Object uncertainty models to assist with drivable area determinations

Patent metadata

Field	Value
Publication number	US-12189387-B2
Application number	US-202017247047-A
Country	US
Kind code	B2
Filing date	Nov 25, 2020
Priority date	Nov 25, 2020
Publication date	Jan 7, 2025
Grant date	Jan 7, 2025

Abstract

Techniques for representing sensor data and predicted behavior of various objects in an environment are described herein. For example, an autonomous vehicle can represent prediction probabilities as an uncertainty model that may be used to detect potential collisions, define a safe operational zone or drivable area, and to make operational decisions in a computationally efficient manner. The uncertainty model may represent a probability that regions within the environment are occupied using a heat map type approach in which various intensities of the heat map represent a likelihood of a corresponding physical region being occupied at a given point in time.

First claim

What is claimed is:

1. One or more non-transitory computer readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:
generating a discretized probability distribution representative of a physical environment at a future time, the discretized probability distribution comprising a plurality of cells representative of an area in the physical environment, a first cell of the plurality of cells representing a first prediction probability that an object in the physical environment is at a first location at the future time and a second cell of the plurality of cells representing a second prediction probability that the object in the physical environment is at a second location at the future time;
receiving a reference trajectory associated with an autonomous vehicle; and
determining, based at least in part on the discretized probability distribution, a drivable area comprising a bounded area in the physical environment through which the reference trajectory passes and having an associated width and length,
wherein determining the drivable area comprises performing a ray trace to determine a nearest occupied region in the physical environment.

2. The one or more non-transitory computer readable media of claim 1 , wherein the operations further comprise:
determining a position of the autonomous vehicle along the reference trajectory at a desired point in time; and
wherein determining the drivable area is based further on the position.

3. The one or more non-transitory computer readable media of claim 2 , wherein the operations further comprise determining that the first cell of the discretized probability distribution is perpendicular to the position at the desired point in time and has a probability of occupancy that meets or exceeds a threshold.

4. The one or more non-transitory computer readable media of claim 2 , wherein the operations further comprise detecting the first cell of the discretized probability distribution and the second cell of the discretized probability distribution, the first cell and the second cell perpendicular to the position at the desired point in time and an accumulation of a first probability of occupancy associated with the first cell and a second probability of occupancy associated with the second cell that meets or exceeds a threshold.

5. The one or more non-transitory computer readable media of claim 2 , wherein the operations further comprise detecting the first cell of the discretized probability distribution and the second cell of the discretized probability distribution, the first cell perpendicular to the position in a first direction and a first probability of occupancy associated with the first cell meets or exceeds a threshold and the second cell perpendicular to the position in a second direction and a second probability of occupancy associated with the second cell meets or exceeds the threshold, the second direction opposite the first direction.

6. The one or more non-transitory computer readable media of claim 1 , further comprising causing the autonomous vehicle to perform an action based at least in part on the drivable area.

7. A method comprising:
receiving a discretized probability distribution representative of a physical environment at a future time, the discretized probability distribution comprising a plurality of cells representative of an area in the physical environment, a first cell of the plurality of cells having a first prediction probability associated with an object in the physical environment occupying a first location at the future time and a second cell having a second prediction probability associated with the object in the physical environment occupying a second location at the future time;
receiving a reference trajectory associated with an autonomous vehicle;
determining a position of the autonomous vehicle along the reference trajectory at a desired point in time; and
determining, based at least in part on at least one of the first prediction probability, the second prediction probability, and the position, a drivable area comprising a boundary and associated with the reference trajectory,
wherein determining the drivable area comprises performing a ray trace to determine a nearest occupied region in the physical environment.

8. The method of claim 7 , wherein the first cell is adjacent to the position at the desired point in time.

9. The method of claim 8 , wherein the first cell is perpendicular to the position at the desired point in time.

10. The method of claim 8 , wherein the first prediction probability represents a probability of occupancy that meets or exceeds a threshold.

11. The method of claim 8 , wherein an accumulation of the first prediction probability and the second prediction probability meets or exceeds a threshold.

12. The method of claim 8 , further comprising:
determining the first prediction probability of the first cell that meets or exceeds a first threshold;
determining the second prediction probability of a second cell that meets or exceeds a second threshold;
generating a function based at least in part on the first prediction probability of the first cell and the second prediction probability of the second cell; and
wherein the drivable area is determined based at least in part on the function.

13. The method of claim 8 , further comprising:
determining that the second cell is perpendicular to the reference trajectory at the position, the second cell on a side of the autonomous vehicle opposite the first cell; and
wherein the drivable area is based at least in part on a location of the second cell.

14. The method of claim 7 , wherein:
the discretized probability distribution further comprises a plurality of probability distributions including a first probability distribution, a second probability distribution, and a third probability distribution;
the first probability distribution corresponds to a first time one interval prior to a second time corresponding to the second probability distribution; and
the second time is one interval prior to a third time corresponding to the third probability distribution.

15. The method of claim 7 , further comprising expanding the discretized probability distribution based at least in part on a characteristic of the autonomous vehicle or a characteristic of the object.

16. The method of claim 7 , further comprising causing the autonomous vehicle to perform an action based at least in part on the drivable area.

17. An autonomous vehicle comprising:
one or more processors; and
one or more non-transitory computer readable media storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the autonomous vehicle to perform operations comprising:
generating a discretized probability distribution comprising a plurality of cells representative of a physical environment at a future time, a first cell of the plurality of cells having a first probability of occupancy and a second cell of the plurality of cells having a second probability of occupancy;
receiving a reference trajectory associated with the autonomous vehicle; and
determining a drivable area associated with the reference trajectory and the future time, wherein the drivable area comprises a boundary and is based at least in part on the first probability of occupancy and the second probability of occupancy, and
further wherein determining the drivable area comprises performing a ray trace to determine a near

Assignees

• Zoox Inc

Inventors

• Fonseca Rasmus
• Kobilarov Marin
• Mcclelland Mark Jonathon
• Riley Jack

Classifications

• G06N3/08

  Learning methods · CPC title

• G05D1/617

  Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards (arrangements for controlling the position or course of two or more vehicles for avoiding collisions therebetween G05D1/693; arrangements for reacting to or preventing system or operator failure G05D1/80) · CPC title

• G05D1/81

  Handing over between on-board automatic and on-board manual control · CPC title

• B60W60/0027

  using trajectory prediction for other traffic participants · CPC title

• G05D1/0221

  involving a learning process · CPC title