Autonomous vehicle technology for facilitating operation according to motion primitives
View Patent ↗Various software techniques for managing operation of autonomous vehicles based on sensor data are disclosed herein. A computing system may generate, based on a set of signals descriptive of a current state of an environment in which the autonomous vehicle is operating, a normal path plan separate from a safe path plan, or a hybrid path plan including a normal path plan and a safe path plan. In generating the safe path plan, the computing system may generate and concatenate a set of motion primitives. When a fault condition occurs, the computing device may transition from executing the normal path plan to executing the safe path plan to safely stop the autonomous vehicle.
1. A computer-implemented method of determining operation of an autonomous vehicle, the method comprising:
processing, by one or more processors, a set of signals descriptive of a current state of an environment in which the autonomous vehicle is operating, wherein processing the set of signals includes assessing a set of risks associated with operation of the autonomous vehicle during a future time period;
determining, by the one or more processors based on the set of risks, a set of motion primitives to safely stop the autonomous vehicle during at least a portion of the future time period, the set of motion primitives comprising (i) a first motion primitive indicative of a first movement to be undertaken by the autonomous vehicle, and (ii) a second motion primitive indicative of a second movement to be undertaken by the autonomous vehicle after undertaking the first movement;
executing, by the one or more processors, the first motion primitive to cause the autonomous vehicle to undertake the first movement; and
subsequent to executing the first motion primitive, executing, by the one or more processors, the second motion primitive to cause the autonomous vehicle to undertake the second movement and safely stop the autonomous vehicle during at least the portion of the future time period.
2. The computer-implemented method of claim 1 , wherein the first motion primitive has a first time period and the second motion primitive has a second time period, and wherein the first time period is different than the second time period.
3. The computer-implemented method of claim 1 , wherein assessing the set of risks associated with operation of the autonomous vehicle during the future time period comprises:
detecting an additional vehicle in a vicinity of the autonomous vehicle; and
estimating a set of future movements of the additional vehicle during at least the portion of the future time period.
4. The computer-implemented method of claim 3 , wherein determining,
based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period comprises:
determining the set of motion primitives based at least in part on the set of future movements of the additional vehicle.
5. The computer-implemented method of claim 1 , wherein determining,
based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period comprises:
accessing a set of traffic laws associated with the environment in which the autonomous vehicle is operating; and
determining, based on the set of traffic laws and the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period.
6. The computer-implemented method of claim 1 , wherein processing the set of signals descriptive of the current state of the environment in which the autonomous vehicle is operating comprises:
accessing a set of most recently available signals descriptive of the environment; and
processing the set of most recently available signals.
7. The computer-implemented method of claim 1 , wherein determining, based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period comprises:
determining a lapse of time associated with the set of signals descriptive of the current state of the environment in which the autonomous vehicle is operating; and
determining, based on the lapse of time and the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period.
8. The computer-implemented method of claim 1 , wherein determining, based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period comprises:
determining, based at least in part on the set of risks, an endpoint location at which to safely stop the autonomous vehicle; and
determining, based at least in part on the set of risks, the set of motion primitives to move the autonomous vehicle from a current location to the endpoint location during at least the portion of the future time period.
9. A non-transitory computer-readable medium storing thereon instructions executable by one or more processors to implement a control architecture for controlling a vehicle, comprising:
instructions for receiving sensor data generated by one or more sensors of the vehicle, wherein the one or more sensors are configured to sense an environment in which the vehicle is operating;
instructions for generating, based on the sensor data, a set of signals descriptive of a current state of the environment;
instructions for assessing, based on the set of signals descriptive of the current state of the environment, a set of risks associated with operation of the vehicle during the future time period;
instructions for generating, based on the set of risks, a set of motion primitives to safely stop the vehicle during at least a portion of the future time period, the set of motion primitives comprising (i) a first motion primitive indicative of a first movement to be undertaken by the vehicle, and (ii) a second motion primitive indicative of a second movement to be undertaken by the vehicle after undertaking the first movement;
instructions for executing the first motion primitive to cause the vehicle to undertake the first movement; and
instructions for executing, subsequent to executing the first motion primitive, the second motion primitive to cause the autonomous vehicle to undertake the second movement and safely stop the autonomous vehicle during at least the portion of the future time period.
10. The non-transitory computer-readable medium of claim 9 , wherein the first motion primitive has a first time period and the second motion primitive has a second time period, and wherein the first time period is different than the second time period.
11. The non-transitory computer-readable medium of claim 9 , wherein the instructions for assessing, based on the set of signals descriptive of the current state of the environment, the set of risks associated with operation of the vehicle during the future time period comprise:
instructions for detecting, from the set of signals, an additional vehicle in a vicinity of the vehicle; and
instructions for estimating a set of future movements of the additional vehicle during at least the portion of the future time period.
12. The non-transitory computer-readable medium of claim 11 , wherein the instructions for generating, based on the set of risks, the set of motion primitives to safely stop the vehicle during at least the portion of the future time period comprise:
instructions for generating the set of motion primitives based at least in part on the set of future movements of the additional vehicle.
13. The non-transitory computer-readable medium of claim 9 , wherein the instructions for generating, based on the set of risks, the set of motion primitives to safely stop the vehicle during at least the portion of the future time period comprise:
instructions for accessing a set of traffic laws associated with the environment in which the vehicle is operating; and
instructions for generating, based on the set of traffic laws and the set of risks, the set of motion primitives to safely stop the vehicle during at least the portion of the future time period.
14. The non-transitory computer-readable medium of claim 9 , wherein the instructions for generating, based on the set of risks, the set of motion primitives to safely stop the vehicle during at least the portion of the future time period comprise:
instructions for determining a lapse of time associated with the set of signals descriptive of the current state of the environment in which the vehicle is operating; and
instructions for generating, based on the lapse of time and the set of risks, the set of motion primitives to safely stop the vehicle during at least the portion of the future time period.
15. The non-transitory computer-readable medium of claim 9 , wherein the instructions for generating, based on the set of risks, the set of motion primitives to safely stop the vehicle during at least the portion of the future time period comprise:
instructions for determining, based at least in part on the set of risks, an endpoint location at which to safely stop the vehicle; and
instructions for generating, based at least in part on the set of risks, the set of motion primitives to move the vehicle from a current location to the endpoint location during at least the portion of the future time period.
16. A system within an autonomous vehicle, the system comprising:
a set of sensors configured to generate a set of sensor data associated with operation of the autonomous vehicle; and
a computing system configured to:
generate, based on the set of sensor data, a set of signals descriptive of a current state of an environment in which the autonomous vehicle is operating,
based on processing the set of signals, assess a set of risks associated with operation of the autonomous vehicle during a future time period,
determine, based on the set of risks, a set of motion primitives to safely stop the autonomous vehicle during at least a portion of the future time period, the set of motion primitives comprising (i) a first motion primitive indicative of a first movement to be undertaken by the autonomous vehicle, and (ii) a second motion primitive indicative of a second movement to be undertaken by the autonomous vehicle after undertaking the first movement,
execute the first motion primitive to cause the autonomous vehicle to undertake the first movement, and
subsequent to executing the first motion primitive, execute the second motion primitive to cause the autonomous vehicle to undertake the second movement and safely stop the autonomous vehicle during at least the portion of the future time period.
17. The system of claim 16 , wherein the first motion primitive has a first time period and the second motion primitive has a second time period, and wherein the first time period is different than the second time period.
18. The system of claim 16 , wherein to assess the set of risks associated with operation of the autonomous vehicle during the future time period, the computing device is configured to:
detect, from the set of signals, an additional vehicle in a vicinity of the autonomous vehicle, and
estimate a set of future movements of the additional vehicle during at least the portion of the future time period.
19. The system of claim 18 , wherein to determine, based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period, the computing device is configured to:
determine the set of motion primitives based at least in part on the set of future movements of the additional vehicle.
20. The system of claim 16 , wherein to determine, based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period, the computing device is configured to:
access a set of traffic laws associated with the environment in which the autonomous vehicle is operating, and
determine, based on the set of traffic laws and the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period.
21. The system of claim 16 , wherein to determine, based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period, the computing device is configured to:
determine a lapse of time associated with the set of signals descriptive of the current state of the environment in which the autonomous vehicle is operating, and
determine, based on the lapse of time and the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period.
22. The system of claim 16 , wherein to determine, based on the set of risks, the set of motion primitives to safely stop the autonomous vehicle during at least the portion of the future time period, the computing device is configured to:
determine, based at least in part on the set of risks, an endpoint location at which to safely stop the autonomous vehicle, and
determine, based at least in part on the set of risks, the set of motion primitives to move the autonomous vehicle from a current location to the endpoint location during at least the portion of the future time period.