Autonomous vehicle safe stop

Patent metadata

Field	Value
Publication number	US-10962973-B2
Application number	US-201815995285-A
Country	US
Kind code	B2
Filing date	Jun 1, 2018
Priority date	Jan 30, 2018
Publication date	Mar 30, 2021
Grant date	Mar 30, 2021

Abstract

Systems, methods, tangible non-transitory computer-readable media, and devices for operating an autonomous vehicle are provided. For example, the disclosed technology can include receiving state data that includes information associated with states of an autonomous vehicle and an environment external to the autonomous vehicle. Responsive to the state data satisfying vehicle stoppage criteria, vehicle stoppage conditions can be determined to have occurred. A severity level of the vehicle stoppage conditions can be selected from a plurality of available severity levels respectively associated with a plurality of different sets of constraints. A motion plan can be generated based on the state data. The motion plan can include information associated with locations for the autonomous vehicle to traverse at time intervals corresponding to the locations. Further, the locations can include a current location of the autonomous vehicle and a destination location at which the autonomous vehicle stops traveling.

First claim

What is claimed is:

1. A computer-implemented method of autonomous vehicle operation, the computer-implemented method comprising:
receiving, by a computing system comprising one or more computing devices, state data comprising information associated with one or more states of an autonomous vehicle or one or more states of an environment external to the autonomous vehicle;
responsive to the state data satisfying one or more vehicle stoppage criteria, determining, by the computing system, that one or more vehicle stoppage conditions have occurred in the autonomous vehicle or the environment external to the autonomous vehicle;
selecting, by the computing system, based at least in part on the state data and a machine-learned model, a severity level of the one or more vehicle stoppage conditions from a plurality of available severity levels, wherein each available severity level of the plurality of available severity levels is associated with a different set of respective constraints, wherein the machine-learned model is configured to select the severity level based at least in part on the one or more vehicle stoppage conditions, the severity level indicating an immediacy with which the autonomous vehicle is to stop traveling; and
generating, by the computing system, based at least in part on the state data, a motion plan that complies with the set of respective constraints associated with the severity level, the motion plan comprising a plurality of paths the autonomous vehicle is capable of traversing, the motion plan comprising information associated with one or more locations for the autonomous vehicle to traverse over one or more time intervals corresponding to the one or more locations, wherein the one or more locations comprise a current location of the autonomous vehicle and a destination location at which the autonomous vehicle will stop traveling,
responsive to all of the plurality of paths being obstructed, determining, by the computing system, based at least in part on the state data, a hard stop time duration for the autonomous vehicle to stop without changing a trajectory of the autonomous vehicle.

2. The computer-implemented method of claim 1 , wherein selecting the severity level of the one or more vehicle stoppage conditions from the plurality of available severity levels comprises:
determining, by the computing system, based at least in part on the state data, one or more motion characteristics of the autonomous vehicle, the one or more motion characteristics comprising a velocity of the autonomous vehicle, an acceleration of the autonomous vehicle, or the trajectory of the autonomous vehicle.

3. The computer-implemented method of claim 2 , wherein the severity level of the one or more vehicle stoppage conditions is inversely proportional to one or more motion planning characteristics comprising the one or more motion characteristics, a distance between the current location of the vehicle and the destination location, an amount of change in the velocity of the autonomous vehicle over the one or more time intervals, an amount of change in the acceleration of the autonomous vehicle over the one or more time intervals, or an amount of change in the trajectory of the autonomous vehicle over the one or more time intervals.

4. The computer-implemented method of claim 1 , wherein the severity level corresponds at least in part to an aggregate duration of the one or more time intervals of the motion plan.

5. The computer-implemented method of claim 4 , wherein generating the motion plan that complies with the set of constraints associated with the severity level comprises:
determining, by the computing system, based at least in part on the state data for at least one of the plurality of paths, whether the autonomous vehicle is capable of traversing from the current location of the autonomous vehicle within the aggregate duration of the one or more time intervals, the traversal comprising stopping at a terminal location of each of the plurality of paths respectively.

6. The computer-implemented method of claim 5 , wherein generating the motion plan that complies with the set of constraints associated with the severity level comprises:
determining, by the computing system, a highest ranked path of the plurality of paths based at least in part on one or more path criteria associated with one or more adverse conditions for the autonomous vehicle to avoid, the one or more adverse conditions comprising a road with a direction of travel opposite to a direction of travel of the autonomous vehicle, an intersection, a railroad crossing, a public transportation pick-up area, a blind curve, a blind corner, an on-ramp for a highway, or an off-ramp for a highway.

7. The computer-implemented method of claim 5 , wherein generating the motion plan that complies with the set of constraints associated with the severity level comprises:
determining, by the computing system, a minimum deviation path of the plurality of paths, wherein the minimum deviation path comprises a least amount of change to a velocity, an acceleration, or the trajectory of the autonomous vehicle.

8. The computer-implemented method of claim 5 , wherein generating the motion plan that complies with the set of constraints associated with the severity level comprises:
determining, by the computing system, based at least in part on the state data, one or more path characteristics for each of the plurality of paths, the one or more path characteristics comprising a path distance, a path angle, a path grade, a path width, a path surface type, a path surface condition, a curb size, a path shoulder size, or a path shoulder type.

9. The computer-implemented method of claim 5 , wherein generating the motion plan that complies with the set of constraints associated with the severity level comprises:
responsive to all of the plurality of paths not being obstructed, determining, by the computing system, based at least in part on the state data, a path of the plurality of paths that comprises an area of predetermined size at which the vehicle can stop.

10. The computer-implemented method of claim 1 , wherein generating the motion plan that complies with the set of constraints comprises:
modifying, by the computing system, a total cost function to include one or more additional cost functions that respectively enforce the set of constraints associated with the selected severity level.

11. The computer-implemented method of claim 1 , wherein generating the motion plan that complies with the set of constraints comprises:
constraining, by the computing system, a search space over which a motion planning system optimizes a total cost function.

12. The computer-implemented method of claim 1 , wherein generating the motion plan that complies with the set of constraints comprises:
modifying, by the computing system, the destination location to comply with the set of constraints; and
determining, by the computing system, a path of the autonomous vehicle to the destination location.

13. The computer-implemented method of claim 1 , wherein generating the motion plan that complies with the set of constraints comprises:
selecting, by the computing system, one of a plurality of motion plans comprising stopping the autonomous vehicle without changing a trajectory of the autonomous vehicle within a first threshold time period or a first threshold distance, changing the trajectory of the autonomous vehicle and stopping before a second time period or a second threshold distance, or changing the trajectory of the autonomous vehicle and stopping after the second time period or the second threshold distance.

Assignees

• Uatc Llc

Inventors

• Kazemi Moslem
• Bardapurkar Sameer

Classifications

• B60W60/0016

  of the vehicle or its occupants · CPC title

• B60W60/0027 Primary

  using trajectory prediction for other traffic participants · CPC title

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• B60W2050/007

  Switching between manual and automatic parameter input, and vice versa · CPC title

• G05D1/247

  using signals provided by artificial sources external to the vehicle, e.g. navigation beacons · CPC title