Abstract: Described herein are methods and systems for obtaining high-quality images, which may be suitable for various applications such as training and operating artificial intelligence (AI) systems. Specifically, a system may comprise multiple cameras and one or more actuators that are capable of moving these cameras relative to each other. For example, these cameras may form one or more stereo pairs, each pair having its stereo axis. The actuators can change baselines in these pairs and/or tilt these stereo axes relative to the imaged objects to address possible self-similarity issues associated with the shape of these objects and their orientation relative to the cameras. In some examples, the simultaneous images captured by these cameras are used to construct a three-dimensional (3D) model. The fidelity of this model is then used to determine the position of the cameras (as a camera unit or individually for each camera).

Abstract: One or more structural equations modeling a physical process over time may be sampled using simulated parameter values to generate input data signal values. A noise generator may be applied to the input data signal values to generate noise values. The noise values and the input data signal values may be combined to determined noisy data signal values. These noisy data signal values may in turn be used in combination with one or more states to train a prediction model.

Abstract: The failure modes of mechanical components may be determined based on text analysis. For example, a word embedding may be determined based on a plurality of text documents that include a plurality of maintenance records characterizing failure of mechanical components. A vector representation for a particular maintenance record may then be determined based on the word embedding. Based on the vector representation, the particular maintenance record may then be identified as belonging to a particular failure mode out of a set of possible failure modes.

Abstract: Described herein are DC-DC converters with electronic module cooling units used for air-convection cooling of some components of power electronic modules and conductive cooling of other components, e.g., switching sub-modules. A cooling unit may have a heat exchanger and a cooling plate, thermally coupled to one or more heat exchangers and one or more switching sub-modules. For example, the cooling plate can be positioned between and thermally coupled to heat exchangers. One fan can direct air through one heat exchanger and to one power electronic module as a part of convection cooling. An additional fan can direct air through the second heat exchanger and to the second power electronic module. The cooling plate can be also positioned between and thermally coupled to switching sub-modules of these power electronic modules thereby enabling conductive cooling. The plate-cooling liquid is pumped through the cooling plate.

Abstract: Electric lawnmowers comprise drive units and mowing units disengageably coupled to the drive units. For example, a drive unit can be disengageably coupled to any one of multiple mowing units (e.g., rotating mowing units, reel mowing units) collecting forming a mowing system. For example, each of the drive and mowing units may be equipped with corresponding mechanical-engagement structures that are configured to be disengageably coupled. Each mowing unit is equipped with its electric motor (e.g., for rotating the cutting blades or the reel of that unit). The electric motor may comprise an electric connector, which is disengageably coupled to the drive unit's electrical wiring. In some examples, each mowing unit can also form a liquid disengageable coupling for circulating a thermal liquid between the drive unit and mowing unit, e.g., for cooling various components of the drive unit.

Abstract: Electric lawnmowers comprise mowing-unit decks with fluid passages used for cooling batteries, power electronics units, and/or drive motors. Specifically, a lawnmower comprises a drive unit (with a battery, power electronics, and one or more drive motors) and a mowing unit (with a mowing-unit deck). The deck's fluid passage is fluidically coupled to the drive unit (e.g., the motor and power electronics). The thermal liquid is heated by the drive unit's components and cooled as the liquid passes through the deck's fluid passage. The mowing unit may be equipped with a pump (for circulating this liquid), which can be powered by an electric motor on the mowing unit. The same motor may be used for rotating the cutting blades. The drive unit may have an additional cooling circuit providing immersion cooling to the batteries.

Abstract: The failure modes of mechanical components may be determined based on text analysis. For example, a word embedding may be determined based on a plurality of text documents that include a plurality of maintenance records characterizing failure of mechanical components. A vector representation for a particular maintenance record may then be determined based on the word embedding. Based on the vector representation, the particular maintenance record may then be identified as belonging to a particular failure mode out of a set of possible failure modes.

Abstract: Remaining useful life may be estimated for a machine component by training a prediction model, even when limited data from actual failures is available. Feature data such as sensor readings associated with a mechanical process may be collected over time. Such readings may be paired with estimates of remaining useful life, for instance as extracted from unstructured text of maintenance records. Such data may be used to train and test the prediction model.

Abstract: A first plurality of predictor values occurring during or before a first time interval may be received. An estimated outcome value may be determined for a second time interval by applying a prediction model via a processor to the first plurality of predictor values. A designated outcome value occurring during the second time interval and a second plurality of predictor values occurring during or before the second time interval may be received. An error value may be determined based on the estimated outcome value and the designated outcome value. A drift value for a second time interval may be determined by fitting a function to the second plurality of predictor values. The prediction model may be updated when it is determined that the drift value exceeds a designated drift threshold or that the error value exceeds a designated error threshold.

Abstract: Described herein are electric vehicles comprising power distribution systems and methods of operating thereof. Specifically, a power distribution system is mechanically coupled to an electric motor, a road wheel, and an auxiliary unit. This system is configured to switch among multiple operating modes and selectively transfer mechanical power among the electric motor, wheel, and auxiliary unit. For example, the power distribution system is configured to transfer mechanical power between the electric motor and the road wheel, but not the auxiliary unit, when switched to a wheel operating mode. The power distribution system is configured to transfer mechanical power between the electric motor and the auxiliary unit, but not the road wheel, when switched to an auxiliary operating mode. The power distribution system is configured to transfer mechanical power between the electric motor, the auxiliary unit, and the road wheel when the system is switched to a combined operating mode.

Abstract: Described herein are battery modules comprising integrated module converters, electric-vehicle battery systems comprising such modules, and methods of operating thereof. An electric-vehicle battery system comprises a high-voltage battery pack and high-voltage contactors that controllably isolate the pack's high-voltage area from other areas in the vehicle. The pack comprises multiple battery modules with battery cells and a primary module converter constantly connected to these cells. Each module has a lower voltage than the entire pack. The power output from the primary module converters is used to operate a battery controller and to close/activate the contactors in response to the switch position (e.g., an ignition switch). The primary module converters can be either constantly activated or controllably activated in response to the switch moving into an activated position. For example, a secondary module converter, with a lower power rating, can be used for this primary module converter activation.

Abstract: Described herein are vehicle charging systems, each comprising a recharge vehicle and a work vehicle configured to form an electrical connection and charge the work vehicle battery from the recharge vehicle battery. In some examples, this charging is performed at 500 kW or more or even at 1,000 kW or more. Furthermore, the connection and/or charging can be performed while both vehicles are moving (e.g., the recharge vehicle moving in front of the work vehicle). The recharge vehicle comprises one or more DC-DC converters, configured to boost a first voltage (V1) of the recharge vehicle battery to a second voltage (V2) of the work vehicle battery. It should be noted that these voltages vary depending on the state of charge of these batteries. In some examples, each DC-DC converter utilizes a combination of immersion, conductive, and convective cooling for different components of the converter.

Abstract: Described herein are DC-DC converters having various immersion-cooling features enabling high-power applications, such as cross-charging electric vehicles. For example, the inductor of a DC-DC converter may be formed using metal and insulator sheets stacked and wound into an inductor coil assembly. The metal sheet comprises grooves, extending parallel to the coil axis and forming coil fluid pathways through this assembly thereby providing immersion cooling to the inductor. An inductor-cooling liquid may be pumped through these fluid pathways while being in direct contact with the metal sheet, at least around the grooves. In some examples, these grooves are distributed along the entire length of the metal sheet. Multiple inductors may be used to enable operations of multiple converter units, e.g., operating out of phase. These inductors may be fluidically interconnectors and have the same cooling features.

Abstract: Described herein are methods and systems for controlling differential wheel speeds of multi-independent-wheel vehicles, such as four-wheel-drive electric tractors (4WD-ETs). Specifically, a method comprises determining a target speed for each wheel of the vehicle based on at least the steering input. The linear travel speeds (corresponding to these target speeds) of any two wheels are different when the vehicle turns (steering input deviates from a no-steering baseline) or the same when the vehicle travels in a straight line (steering input is at the no-steering baseline). Each target wheel speed is then used to control the rotational speed of the corresponding electric motor, which independently drives one of the vehicle’s wheels. This process of determining the target wheel speeds and independently controlling all electric motors is frequently repeated such that the vehicle can be propelled through the turn at the desired speed with minimal wheel slip.

Abstract: Described herein are swappable battery modules comprising immersion-thermally controlled prismatic battery cells and methods of operating thereof. A module comprises a tubular enclosure attached (e.g., glued) to different surfaces of the cells and forming two fluid channels with one side of the cells and two additional fluid channels with the opposite side. The module also comprises a first end plate, which is attached to the tubular enclosure and comprises two electrical terminals for connecting to an electric vehicle (EV) and/or external charger. The first end plate also comprises a first fluidic port (fluidically coupled with two fluid channels) and a second fluidic port (fluidically coupled to the remaining two fluid channels), both are configured to form fluidic coupling to the electric vehicle and/or the external charger. The module also comprises a second end plate that fluidically interconnects paid fluid channels from different cell sides.

Abstract: A feature data segment may be determined by applying a feature segmentation model to a test data observation. The feature segmentation model may be pre-trained via a plurality of training data observations and may divide the plurality of training data observations into a plurality of feature data segments. A predicted target value may be determined by applying to a test data observation a prediction model pre-trained via a plurality of training data observations. One or more distance metrics representing a respective distance between the test data observation and the feature data segment along one or more dimensions may be determined. The one or more distance metrics may be represented in a user interface. An updated prediction model and an updated feature segmentation model that both incorporate the test data observation and the training data observations may be determined based on user input.

Abstract: In many industrial settings, a process is repeated many times, for instance to transform physical inputs into physical outputs. To detect a situation involving such a process in which errors are likely to occur, information about the process may be collected to determine time-varying feature vectors. Then, a drift value may be determined by comparing feature vectors corresponding with different time periods. When the drift value crosses a designated drift threshold, a predicted outcome value may be determined by applying a prediction model. Sensitivity values may be determined for different features, and elements of the process may then be updated based at least in part on the sensitivity values.

Abstract: Systems and methods are disclosed for training a previously trained neural network with incremental dataset. Original train data is provided to a neural network and the neural network is trained based on the plurality of classes in the sets of training data and/or testing data. The connected representation and the weights of the neural network is the model of the neural network. The trained model is to be updated for an incremental train data. The embodiments provide a process by which the trained model is updated for the incremental train data. This process creates a ground truth for the original training data and trains on the combined set of original train data and the incremental train data. The incremental training is tested on a test data to conclude the training and to generate the incremental trained model, minimizing the knowledge learned with the original data. Thus, the results remain consistent with the original model trained by the original dataset except the incremental train data.

Abstract: Described herein are methods and systems for remote charging of work vehicles using recharge vehicles. A recharge vehicle is equipped with power storage that has a sufficient capacity for propelling the recharge vehicle between a charging station (used for charging the recharge vehicle) and a work location (of the work vehicle) and also for charging the work vehicle at the work location. In some examples, the charging of the work vehicle and even the connection between the vehicles are formed while the work vehicle continues to operate. This approach helps to maximize the operating time of the work vehicle. Furthermore, this approach relaxes the charge rate requirement for charging the recharge vehicle and also for charging the work vehicle as well as the location of the charging station (for charging the recharge vehicle). In some examples, work vehicles and/or recharge vehicles are autonomous vehicles and use vehicle-to-vehicle coordination features.

Abstract: Electric vehicles include adjustable battery positions and/or adjustable track widths for controlling vehicle stability. In some examples, an electric vehicle comprises a positioning mechanism configured to move the battery pack relative to the support structure (e.g., operable as the vehicle's frame) to change the vehicle's COG. The battery pack can be moved in response to other vehicle operations, e.g., COG changes caused by adding/moving loads, changes to the route grade, and the like. The battery pack can be slidably coupled to the support structure. In some examples, an electric vehicle comprises a track adjustment mechanism configured to move the vehicle's wheel axle relative to the support structure, along the wheel axle center axis, thereby changing the track width. The wheel axle can be coupled to a hub motor. In some examples, the battery is moved, and/or the track width is changed during the vehicle's operation.