Abstract: A machine-learned architecture may use sensor data, data derived from the sensor data, and/or to determine a grid indicating objects that are occluded to one or more sensors of a vehicle and velocities associated therewith. This grid may be used to generate a candidate object detection associated with an occluded object and/or an object track associated with the occluded object. The candidate object detection and/or object track may be used to determine a predicted trajectory of the occluded object and, in cases where the occluded object is affirmed by a perception component of the vehicle to be a true positive, may be used to initialize a track associated with the newly disoccluded object.

Abstract: An intelligent surface burnishing tool system is provided. A surface burnishing tool can directly machine a surface of an irregular rotating workpiece and have a capability of sensing a cutting force and a vibration signal. In addition, according to the present disclosure, based on a multi-sensor integrated intelligent tool combined with a method for on-line monitoring of changes in surface roughness, the changes in workpiece surface roughness during machining are determined. Finally, based on on-line monitoring of the changes in surface roughness of the workpiece, functions such as real-time collection of a multidimensional force and vibration signals during surface burnishing and on-line monitoring of the changes in surface roughness are realized.

Abstract: Techniques for performing object detection in a vehicle environment using sensor data captured by one or more sensors of the vehicle are described herein. In some cases, an object in a vehicle environment can be detected based on at least one of (i) a first similarity matrix that represents a first similarity value for two sensor observations associated with the vehicle environment, or (ii) a second similarity matrix that represents a second similarity value for a sensor observation and a track associated with the vehicle environment.

Abstract: Techniques for performing object detection in a vehicle environment using sensor data captured by one or more sensors of the vehicle are described herein. In some cases, an object in a vehicle environment can be detected based on at least one of (i) a first similarity matrix that represents a first similarity value for two sensor observations associated with the vehicle environment, or (ii) a second similarity matrix that represents a second similarity value for a sensor observation and a track associated with the vehicle environment.

Abstract: A ground point cloud segmentation method and apparatus and an autonomous vehicle. The method includes dividing a region of interest into a plurality of grids, and putting point clouds in the region of interest into the corresponding grids; determining a plane equation corresponding to the point cloud in each grid; taking, as a central grid, a grid where a radar is located, and determining a ground equation of the central grid; marking the central grid as a ground grid, and according to the plane equation corresponding to the point cloud in each grid and the ground equation of the central grid, performing gradual outward diffusion from the central grid, and calculating a ground equation of each grid in the region of interest; and according to the ground equation of each grid, determining whether the point cloud in the grid is a ground point cloud.

Abstract: Disclosed is a method for predicting surface quality of a burnishing workpiece. The method includes the steps: using vibration sensors and signal acquisition instrument to acquire vibration signals generated on a surface of the burnishing workpiece during machining, evaluating the surface quality of the burnishing workpiece based on a coupling coordination degree model, processing signals by using an ensemble empirical mode decomposition method, identifying power spectral density, kurtosis and form factor as signal characteristics, identifying a support vector machine as a decision-making model, optimizing penalty parameters and kernel function parameters by using the Bayesian optimization method, and establishing the relationship between the signal characteristics and the surface quality.

Abstract: Disclosed is a method for predicting surface quality of a burnishing workpiece. The method includes the steps: using vibration sensors and signal acquisition instrument to acquire vibration signals generated on a surface of the burnishing workpiece during machining, evaluating the surface quality of the burnishing workpiece based on a coupling coordination degree model, processing signals by using an ensemble empirical mode decomposition method, identifying power spectral density, kurtosis and form factor as signal characteristics, identifying a support vector machine as a decision-making model, optimizing penalty parameters and kernel function parameters by using the Bayesian optimization method, and establishing the relationship between the signal characteristics and the surface quality.

Abstract: An alkali-free ultrafine glass fiber formula includes the following components, in mass percentage calculated based on 100 Kg: SiO2: 50% to 65%, Al2O3: 10% to 16.5%, CaO: 17% to 28%, MgO: 0.2% to 4.0%, Na2O and K2O: 0.1% to 0.8% in total, CeO2: 0.1% to 0.5%, Li2O: 0.1% to 0.7%, Fe2O3: 0.05% to 0.6%, TiO2: 0.1% to 1%, and impurities: the balance. In the preparation of alkali-free ultrafine glass fibers, no fluorine and boron-containing raw materials are used, and CeO2 and Li2O are introduced, which avoids the use of B2O3 and F that have a large impact on the environment, and reduces environmental pollution. A single fiber strength of prepared glass fibers is about 9% higher than that of the traditional E glass fibers, and the comprehensive performance of a prepared glass fiber product is significantly superior than that of the existing E glass fiber product.

Abstract: An alkali-free ultrafine glass fiber formula includes the following components, in mass percentage calculated based on 100 Kg: SiO2: 50% to 65%, Al2O3: 10% to 16.5%, CaO: 17% to 28%, MgO: 0.2% to 4.0%, Na2O and K2O: 0.1% to 0.8% in total, CeO2: 0.1% to 0.5%, Li2O: 0.1% to 0.7%, Fe2O3: 0.05% to 0.6%, TiO2: 0.1% to 1%, and impurities: the balance. In the preparation of alkali-free ultrafine glass fibers, no fluorine and boron-containing raw materials are used, and CeO2 and Li2O are introduced, which avoids the use of B2O3 and F that have a large impact on the environment, and reduces environmental pollution. A single fiber strength of prepared glass fibers is about 9% higher than that of the traditional E glass fibers, and the comprehensive performance of a prepared glass fiber product is significantly superior than that of the existing E glass fiber product.