Various aspects of the subject technology relate to a mobile support platform for vehicle sensor calibration. The mobile support platform includes a chassis, lift posts on the chassis configured to interface with one or more lift points on a vehicle and raise the vehicle, and a set of wheels mounted to the chassis configured to carry the vehicle through a calibration sequence.

An example sensor bracket assembly can include one or more cold plates forming a core bracket structure, wherein the core bracket structure and the one or more cold plates provide structural support for the sensor bracket assembly; a housing enclosing the core bracket structure; one or more sensor mounts for mounting one or more sensors on the sensor bracket assembly; and one or more attachment portions for attaching the sensor bracket assembly to a body of a vehicle.

The present invention provides for a genetically modified host cell capable of producing isopentenol and/or 3-methyl-3-butenol, comprising (a) an increased expression of phosphomevalonate decarboxylase (PMD) (b) an increased expression of a phosphatase capable of converting isopentenol into 3-methyl-3-butenol, (c) optionally the genetically modified host cell does not express, or has a decreased expression of one or more of NudB, phosphomevalonate kinase (PMK), and/or PMD, and (d) optionally one or more further enzymes capable of converting isopentenol and/or 3-methyl-3-butenol into a third compound, such as isoprene.

The present disclosure provides a circuitry for radar detection data disambiguation for a mobile platform. The circuitry is configured to obtain radar detection data from a radar sensor mounted on the mobile platform, wherein the radar detection data indicate, for each of a plurality of targets, a radial velocity and an angle of arrival; estimate, based on the radar detection data, an ego-motion of the mobile platform; and determine an unambiguous radial velocity value of a target of the plurality of targets based on the ego-motion and the radar detection data.

Sensor module for mounting on a motor vehicle panel component having a sensor housing, at least one environment sensor, at least part of which is disposed in the sensor housing, and which is configured to send and/or receive electromagnetic signals to thus detect a vehicle environment, and a kinematic system having a drive configured to move the sensor housing from a retracted position into at least one deployed position. The kinematic system is configured to move the sensor housing into a first deployed position, which activates the at least one environment sensor to detect the vehicle environment in a portion of its field of view, and to move the sensor housing into a second deployed position, which activates the at least one environment sensor to detect the vehicle environment in its entire field of view.

To perform high-speed recognition processing of an image signal acquired by imaging.

A recognition processing system of the present disclosure includes: a first sensor device that acquires an image signal by imaging; a second sensor device that performs an object detection process, a selection unit that selects one of a plurality of recognition processes based on information on the object detected by the detection process; and a recognition processing unit that executes the recognition process selected by the selection unit based on the image signal.

A computer implemented method for determining a position, and/or an acceleration, and/or an angular rate and/or an orientation of a vehicle includes the following steps carried out by computer hardware components: determining first measurement data using a first sensor; determining a preliminary position and/or a preliminary orientation based on the first measurement data; determining second measurement data using a second sensor, wherein the second sensor includes a radar sensor and/or a LIDAR sensor and/or a camera; determining a preliminary acceleration and/or a preliminary angular rate based on the second measurement data; and determining a final position, and/or a final acceleration, and/or a final angular rate and/or a final orientation based on the preliminary acceleration and/or the preliminary angular rate, and the preliminary position and/or the preliminary orientation.

A system and method of calibrating an ADAS sensor of a vehicle by aligning a target with the sensor, where the vehicle is initially nominally positioned in front of a target adjustment stand that includes a stationary base frame and a movable target mount configured to support a target, with the target adjustment stand including one or more actuators for adjusting the position of the target mount. A computer system is used to determine an orientation of the vehicle relative to the target adjustment stand, with the position of the target mount being adjusted based on the determined orientation of the vehicle relative to the target adjustment stand. Upon properly orienting the target mount, and the target supported thereon, a calibration routine is performed whereby the sensor is calibrated using the target.

This document describes techniques, apparatuses, and systems for sensor fusion for object-avoidance detection, including stationary-object height estimation. A sensor fusion system may include a two-stage pipeline. In the first stage, time-series radar data passes through a detection model to produce radar range detections. In the second stage, based on the radar range detections and camera detections, an estimation model detects an over-drivable condition associated with stationary objects in a travel path of a vehicle. By projecting radar range detections onto pixels of an image, a histogram tracker can be used to discern pixel-based dimensions of stationary objects and track them across frames. With depth information, a highly accurate pixel-based width and height estimation can be made, which after applying over-drivability thresholds to these estimations, a vehicle can quickly and safely make over-drivability decisions about objects in a road.

Systems and methods for assigning a lane to an object in an environment of an autonomous vehicle are disclosed. The methods include assigning an instantaneous probability to each of a plurality of lanes in the environment based on a current state of the object, generating a transition matrix for each of the plurality of lanes, and identifying the lane in which the object is moving at the current time t based on the instantaneous probability and the transition matrix. The instantaneous probability is a measure of likelihood that the object is in that lane at a current time. The transition matrix encodes one or more probabilities that the object transitioned either into that lane or out of that lane at the current time.