Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for obtaining a training data set comprising a plurality of training point clouds and, for each training point cloud, a corresponding set of images; and training, on the training data set, a point cloud processing neural network that is configured to process an input point cloud comprising a plurality of points to generate a respective feature for each of the plurality of points, the training comprising, using, as target features for the point cloud processing neural network, features generated by processing the corresponding sets of images using a pre-trained computer vision neural network.

Abstract: Methods, systems, and apparatus for predicting future trajectories of agents in an environment. In one aspect, a system comprises one or more computers configured to receive sensor data of an environment having one or more agents. The system decomposes the sensor data into a plurality of scene elements in the environment, and the system generates multiple tokens including a respective token for each respective scene element of the multiple scene elements in the environment. The system processes the multiple tokens using a decoder model to generate a respective predicted trajectory for the one or more agents in the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

Abstract: A device includes a chamber, a lid, heating elements, a base, and a controller. The chamber is a structure containing a inner cavity, the base is below the chamber, and the heating elements are between a lower surface of the chamber and the base. Cooling fins are in the inner cavity connected to a lower surface of the inner cavity and are close to the heating elements. Channels for liquid circulation are provided between fins and between the fins and an inner wall of the chamber. The lid is above the chamber and seals the inner cavity so that the inner cavity is closed. Gas outlet ports are on the lid. Due to the cooling fins, when the heating elements heat liquid fuel in the inner cavity, the liquid fuel is heated uniformly, and the gasification process is stable and controllable, avoiding explosive boiling of the liquid fuel.

Abstract: A burner for burning gaseous fuel includes a gas intake port, several horizontal portions, and several inclined portions. One end of each inclined portion located at a lower position is connected and fixed to one end of a horizontal portion, and the other ends of all the horizontal portions are connected to each other either directly or by means of a combustion chamber main body. The horizontal portions, the inclined portions, and the combustion chamber main body are in communication with each other. The inclined portions are inclined with respect to the horizontal portions. The gas intake port is provided at the very bottom of the burner. When a gaseous fuel is introduced and ignited, flames burn in each of the combustion chamber main body, the horizontal portions, and the inclined portions, thereby forming a flame effect in a three-dimensional (3D) form.

Abstract: A fireplace includes a housing, a burner, a gasification device, a liquid supply device, a fuel tank, and a controller. The burner includes an intake port, horizontal portions, and inclined portions. Ends of inclined portions are connected to ends of horizontal portions, and the other ends of the horizontal portions are connected to each other. The horizontal portions, the inclined portions, and the main body each have a hollow structure and are in communication. The inclined portions are inclined with respect to the horizontal portions, and the inclined portions and the horizontal portions are combined into a three-dimensional shape. The intake port is below the burner and communicates with the interior of the burner. The horizontal portions include first flame holes, the inclined portions include second flame holes, and the main body includes third flame holes. Flames burn in the main body, the horizontal portions, and the inclined portions.

Abstract: Disclosed are a device for supplying liquid at a constant amount and a method for controlling the same, and the device for supplying liquid at a constant amount comprises a constant amount chamber, an input pump, an output pump, a liquid level detection device, and a controller; the input pump is provided with an input pump liquid feeding pipe and an input pump liquid discharging pipe; the output pump is provided with an output pump liquid feeding pipe and an output pump liquid discharging pipe; the input pump, the output pump, and the liquid level detection device are each in matched connection with the controller. In the present invention, by cyclic operation, a liquid volume between a high liquid level and a low liquid level is delivered at a constant amount in each cycle, so that liquid fuel is supplied at a constant amount.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generated simulated sensor data. One of the methods includes obtaining a surfel map generated from sensor observations of a real-world environment and generating, for each surfel in the surfel map, a respective grid having a plurality of grid cells, wherein each grid has an orientation matching an orientation of a corresponding surfel, and wherein each grid cell within each grid is assigned a respective color value. For a simulated location within a simulated representation of the real-world environment, a textured surfel rendering is generated, including combining color information from grid cells visible from the simulated location within the simulated representation of the real-world environment.

Abstract: Disclosed in the present disclosure is a movably installed ejector pipe for a gas fireplace, the nozzle and the limit seat are fixed to the substrate, the ejector pipe is inserted between the limit seat and the nozzle, the limit seat is provided inside with a first inner bore and a second inner bore of a stepped shape, the first inner bore is below the second inner bore and is larger than the second inner bore, a head of the ejector pipe is provided with a groove. In the gas fireplace provided in the present disclosure, because a limit seat is added, the ejector pipe can swing at a certain angle within the limit seat, so that a placing angle of a burner can be finely adjusted and thereby the burner is in a position that allows for the optimal viewing effect of flame combustion.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing three-dimensional auto-labeling on sensor data. The system obtains a sensor data segment that includes a temporal sequence of three-dimensional point clouds generated from sensor readings of an environment by one or more sensors. The system identifies, from the sensor data segment, (i) a plurality of object tracks that each corresponds to a different object in the environment and (ii) for each object track, respective initial three-dimensional regions in each of one or more of the point clouds in which the corresponding object appears. The system generates, for each object track, extracted object track data that includes at least the points in the respective initial three-dimensional regions for the object track.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining estimated ground truth object keypoint labels for sensor readings of objects. In one aspect, a method comprises obtaining a plurality of sets of label data for a sensor reading of an object; obtaining respective quality control data corresponding to each of the plurality of sets of label data, the respective quality control data comprising: data indicating whether the labeled location of the first object keypoint in the corresponding set of label data is accurate; and determining an estimated ground truth location for the first object keypoint in the sensor data keypoint from (i) the labeled locations that were indicated as accurate by the corresponding quality control data and (ii) not from the labeled locations that were indicated as not accurate by the corresponding quality control data.

Abstract: Provided are a calcium-sensing receptor (CaSR) agonist composition and an application thereof. Specifically, provided is a pharmaceutical composition of a polypeptide CaSR agonist, the composition comprising an active ingredient, a buffer and an osmotic pressure regulator. The present composition has high stability, may be stored for a long time, may effectively reduce the plasma parathyroid hormone, and has a low level of histamine release.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating trajectory predictions for one or more target agents, e.g., a vehicle, a cyclist, or a pedestrian, in an environment. In one aspect, one of the methods include: obtaining scene context data characterizing a scene at a current time point in an environment that includes multiple target agents; generating, from the scene context data, an encoded representation of the scene in the environment; and generating, by a diffusion model based on the encoded representation, a respective trajectory prediction output that predicts a respective future trajectory for each of the multiple target agents after the current time point.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a semantic segmentation neural network for point clouds. One of the methods includes: obtaining a plurality of training points divided into a respective plurality of components; obtaining, for each of the respective plurality of components, data identifying a ground truth category for one or more labeled point; processing each training points using a semantic segmentation neural network to generate a semantic segmentation that includes a respective score for each of the plurality of categories; determining a gradient of a loss function that penalizes the semantic segmentation neural network for generating, for points in the component, non-zero scores for categories that are not the ground truth category for any labeled point in the component; and updating, using the gradient, the parameters of the semantic segmentation neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating realistic full-scene point clouds. One of the methods includes obtaining an initial scene point cloud characterizing an initial scene in an environment; obtaining, for each of one or more objects, an object point cloud that characterizes the object; and processing a first input comprising the initial scene point cloud and the one or more object point clouds using a first neural network that is configured to process the first input to generate a final scene point cloud that characterizes a transformed scene that has the one or more objects added to the initial scene.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing sensor data, e.g., laser sensor data, using neural networks. One of the methods includes obtaining a temporal sequence of multiple three-dimensional point clouds generated from sensor readings of an environment collected by one or more sensors within a given time period, each three-dimensional point cloud comprising a respective plurality of points in a first coordinate system; processing, using a feature extraction neural network, an input that comprises data derived from the temporal sequence of multiple three-dimensional point clouds to generate a feature embedding; receiving a query that specifies one time point within the given time period; and generating, from the feature embedding and conditioned on the query, one or more outputs that characterize one or more objects in the environment at the time point specified in the received query.

Abstract: The present invention discloses a flame simulating device, comprising a mist generating chamber, an atomizing head, an air orifice and a nozzle. The inside of the mist generating chamber is provided with a liquid and the atomizing head, the atomizing head being capable of atomizing the liquid inside the mist generating chamber, the two sides of the nozzle being set as Coanda curved surfaces, the cross section of the air orifice being in a constricted shape and providing an air flow blown upward such that under the Venturi effect, the air flow blown upward will guide and attract the mist from inside the mist generating chamber to vent out and flow into a nozzle inlet; the upper surface of the mist generating chamber is provided with a breathing port, and the breathing port directly faces the atomizing head. Due to the Coanda curved surface on the side of the nozzle, the mist flows along both sides of the nozzle under the Coanda effect and then vents out of the nozzle.