Abstract: A controller of a chemical mechanical polishing system is configured to cause a carrier head to sweep across a polishing pad in accord with a sweep profile. The controller is also configured to select values for a plurality of control parameters to minimize a difference between a target removal profile and an expected removal profile. The plurality of control parameters include a plurality of dwell time parameters. A relationship between the plurality of control parameters and a removal rate is stored in a data structure representing a first matrix which includes a plurality of columns including a column for each dwell time parameter and a row for each position on the substrate represented in the expected removal profile, and the controller is configured to, as part of selection of the values, calculate the expected removal profile by multiplying the first matrix by a second matrix representing control parameter values.

Abstract: In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: In various examples, a deep neural network (DNN) may be used to detect and classify animate objects and/or parts of an environment. The DNN may be trained using camera-to-LiDAR cross injection to generate reliable ground truth data for LiDAR range images. For example, annotations generated in the image domain may be propagated to the LiDAR domain to increase the accuracy of the ground truth data in the LiDAR domain—e.g., without requiring manual annotation in the LiDAR domain. Once trained, the DNN may output instance segmentation masks, class segmentation masks, and/or bounding shape proposals corresponding to two-dimensional (2D) LiDAR range images, and the outputs may be fused together to project the outputs into three-dimensional (3D) LiDAR point clouds. This 2D and/or 3D information output by the DNN may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In some implementations, an optical device includes a one-way mirror formed by a polarization selective mirror and an absorptive polarizer. The absorptive polarizer has a transmission axis aligned with the transmission axis of the reflective polarizer. The one-way mirror may be provided on the world side of a head-mounted display system. Advantageously, the one-way mirror may reflect light from the world, which provides privacy and may improve the cosmetics of the display. In some implementations, the one-way mirror may include one or more of a depolarizer and a pair of opposing waveplates to improve alignment tolerances and reduce reflections to a viewer. In some implementations, the one-way mirror may form a compact integrated structure with a dimmer for reducing light transmitted to the viewer from the world.

Abstract: A neural network may be used to determine corner points of a skewed polygon (e.g., as displacement values to anchor box corner points) that accurately delineate a region in an image that defines a parking space. Further, the neural network may output confidence values predicting likelihoods that corner points of an anchor box correspond to an entrance to the parking spot. The confidence values may be used to select a subset of the corner points of the anchor box and/or skewed polygon in order to define the entrance to the parking spot. A minimum aggregate distance between corner points of a skewed polygon predicted using the CNN(s) and ground truth corner points of a parking spot may be used simplify a determination as to whether an anchor box should be used as a positive sample for training.

Abstract: Systems and methods are disclosed that relate to freespace detection using machine learning models. First data that may include object labels may be obtained from a first sensor and freespace may be identified using the first data and the object labels. The first data may be annotated to include freespace labels that correspond to freespace within an operational environment. Freespace annotated data may be generated by combining the one or more freespace labels with second data obtained from a second sensor, with the freespace annotated data corresponding to a viewable area in the operational environment. The viewable area may be determined by tracing one or more rays from the second sensor within the field of view of the second sensor relative to the first data. The freespace annotated data may be input into a machine learning model to train the machine learning model to detect freespace using the second data.

Abstract: A vehicle radar inspection system and method are provided for inspecting a mounting state of a radar sensor mounted to a vehicle. The vehicle radar inspection system includes a centering portion that aligns a position of the vehicle by driving rollers, displacement sensors that are respectively disposed at front and rear sides of the centering portion, an array antenna that measures propagation intensity of a radar signal transmitted from the radar sensor, and a server that connects wireless communication with a wireless terminal of the vehicle, calculates a mounting position of the radar sensor, and detects a mounting error of the radar sensor with reference to a normal reference mounting specification.

Abstract: A production factory unmanned transfer system includes: a vehicle, which connects Vehicle to Everything (V2X) communication with an infrastructure facility in a vehicle production factory and transfers a worker to a set destination in an unmanned manner through autonomous driving; and a road side unit, which is fixed around a road in the production factory to relay the V2X communication and which generates positioning error correction information based on high-precision Real Time Kinematic-Global Navigation Satellite System (RTK-GNSS) based on a fixed absolute coordinate and transmits the generated positioning error correction information to the vehicle. The vehicle includes a vehicle terminal, which controls autonomous driving according to a lane of a precise map based on high-precise positioning information obtained by correcting an error of satellite-based vehicle location information with the positioning error correction information.

Abstract: A V2X network handover system supporting autonomous driving of an unmanned transport vehicle may include, a plurality of RSUs disposed in a production plant, each being configured to broadcast a WSA message in a service area, and an OBU installed in the unmanned transport vehicle to transmit and receive V2X communication data through an integrated antenna and configured to obtain vehicle position information based on GNSS, where the OBU may be configured to execute a handover determination algorithm from the WSA message received in a service overlap area of a plurality of RSUs to select a handover target RSU based on an integrated condition combined with two or more among a distance-based condition based on a distance between each RSU and the unmanned transport vehicle, a weighted moving average condition of received signal strength indication (RSSI), and a data normal reception count condition.

Abstract: A vehicle to everything (V2X) mesh network system supporting a mobility operation of a production factory includes a road side unit (RSU) which is disposed in plural in the production factory, and connects infra-to-infra (I2I) wireless communication with an infrastructure facility, and connects vehicle-to-infra (V2I) wireless communication with an on board unit (OBU) mounted on an autonomous driving vehicle to form a V2X mesh network; and a control server controlling operation states of the RSU and the vehicle through the V2X mesh network.

Abstract: A production factory unmanned transfer system includes: a vehicle, which connects Vehicle to Everything (V2X) communication with an infrastructure facility in a vehicle production factory and transfers a worker to a set destination in an unmanned manner through autonomous driving; and a road side unit, which is fixed around a road in the production factory to relay the V2X communication and which generates positioning error correction information based on high-precision Real Time Kinematic-Global Navigation Satellite System (RTK-GNSS) based on a fixed absolute coordinate and transmits the generated positioning error correction information to the vehicle. The vehicle includes a vehicle terminal, which controls autonomous driving according to a lane of a precise map based on high-precise positioning information obtained by correcting an error of satellite-based vehicle location information with the positioning error correction information.

Abstract: A vehicle radar inspection system and method are provided for inspecting a mounting state of a radar sensor mounted to a vehicle. The vehicle radar inspection system includes a centering portion that aligns a position of the vehicle by driving rollers, displacement sensors that are respectively disposed at front and rear sides of the centering portion, an array antenna that measures propagation intensity of a radar signal transmitted from the radar sensor, and a server that connects wireless communication with a wireless terminal of the vehicle, calculates a mounting position of the radar sensor, and detects a mounting error of the radar sensor with reference to a normal reference mounting specification.

Abstract: Provided herein, inter alia, are compositions and methods for treating bladder cancer, including CD4+T cells that can be cultured ex vivo to generate a population of cytotoxic CD4+T cells capable of killing bladder cancer tumor cells. Pharmaceutical compositions containing such a cytotoxic CD4+T cell population, as well as methods for treating an individual having or suspected of having bladder cancer are also provided.

Abstract: A vehicle radar inspection system and method are provided for inspecting a mounting state of a radar sensor mounted to a vehicle. The vehicle radar inspection system includes a centering portion that aligns a position of the vehicle by driving rollers, displacement sensors that are respectively disposed at front and rear sides of the centering portion, an array antenna that measures propagation intensity of a radar signal transmitted from the radar sensor, and a server that connects wireless communication with a wireless terminal of the vehicle, calculates a mounting position of the radar sensor, and detects a mounting error of the radar sensor with reference to a normal reference mounting specification.

Abstract: A system for aiming a radar sensor angle which adjusts an angle of the radar sensor mounted on a vehicle entering an inspection line includes: a radar sensor mounted inside a front bumper of the vehicle, a wireless terminal connected to the radar sensor through an in-vehicle communication line and connected to the outside through a repeater, a centering unit for aligning a position of the vehicle by a driving roller based on a reference inspection position of the radar sensor, an array antenna for measuring an intensity of a radar signal transmitted from the radar sensor and detecting a radar center value, and a server detecting an angular error value of the radar sensor by comparing the radar center value with a reference center value of a set mounting specification and transmitting an angular correction value to the radar sensor.

Abstract: A system for aiming a radar sensor angle which adjusts an angle of the radar sensor mounted on a vehicle entering an inspection line includes: a radar sensor mounted inside a front bumper of the vehicle, a wireless terminal connected to the radar sensor through an in-vehicle communication line and connected to the outside through a repeater, a centering unit for aligning a position of the vehicle by a driving roller based on a reference inspection position of the radar sensor, an array antenna for measuring anintensity of a radar signal transmitted from the radar sensor and detecting a radar center value, and a server detecting an angular error value of the radar sensor by comparing the radar center value with a reference center value of a set mounting specification and transmitting an angular correction value to the radar sensor.

Abstract: A vehicle radar inspection system and method are provided for inspecting a mounting state of a radar sensor mounted to a vehicle. The vehicle radar inspection system includes a centering portion that aligns a position of the vehicle by driving rollers, displacement sensors that are respectively disposed at front and rear sides of the centering portion, an array antenna that measures propagation intensity of a radar signal transmitted from the radar sensor, and a server that connects wireless communication with a wireless terminal of the vehicle, calculates a mounting position of the radar sensor, and detects a mounting error of the radar sensor with reference to a normal reference mounting specification.

Abstract: The present disclosure provides a system and method for vehicle inspection. The system for vehicle inspection installed on an inspection line to inspect an assembled vehicle may include: a wireless terminal connected to the vehicle and configured to externally transmit vehicle state information; an antenna arranged on the inspection line and configured to relay wireless communication of the wireless terminal; a camera arranged upwardly along the inspection line and configured to transmit image information of a photographed vehicle; and a server configured to set a coordinates system and a reference driving line on the inspection line, generate drive control information based on the image information and the vehicle state information such that the vehicle moves along the reference driving line, and transmit the drive control information to the wireless terminal.

Abstract: A roll and brake test system and a method of controlling the same are disclosed. The roll and brake test system can automatically test a steering device, an accelerator, a transmission, and a brake of a vehicle. The roll and brake test system includes: a roll and brake apparatus for accommodating a vehicle on a roll; a management apparatus for controlling the roll and brake apparatus and for generating test information for testing the vehicle; and a control apparatus for controlling the vehicle according to the test information from the management apparatus.