy storage system may include a series arrangement of a plurality of batteries coupled to a first DC bus at a first DC voltage. A DC to DC converter may include a multi-input DC input stage coupled to a multi-output DC output stage. The multi-input DC input stage may include multiple distributed DC inputs, each distributed DC input being coupled to a respective one of the plurality of batteries. The multi-output DC output stage may include multiple aggregated DC outputs. At least one controllable switch may couple one or more of the multiple aggregated DC outputs to one or more other DC buses.

Abstract: A battery cell pack has a plurality of battery cells that are assembled into a prismatic frame, with deformable separators interposed to accommodate elastic and plastic deformation caused by cyclic and acyclic expansion and contraction thereof during charging and discharging over the life of the battery cell pack. The battery cells are arranged in a horizontal stack within the prismatic frame, and the deformable separators are interposed between subsets of the battery cells. The deformable separators exert compressive force on the subsets of the battery cells along a longitudinal axis that is defined by the horizontal stack. The compressive force exerted by the deformable separators is at least a minimum force over a service life of the battery cell pack.

Abstract: A vehicle having at least one vehicle access secured by a first lock and at least one secure area secured by a second lock. The vehicle may also have a receiver configured to receive a command from a remote computing system to unlock the vehicle access or the secure area.

Abstract: A Lidar system and method of detecting an object is disclosed. The Lidar system includes a photodetector, a spectrum analyzer and a processor. The photodetector generates an electrical signal in response to a reflected light beam received at the photodetector, the reflected light beam being a reflection of a chirp signal from the object. The electrical signal has a bandwidth the same as a bandwidth of the chirp signal. The spectrum analyzer includes a power divider that partitions the electrical signal into a plurality of channels, an analog-to-digital converter that converts the electrical signal within a selected channel from an analog signal to a digital signal, and a comb filter that provides output from the selected channel from the power divider to the analog-to-digital converter. The processor determines a parameter of the object from the digital signal in the selected channel.

Abstract: A method of caching large data objects of greater than 1 GB, comprising: populating a sharded cache with large data objects backfilled from a data store; servicing large data object requests from a plurality of worker nodes via the sharded cache, comprising deterministically addressing objects within the sharded cache; and if a number of requests for an object within a time exceeds a threshold: after receiving a request from a worker node for the object, sending the worker node a redirect message directed to a hot cache, wherein the hot cache is to backfill from a hot cache backfill, and wherein the hot cache backfill is to backfill from the sharded cache.

Abstract: A system for active roll control for a vehicle body is provided and includes a sensor operable to monitor a tilt of the body and a suspension system. The suspension system includes an active sway bar including a first bar portion, a second bar portion, and an active roll control motor disposed between the first bar portion and the second bar portion. The active roll control motor is operable to turn the first bar portion in relation to the second bar portion. The system further includes a computerized active roll control controller which is operative to monitor a driving mode including one of straight-line driving and rounding a curve on a road, monitor an output of the sensor, determine a desired roll moment based upon the driving mode and the output of the sensor, and control the active roll control motor based upon the desired roll moment.

Abstract: The disclosed technology provides solutions for improving the operational efficiency and safety of autonomous vehicles (AVs). In some implementations, the disclosed technology encompasses methods for performing vehicle clustering or platooning, for example, that can include steps for computing navigation routes for each of a plurality of autonomous vehicles (AVs), identifying a route overlap for a first AV and a second AV selected from among the plurality of AVs, and transmitting a clustering instruction to the first AV and the second AV based on the route overlap, wherein the clustering instruction is configured to cause the first AV and the second AV to initiate a clustering configuration. Systems and machine-readable media are also provided.

Abstract: Systems and methods to perform behavioral planning in an autonomous vehicle from a reference state involve generating a set of actions of a fixed size and fixed order according to a predefined methodology. Each action is a semantic instruction for a next motion of the vehicle. A set of trajectories is generated from the set of actions as an instruction indicating a path and a velocity profile to generate steering angles and accelerations for implementation by the vehicle. A trajectory filter is applied to filter the set of trajectories such that unfiltered trajectories are candidate trajectories. Applying the trajectory filter includes assessing the path and velocity profile indicated by each of the set of trajectories. A selected trajectory is used to control the vehicle or the action that corresponds to the selected trajectory is used in trajectory planning to generate a final trajectory that is used to control the vehicle.