Abstract: In various examples, image-based three-dimensional occupant assessment for in-cabin monitoring systems and applications are provided. An evaluation function may determine a 3D representation of an occupant of a machine by evaluating sensor data comprising an image frame from an optical image sensor. The 3D representation may comprise at least one characteristic representative of a size of the occupant, (e.g., a 3D pose and/or 3D shape), which may be used to derive other characteristics such as, but not limited to weight, height, and/or age. A first processing path may generate a representation of one or more features corresponding to at least a portion of the occupant based on optical image data, and a second processing path may determine a depth corresponding to the one or more features based on depth data derived from the optical image data and ground truth depth data corresponding to the interior of the machine.

Abstract: Apparatuses, systems, and techniques of identifying one or more distances to one or more objects. In at least one embodiment, one or more distances to one or more objects are identified based, at least in part on one or more first optical rays of a first image depicting an objects and one or more second optical rays a second images depicting the object. In at least one embodiment, one or more machine learning processes (e.g., neural network(s)) are used to identify a correspondence ray to determine distances to one or more objects.

Abstract: In various examples, an environment visualization pipeline may determine whether to generate or otherwise enable a visualization using an environmental modeling pipeline that models an environment as a 3D bowl or using an environmental modeling pipeline that models the environment using some other 3D representation, such as a detected 3D surface topology. The determination may made based on various factors, such as ego-machine state, (e.g., one or more detected features indicative of a designated operational scenario, proximity to a detected object, speed of ego-machine, etc.), estimated image quality of a corresponding environment visualization, and/or other factors. Accordingly, an environment around an ego-machine, such as a vehicle, robot, and/or other type of object, may be visualized in systems such as parking visualization systems, Surround View Systems, and/or others.

Abstract: A method includes: identifying an obstacle within a predetermined range of the lawnmower robot in a case where it is detected that positioning information of the lawnmower robot is lost; determining a first vector according to a first projection point of a first reference point of the obstacle on a ground and a second projection point of a second reference point of the lawnmower robot on the ground; wherein a starting point of the first vector is the first projection point, and an ending point of the first vector is the second projection point; and controlling, based on a posture of the lawnmower robot and the first vector, the lawnmower robot to move such that the lawnmower robot is extricated. In a case where the positioning information of the lawnmower robot is lost, the lawnmower robot can obtain a positioning signal and is extricated.

Abstract: A method for residential unit floorplan generation, includes obtaining a current status of a floorplan, performing a plurality of iterations to obtain a plurality of scores until a predetermined number of iterations is reached, and deploying the one or more rooms to be deployed according to a highest score of the plurality of the scores to update the floorplan. In each of the plurality of iterations, the method further includes obtaining room information of one or more rooms to be deployed through a particle swarm algorithm, according to the room information of the one or more rooms to be deployed, performing multiple Monte Carlo tree searches to obtain coordinate information of the one or more rooms to be deployed, and determining one of the plurality of scores of the room information and the coordinate information through an evaluation function.

Abstract: Techniques for text generation refinement are described. In some examples, a predicted text output is generated, wherein the predicted text output is selected from a plurality of predicted texts generated in response to the request, wherein the generating comprises: predicting a plurality of predicted texts using at least one machine learning model, scoring each of the plurality of predicted texts using at least one of intra-sample scoring and inter-sample scoring, computing a composite score for each of the plurality of predicted texts from the scores, ranking the plurality of predicted texts based at least in part the composite score, and selecting at least a highest ranked predicted text of the plurality of predicted texts as the predicted text output.

Abstract: A method for evaluating an on-site desorption effect of activated coke. An on-site desorption effect of activated coke is evaluated in combination with a laboratory simulation desorption process, an activated-coke desorption rate R is calculated by means of measuring the sulfur content of activated-coke samples before and after on-site desorption and the sulfur content of an activated-coke sample after laboratory simulation desorption, and then the on-site desorption effect of activated coke is evaluated, so as to ensure the recycling effect of activated coke. Therefore, the problem of it being impossible to accurately evaluate the on-site desorption effect of activated coke is solved, and an important guidance is provided for on-site process optimization control.

Abstract: A computer implemented method for learning an operator mapping from multiple input functions to a solution function of partial differential equations (PDEs) based on a Transformer model is disclosed. The method includes inputting coordinates of query points and the multiple input functions to the Transformer model; encoding the coordinates of query points and the multiple input functions into feature embeddings via respective encoders; and learning the operator by minimizing a mean square error (MSE) loss between output features processed by the Transformer model and ground-truth values of the solution function.

Abstract: Apparatuses, systems, and techniques to generate an image. In at least one embodiment, neural networks receive an inputted one or more images, generate feature and depth information, and a neural network uses said information to generate one or more images. In at least one embodiment, a processor comprises one or more circuits to use one or more first neural networks to generate one or more first images from a viewpoint outside of an object based, at least in part, on depth information generated using one or more second neural networks and feature information generated by one or more third neural networks. In at least one embodiment, Using a point cloud and a viewpoint as inputs, a third neural network generates an image of vehicle from said viewpoint while parking.

Abstract: In fields related to battery cathode material technologies, a nano-silicon composite material and a preparation method thereof, an electrode material, and a battery are provided to resolve large volume expansion of a cathode material of a battery and a serious side reaction with an electrolyte. The nano-silicon composite material includes a core, a first coating layer, and a second coating layer. The core includes a nano-silicon crystal. The first coating layer covers a surface of the core. The first coating layer is of a porous structure. A material of the first coating layer includes bisilicate and silicon oxide in a deoxidized state. The second coating layer covers a surface of the first coating layer. A material of the second coating layer includes silicon dioxide in a deoxidized state.

Abstract: Feedforward reasoning models that include a video encoder configured to generate feature tokens from an input video, logic to condition the feature tokens with camera parameters, at least one sparse attention head with two-way attention to transform settings from the feature tokens into a tracking token, a depth token, and a visibility token in accordance with an input prompt, and logic configured to transform the tracking token, depth token, and visibility token into track predictions for an object specified by the input prompt.

Abstract: Feedforward reasoning models that include a video encoder configured to generate feature tokens from an input video, at least one dense attention head, at least one sparse attention head with two-way attention logic configured to transform settings from the feature tokens into a tracking token, a depth token, and a visibility token in accordance with an input prompt, and logic configured to transform the tracking token, depth token, and visibility token into track predictions for an object specified by the input prompt.

Abstract: A method to predict and fit an APC of a LEO satellite considering attitude information is provided, which includes: transforming a spacecraft body-fixed coordinate system, obtaining a transformation matrix from orbital coordinate system to transformed spacecraft body-fixed coordinate system, obtaining rotation angles during a rotation process, obtaining rotation angles in orbit determination time period to predict rotation angles in orbit prediction time period, obtaining a transformation matrix from spacecraft body-fixed coordinate system to Earth-fixed coordinate system of each prediction moment, obtaining a correction vector from a CoM to a phase center of a downlink signal antenna in the Earth-fixed coordinate system at each prediction moment, and obtaining an orbit of the phase center of the downlink signal antenna of a LEO satellite, and performing an ephemeris parameter fitting on the orbit of the phase center of the downlink signal antenna of the LEO satellite in a fitting time period.

Abstract: A location-aware search assist capability identifies location-aware search query suggestions using location information associated with the location-aware search query suggestions. A user's search query input and location and a location associated with each location-aware search query suggestion candidates may be used to identify a set of search query suggestions for presentation to the user. Location-aware search query suggestion candidates may be ranked in accordance with a closeness of each one's location to the user's location. The ranking may be performed using a score, such as a popularity score associated with each search query suggestion candidate. The location-aware search query suggestion candidates having a location closer to the user's location may be promoted by adjusting each candidate's popularity score upward, and the search query suggestion candidates that are farther away from the user's location may be demoted by adjusting each such candidate's popularity score downward.

Abstract: Embodiments of the present disclosure, relate to the technical field of path planning, provide a method for path planning, an apparatus for path planning, and a computer device therefor. The method includes: controlling a lawnmower robot to travel along a boundary of a mowing area for at least one lap to obtain a plurality of position information points of the mowing area; performing a fitting process on the plurality of position information points to obtain a fitted curve; performing a polyline conversion process on sample points on the fitted curve to obtain a target polyline; and determining the target polyline as a mowing path for the mowing area. In this way, the operating efficiency of the lawnmower robot is improved.

Abstract: Embodiments of the present disclosure provide a method for localizing a lawnmower robot, an apparatus, and a readable storage medium. During the operation of the lawnmower robot, corresponding data is acquired by a wheel speedometer, an inertial positioning device, and an image sensing device disposed on the lawnmower robot; the acquired wheel speedometer data is analyzed to derive a first residual term, the inertial positioning data is analyzed to derive a second residual term, and the image data is analyzed to determine a third residual term; and a cost function is constructed based on the first, second, and third residual terms, and the current position information of the lawnmower robot is obtained by minimizing the cost function. By tightly coupling the data collected from multiple sensors in the manner described above, the present disclosure is advantageous for improving the accuracy of localization results of the lawnmower robot.

Abstract: Disclosed is a Bayesian classification recognition system based on an industrial PaaS platform, comprising: an IaaS infrastructure service layer, a G-PaaS graph neural network processing layer, an O-PaaS docking service layer and an SaaS system application layer. The G-PaaS graph neural network processing layer is configured for point cloud feature generation, point cloud feature learning, point cloud structure estimation and point cloud model classification; and the recognition accuracy of a workpiece point cloud model is improved through the Bayesian classification recognition system based on the industrial PaaS platform.

Abstract: A method for generating a set of adversarial patches for an image. The method includes segmenting the image into a plurality of regions; selecting a set of target regions that satisfies an attacking criterion by discretely searching of the plurality of regions; and generating a set of adversarial patches by using the set of target regions.

Abstract: Disclosed are a method for constructing a mowing path for multiple lawns, an electronic device, and a computer readable medium. The method includes: displaying an area map of a first lawn and an area map of a second lawn; receiving a first position and a second position, wherein the first position is a position within the area map of the first lawn, and the second position is a position within the area map of the second lawn; controlling a mower to travel from the first position to the second position to obtain a corridor path; and constructing a joint mowing path for the first lawn and the second lawn based on the corridor path, a mowing path of the first lawn, and a mowing path of the second lawn. No user intervention is required while the mower operates along the joint mowing path, thereby saving manpower and facilitating.

Abstract: Apparatuses, systems, and techniques to generate an image. In at least one embodiment, neural networks receive an inputted one or more images, generate feature and depth information, and a neural network uses said information to generate one or more images. In at least one embodiment, a processor comprises one or more circuits to use one or more first neural networks to generate one or more first images from a viewpoint outside of an object based, at least in part, on depth information generated using one or more second neural networks and feature information generated by one or more third neural networks. In at least one embodiment, Using a point cloud and a viewpoint as inputs, a third neural network generates an image of vehicle from said viewpoint while parking.