All Mover Priors

Patent metadata

Field	Value
Publication number	US-2020207369-A1
Application number	US-201916727654-A
Country	US
Kind code	A1
Filing date	Dec 26, 2019
Priority date	Dec 26, 2018
Publication date	Jul 2, 2020
Grant date	—

Abstract

Systems, devices, products, apparatuses, and/or methods for generating a driving path for an autonomous vehicle on a roadway by determining one or more prior probability distributions of one or more motion paths for one or more objects that have previously moved in a geographic location and/or for controlling travel of an autonomous vehicle on a roadway by predicting movement of a detected object according to one or more prior probability distributions of one or more motion paths for one or more objects that have previously moved in a geographic location.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
obtaining, with a computing system comprising one or more processors, sensor data associated with one or more objects that previously moved in a geographic location; determining, with the computing system, one or more prior probability distributions of one or more motion paths for the one or more objects in the geographic location based on the sensor data; and generating, with the computing system, a driving path including one or more trajectories for an autonomous vehicle on a roadway based on the one or more prior probability distributions.

2 . The computer-implemented method of claim 1 , wherein determining the one or more prior probability distributions further comprises:
detecting a plurality of objects in the geographic location based on the sensor data; and identifying the one or more objects that previously moved in the geographic location from the plurality of objects based on the sensor data.

3 . The computer-implemented method of claim 1 , wherein determining the one or more prior probability distributions further comprises:
classifying each object of the one or more objects within one or more predetermined object classes of a plurality of predetermined object classes based on the sensor data, wherein the one or more prior probability distributions are determined based on the one or more predetermined object classes of the plurality of predetermined object classes in which the one or more objects are classified.

4 . The computer-implemented method of claim 1 , wherein the one or more prior probability distributions are determined based on at least one prior probability associated with at least one condition parameter of the following plurality of condition parameters: one or more velocities associated with the one or more objects, one or more acceleration and/or deceleration rates associated with the one or more objects, one or more orientations associated with the one or more objects, a time of day associated with the sensor data, a date associated with the sensor data, a geographic region of a plurality of geographic regions including the geographic location, or any combination thereof.

5 . The computer-implemented method of claim 1 , wherein the one or more prior probability distributions are associated with one or more probability values that correspond to one or more elements of a plurality of elements in a map of the geographic location, and wherein the one or more probability values include one or more probabilities of the one or more objects at one or more positions in the geographic location associated with the one or more elements in the map moving over the one or more motion paths.

6 . The computer-implemented method of claim 5 , wherein the one or more probability values further include at least one probability associated with at least one of the following: one or more predetermined object classes of a plurality of predetermined object classes associated with the one or more objects, one or more velocities associated with the one or more objects, one or more acceleration and/or deceleration rates associated with the one or more objects, one or more orientations associated with the one or more objects, a time of day associated with the one or more motion paths, a date associated with the one or more motion paths, a geographic region of a plurality of geographic regions including the geographic location, or any combination thereof.

7 . The computer-implemented method of claim 5 , further comprising:
obtaining, with the computing system, map data associated with the map of the geographic location; and generating, with the computing system, the driving path including the one or more trajectories for the autonomous vehicle on the roadway in the map based on the map data and the one or more prior probability distributions.

8 . The computer-implemented method of claim 7 , further comprising:
obtaining, with the computing system, user input associated with at least one element of the plurality of elements of the map of the geographic location; and generating, with the computing system, the driving path including the one or more trajectories for the autonomous vehicle on the roadway in the map based on the map data, the one or more prior probability distributions, and the user input.

9 . The computer-implemented method of claim 8 , wherein the user input is associated with a first element of the plurality of elements of the map of the geographic location and a second element of the plurality of elements of the map of the geographic location different than the first element, and wherein the driving path is generated on the roadway in the map between the first element and the second element.

10 . A computing system comprising:
one or more processors programmed and/or configured to:
obtain sensor data associated with one or more objects that previously moved in a geographic location;
determine one or more prior probability distributions of one or more motion paths for the one or more objects in the geographic location based on the sensor data; and
generate a driving path including one or more trajectories for an autonomous vehicle on a roadway based on the one or more prior probability distributions.

11 . The computing system of claim 10 , wherein the one or more processors are further programmed and/or configured to determine the one or more prior probability distributions by:
detecting a plurality of objects that previously moved in the geographic location based on the sensor data; and identifying the one or more objects that previously moved in the geographic location from the plurality of objects based on the sensor data.

12 . The computing system of claim 10 , wherein the one or more processors are further programmed and/or configured to determine the one or more prior probability distributions by:
classifying each object of the one or more objects within one or more predetermined object classes of a plurality of predetermined object classes based on the sensor data, wherein the one or more prior probability distributions are determined based on the one or more predetermined object classes of the plurality of predetermined object classes in which the one or more objects are classified.

13 . The computing system of claim 10 , wherein the one or more prior probability distributions are determined based on at least one prior probability associated with at least one condition parameter of the following plurality of condition parameters: one or more velocities associated with the one or more objects, one or more acceleration and/or deceleration rates associated with the one or more objects, one or more orientations associated with the one or more objects, a time of day associated with the sensor data, a date associated with the sensor data, a geographic region of a plurality of geographic regions including the geographic location, or any combination thereof.

14 . An autonomous vehicle comprising:
one or more sensors for detecting objects in an environment surrounding the autonomous vehicle; a vehicle computing system comprising one or more processors, wherein the vehicle computing system is programmed and/or configured to: obtain feature data associated with a current geographic location surrounding the autonomous vehicle, the feature data including characteristic features of the current geographic location; determine one or more predicted probability distributions of one or more predicted motion paths for one or more objects in the current geographic location based on (i) the feature data associated with the current

Assignees

• Uatc Llc

Inventors

• Mehta Hersh
• Werner Eric Blaine
• Biglan Albert John
• Haynes Galen Clark

Classifications

• B60W60/00274

  considering possible movement changes · CPC title

• G06F18/2321

  using statistics or function optimisation, e.g. modelling of probability density functions · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• B60W60/0011 Primary

  involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles · CPC title

• B60W60/0016

  of the vehicle or its occupants · CPC title