Motional Ad LLC

Maurilio Di Cicco

Junqing Wei

Eric Wolff

Hsun-Hsien Chang

Philipp Robbel

Yifan Yang

Guchan Ozbilgin

David Butterworth

Andrew J Eick

Bishwamoy Sinha Roy

Scott D Pendleton

Jonathan L Wieskamp

Alok Sharma

Matthias Sapuan

Noam Weinstein

Akshay Bhagat

Mauro Aguiar

Karan Rajendra Shetti

Grigoriy Dubrovskiy

Theodore Alden

Jun Shern Chan

Andreas Jianhao Aumiller

Paul Aurel Diederichs

Scott D Pendelton

Bing Han

Meshari Alhemaidi

Nicholas Merritt

Sai Sonti

Manuel Weiss

Francisco Alejandro Suarez Ruiz

Sachit Kaul

Ryan Trumpore

Priyanka Ashok

Katherine Colwell

Zi Yi Chong

Among other things, we describe systems and method for validating sensor calibration. For validating calibration of a system of sensors having several types of sensors, an object may be configured to have a substantially reflective portion such that the sensors can isolate the substantially reflective portion, and their sensor data can be compared to determine, if the detected locations of the substantially reflective portion by each sensor are aligned. For calibrating a system of sensors, an object having known calibration features can be used and detected by each sensor, and the detected data can be compared to known calibration data associated with the object to determine if each sensor is correctly calibrated.

Systems and methods for validating sensor calibration

An automatic calibration and validation pipeline is disclosed to estimate and evaluate the accuracy of extrinsic parameters of a camera-to-LiDAR coordinate transformation. In an embodiment, an automated and unsupervised calibration procedure is employed where the computed rotational and translational parameters ('extrinsic parameters') of the camera-to-LiDAR coordinate transformation are automatically estimated and validated, and upper bounds on the accuracy of the extrinsic parameters are set. The calibration procedure combines three-dimensional (3D) plane, vector and point correspondences to determine the extrinsic parameters, and the resulting coordinate transformation is validated by analyzing the projection of a filtered point cloud including a validation target in the image space. A single camera image and LiDAR scan (a “single shot”) are used to calibrate and validate the extrinsic parameters. In addition to only requiring a single shot, the complete procedure solely relies on one or more planar calibration targets and simple geometrical validation targets.

Camera-to-LiDAR calibration and validation

Among other things, we describe techniques for operation of a vehicle based on measured load characteristics and/or passenger comfort. One or more sensors of the vehicle can measure passenger data and/or load data of the vehicle. The passenger data and/or load data of the vehicle can be used by the vehicle to determine how to navigate within the surrounding environment.

Systems and methods for controlling actuators based on load characteristics and passenger comfort

Techniques for determination of an optimal spatiotemporal sensor configuration for navigation of a vehicle include generating a model of a virtual vehicle operating in an environment. The model of the virtual vehicle includes a virtual sensor having a virtual viewing range. The virtual viewing range of the virtual sensor is segregated into frustums. The virtual viewing range of the virtual sensor corresponds to a viewing range of a sensor of a vehicle operating in the environment. A geometric viewport is generated including pixels. The geometric viewport has a height corresponding to a number of rays emitted from the virtual sensor. The geometric viewport is segregated into sections. Each section corresponds to a frustum. A virtual point cloud of the virtual sensor is rendered. The virtual point cloud includes coordinate positions representing a portion of the environment located within the virtual viewing range of the virtual sensor.

Determination of an optimal spatiotemporal sensor configuration for navigation of a vehicle using simulation of virtual sensors

Among other things, a method includes receiving first LiDAR point cloud information from a first LiDAR device and second LiDAR point cloud information from a second LiDAR device, generating third point cloud information according to merging the first and second LiDAR point cloud information, and operating the vehicle based upon the third LiDAR point cloud information.

Merging data from multiple LiDAR devices

Growing community of inventors

Singapore, Singapore

Maurilio Di Cicco