Scenario description language

Patent metadata

Field	Value
Publication number	US-11301601-B2
Application number	US-201916657232-A
Country	US
Kind code	B2
Filing date	Oct 18, 2019
Priority date	Oct 14, 2016
Publication date	Apr 12, 2022
Grant date	Apr 12, 2022

Abstract

A domain specific language, or Scenario Description Language (SDL), can be used for quickly enumerating scenarios in a simulation for testing and validating interaction of an object (e.g., an autonomous vehicle) within an environment. Scenarios in a simulation are defined using one or more primitives. Primitives are used to define objects to be instantiated (such as body size, position, orientation, velocities, etc.) and/or actions to be performed by the objects in the simulation (such as wait for a period of time, goal positions, follow a particular object, etc.). The SDL enables simple creation of multiple scenarios by combining primitives combinatorially and in some examples, limiting which scenarios are created to those that correspond to combinations that provide meaningful information. Additionally, the SDL allows for instantiation to be agnostic of map features so that a particular scenario can be instantiated automatically over all possible positions within a map.

First claim

What we claim is:

1. A system 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 program the one or more processors to perform operations comprising:
receiving, as a first input to an application, a set of values representing an object and at least one of: an object behavior, a first condition, or a first action to be included in a simulated scenario;
receiving a second input to the application indicating a type of road intersection;
defining, based at least in part on linear temporal logic, a sequence of multiple steps to be performed in sequential order between the set of values and at least one of: a second condition, a second action, a fault, or a noise during execution of the simulated scenario;
determining a semantic coordinate representing the set of values in a map, the semantic coordinate indicative of the type of road intersection;
generating, based at least in part on the set of values, the sequence defined based at least in part on the linear temporal logic, and the semantic coordinate, the simulated scenario for execution; and
determining, based at least in part on executing the simulated scenario, outcome data indicating a response by an autonomous controller to the simulated scenario.

2. The system of claim 1 , wherein the object is associated with at least one of a body comprising a defined dimension, a pose, or a mesh to render the object in the simulated scenario.

3. The system of claim 1 , wherein the outcome data is based at least in part on an evaluation of the linear temporal logic.

4. The system of claim 1 , wherein determining the outcome data indicating the response by the autonomous controller to the simulated scenario comprises determining an operational space of the autonomous controller given the simulated scenario.

5. The system of claim 1 , wherein the simulated scenario represents an interaction between the object and the type of road intersection.

6. The system of claim 1 , wherein the simulated scenario comprises a first scenario and the sequence of multiple steps comprises a first combination of values associated with the first scenario and a second combination of values associated with a second scenario, and the operations further comprising:
determining whether the first combination of values and the second combination of values are associated with same outcome data; and performing at least one of:
executing only one of the first scenario or the second scenario when the first combination of values and the second combination of values are associated with the same outcome data; or
executing the first scenario and the second scenario when the first combination of values and the second combination of values are not associated with the same outcome data.

7. The system of claim 1 , the operations further comprising determining to modify a behavior of the autonomous controller based at least in part on the outcome data wherein the object comprises a static object or a dynamic object.

8. The system of claim 1 , wherein the object comprises a static object or a dynamic object.

9. The system of claim 1 , wherein the object is associated with an inertial coordinate system, a map based coordinate system, or a track based coordinate system.

10. A method comprising:
receiving, as a first input to an application, a set of values representing an object and at least one of: an object behavior, a first condition, or a first action to be included in a simulated scenario;
receiving a second input to the application indicating a type of road intersection;
defining, based at least in part on linear temporal logic, a sequence of multiple steps to be performed in sequential order between the set of values and at least one of: a second condition, a second action, a fault, or a noise during execution of the simulated scenario;
determining a semantic coordinate representing the set of values in a map, the semantic coordinate indicative of the type of road intersection;
generating, based at least in part on the set of values, the sequence defined based at least in part on the linear temporal logic, and the semantic coordinate, the simulated scenario for execution; and
determining, based at least in part on executing the simulated scenario, outcome data indicating a response by an autonomous controller to the simulated scenario.

11. The method of claim 10 , further comprising determining to modify a behavior of the autonomous controller based at least in part on the outcome data.

12. The method of claim 10 , wherein the object is associated with at least one of a body comprising a defined dimension, a pose, or a mesh to render the object in the simulated scenario.

13. The method of claim 10 , wherein the outcome data is based at least in part on an evaluation of the linear temporal logic.

14. The method of claim 10 , wherein determining the outcome data indicating the response by the autonomous controller to the simulated scenario comprises determining an operational space of the autonomous controller given the simulated scenario.

15. The method of claim 10 , wherein the simulated scenario represents an interaction between the object and the type of road intersection.

16. The method of claim 10 , wherein the simulated scenario comprises a first scenario and the sequence of multiple steps comprises a first combination of values associated with the first scenario and a second combination of values associated with a second scenario, and further comprising:
determining whether the first combination of values and the second combination of values are associated with same outcome data; and performing at least one of:
executing only one of the first scenario or the second scenario when the first combination of values and the second combination of values are associated with the same outcome data; or
executing the first scenario and the second scenario when the first combination of values and the second combination of values are not associated with the same outcome data.

17. A non-transitory computer-readable medium storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:
receiving, as a first input to an application, a set of values representing an object and at least one of: an object behavior, a first condition, or a first action to be included in a simulated scenario;
receiving a second input to the application indicating a type of road intersection;
defining, based at least in part on linear temporal logic, a sequence of multiple steps to be performed in sequential order between the set of values and at least one of: a second condition, a second action, a fault, or a noise during execution of the simulated scenario;
determining a semantic coordinate representing the set of values in a map, the semantic coordinate indicative of the type of road intersection;
generating, based at least in part on the set of values, the sequence defined based at least in part on the linear temporal logic, and the semantic coordinate, the simulated scenario for execution; and
determining, based at least in part on executing the simulated scenario, outcome data indicating a response by an autonomous controller to the simulated scenario.

18. The non-transitory computer-readable medium of claim 17 , the operations further comprising determining to modify a behavior of the autonomous controller based at least in par

Assignees

• Zoox Inc

Inventors

• Cahoon Ryan Martin
• Linscott Gary
• Treuille Adrien

Classifications

• G06F30/15 Primary

  Vehicle, aircraft or watercraft design · CPC title

• G06F11/3684

  for test design, e.g. generating new test cases · CPC title

• G09B29/007

  using computer methods · CPC title

• G06F30/20 Primary

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title