Ford Global Technolgoies, LLC

Argo Ai Gmbh

Kevin Lee Wyffels

G Peter K Carr

Wulue Zhao

Fnu Ratnesh Kumar

Basel Alghanem

Arsenii Saranin

Randall Schur

Alexander Metz

Devices, systems, and methods are provided for classifying detected objects as static or dynamic. A device may determine first light detection and ranging (LIDAR) data associated with a convex hull of an object at a first time, and determine second LIDAR data associated with the convex hull at a second time after the first time. The device may generate, based on the first LIDAR data and the second LIDAR data, a vector including values of features associated with the first convex hull and the second convex hull. The device may determine, based on the vector, a probability that the object is static. The device may operate a machine based on the probability that the object is static.

Enhanced static object classification using LiDAR

Systems and methods for tracking an object. The method comprising: receiving, by a processor, a series of observations made over time for the object; selecting, by the processor, a plurality of sets of observations using the series of observations; causing, by the processor, the plurality of sets of observations to be used by at least one filter to generate a track for the object (wherein the at least one filter uses sensor data associated with each of a plurality of frames of sensor data only once during generation of the track); and causing, by the processor, operations of an autonomous robot to be controlled based on the track for the object.

Systems and methods for temporal decorrelation of object detections for probabilistic filtering

Disclosed herein are systems, methods, and computer program products for operating a robotic system. For example, the method includes: obtaining a first cuboid generated based on an image, a second cuboid generated based on a lidar dataset and/or a third cuboid generated by a heuristic algorithm using the lidar dataset; using a machine learning model to generate a heading for an object in proximity to the robotic system based on the first cuboid, second cuboid and/or third cuboid; generating a bounding box geometry and a bounding box location based on the second cuboid or third cuboid; and generating a fourth cuboid using the bounding box geometry, the bounding box location, and the heading generated using the machine learning model.

Systems and methods for estimating cuboid headings based on heading estimations generated using different cuboid defining techniques

A system obtains, from an autonomous vehicle, point cloud data, projects the point cloud data onto a two-dimensional plane, and determines an optimized center parameter value of an optimized circle and an optimized radius parameter value of the optimized circle that, collectively, maximizes a probability distribution of a center parameter and a radius parameter across the point cloud data. The system determines whether one or more of the data points of the point cloud data are located within the optimized circle. If there are, the system assigns a pedestrian class value to the point label of the data point. If there are data points of the point cloud data that are located outside of the optimized circle, they system assigns a non-pedestrian class value to the point label of the data point.

Autonomous vehicle system for performing object detections using a logistic cylinder pedestrian model

Systems/methods for operating an autonomous vehicle. The methods comprise: obtaining LiDAR data generated by a LiDAR system of the autonomous vehicle and image data generated by a camera of the autonomous vehicle; performing a first object detection algorithm to generate first object detection information using the LiDAR data, and a second object detection algorithm to generate second object detection information using both the LiDAR data and the image data; and processing the first and second object detection information to determine whether a given object was detected by both the first and second object detection algorithms. When a determination is made that the given object was detected by both the first and second object detection algorithms, the first object detection information is selectively modified based on contents of the second object detection information. The modified first object detection information is used to facilitate at least one autonomous driving operation.

Systems and methods for object detection with LiDAR decorrelation

Disclosed herein are system, method, and computer program product embodiments for state identification for road actors with uncertain measurements based on compliant priors. The perception system of an autonomous vehicle (AV) may detect an object with an uncertain kinematic state based on sensor information received from a sensing device associated with the AV. A first, second, and third distribution of velocity values may be generated based on the sensor information, map information, and a kinematic state for each additional object of a plurality of additional objects in proximity to the detected object with the uncertain kinematic state, respectively. A velocity value for the detected object with the uncertain kinematic state may be generated based on a comparison of the first, second, and third distributions of velocity values. The AV may perform a driving maneuver based on the velocity value for the detected object.

State identification for road actors with uncertain measurements based on compliant priors

Systems and methods for operating a robotic system. The methods comprise: inferring, by a computing device, a first heading distribution for the object from a 3D point cloud; obtaining, by the computing device, a second heading distribution from a vector map; obtaining, by the computing device, a posterior distribution of a heading using the first and second heading distributions; defining, by the computing device, a cuboid on a 3D graph using the posterior distribution; and using the cuboid to facilitate driving-related operations of a robotic system.

Systems and methods for estimating cuboids from LiDAR, map and image data

Systems and methods for object detection. The object detection may be used to control an autonomous vehicle. For example, the methods comprise: obtaining, by a computing device, a LiDAR dataset generated by a LiDAR system of the autonomous vehicle; and using, by the computing device, the LiDAR dataset and at least one image to detect an object that is in proximity to the autonomous vehicle. The object is detected by: matching points of the LiDAR dataset to pixels in the at least one image; and detecting the object in a point cloud defined by the LiDAR dataset based on the matching. The object detection may be used to facilitate at least one autonomous driving operation (e.g., autonomous driving operation comprises an object tracking operation, an object trajectory prediction operation, a vehicle trajectory determination operation, and/or a collision avoidance operation).

Systems and methods for camera-LiDAR fused object detection with LiDAR-to-image detection matching

This document discloses system, method, and computer program product embodiments for controlling a vehicle. For example, the method includes: receiving an observation probability distribution function associated with a target object that was detected by sensor(s) of an autonomous vehicle (AV); identifying a target attribute associated with the target object; detecting a target attribute value associated with the target attribute; and issuing vehicle control instruction(s) that cause AV to adjust driving operation(s) using a future behavior of the target object predicted based on an attribute probability distribution function that defines a probability that the target attribute is actually present for the target object based on probability distribution function(s), wherein the attribute probability distribution function comprises: a probability value associated with the target attribute being present for the target object; and a probability value associated with the target attribute not being present for the target object.

Systems and methods for determining an object type and an attribute for an observation based on fused sensor data

A system may receive point cloud data that includes one or more data points associated with an object that was detected by sensors of an autonomous vehicle. The system may identify a subset of the point cloud data having data points that are associated with a likelihood of a pedestrian entering a scene with the object, determine a current probability value using a logistic function that is associated with the subset of the point cloud data, determine, based at least in part on the current probability value, a probability value representing a likelihood of the pedestrian actually being present for the subset of the point cloud data, determine whether the probability value exceeds a false alarm threshold value, and in response to the probability value exceeding the false alarm threshold value, assign data points of the subset an attribute value indicative of the pedestrian being present.

Autonomous vehicle system for detecting pedestrian presence

Systems and methods for operating an autonomous vehicle. The methods comprising: obtaining, by a computing device, a LiDAR dataset; plotting, by a computing device, the LiDAR dataset on a 3D graph to define a 3D point cloud; using, by a computing device, the LiDAR dataset and contents of a vector map to define a cuboid on the 3D graph that encompasses points of the 3D point cloud that are associated with an object in proximity to the vehicle, where the vector map comprises lane information; and using the cuboid to facilitate driving-related operations of the autonomous vehicle.

Enhanced static object classification using lidar

A system receives an observation probability distribution function associated with a target object that was detected by sensors of an autonomous vehicle. The system identifies a target attribute of the target object, and detects a target attribute value associated with the target object. The system determines a first probability distribution function representing a probability of the autonomous vehicle detecting an object having an object label, determines a second probability distribution function defining a probability of the autonomous vehicle detecting the target attribute, determines a third probability distribution function defining a probability of the target attribute being present for the target object based on the target attribute value, and determines an attribute probability distribution function defining a probability that the target attribute is actually present for the target object. The system executes vehicle control instructions that cause the autonomous vehicle to adjust driving operations based on the attribute probability distribution function.

A method of estimating a kinetic state of a rigid body is disclosed. A LiDAR sensor receives multiple point clouds. A processor determined a rigid body transform for a pair of the received point clouds and obtains a sample space of previous rigid body transforms. The processor then identifies a proposal distribution that represents the probability that any rigid body transform in the sample space best aligns a subset of points of a first point cloud of the pair to a subset of points in a second point cloud of the pair. The processor then uses importance sampling to identify a probability distribution for the rigid body transform that best aligns the subsets of points, It then uses the identified probability distribution and a history of probability distributions to estimate a kinetic state of the rigid body.

Determining the kinetic state of a body using LiDAR point cloud registration with importance sampling

A computing device in a vehicle can determine one or more objects based on 3D data points by determining a joint Bayesian probability of each of the one or more objects, conditioned on previously determined objects, and pilot the vehicle based on the determined one or more objects, wherein the objects have parameters including locations, sizes, poses, speeds, directions and predicted paths.

Growing community of inventors

Livonia, MI, United States of America

Kevin Lee Wyffels