Methods and systems for prioritizing computing methods for autonomous vehicles
AssigneeToyota Research Institute, Inc.
InventorsStephen G. McGill, Nicholas Charles Fishwick
Life of this patent
Estimating the term…
Abstract
A method includes receiving sensor data associated with one or more inputs associated with a road portion, determining a level of risk associated with each of the one or more inputs, determining an estimated amount of computing resources that each of a plurality of candidate computing methods will consume, and selecting one or more computing methods from the plurality of candidate computing methods to associate with the one or more inputs based on the levels of risk associated with the one or more inputs and the estimated amount of computing resources that the candidate computing methods will consume.
Claims13
A method comprising:
- receiving, by a vehicle system of an autonomous vehicle, first sensor data associated with a first area of a road;
- receiving, by the vehicle system of the autonomous vehicle, second sensor data associated with a second area of the road;
- determining a first level of risk associated with the first area of the road based on the first sensor data;
- determining a second level of risk associated with the second area of the road based on the second sensor data;
- selecting a first computing method to predict road agent behavior in one of the first area of the road and the second area of the road having a higher risk level, and selecting a second computing method to predict road agent behavior in the other of the first area of the road and the second area of the road having a lower risk level, the first computing method having a higher prediction accuracy than the second computing method;
- executing the first computing method and the second computing method to predict road agent behavior in the first area of the road and the second area of the road;
- and
- adjusting driving behavior of the autonomous vehicle based on a first output of the first computing method and a second output of the second computing method.
A vehicle system for an autonomous vehicle comprising:
- one or more processors;
- one or more memory modules
- one or more vehicle sensors;
- and
- machine readable instructions stored in the one or more memory modules that, when executed by the one or more processors, cause the vehicle system to:
- receive, with the one or more vehicle sensors, first sensor data associated with a first area of with a road;
- receive, with the one or more vehicle sensors, second sensor data associated with a second area of the road;
- determine a first level of risk associated with the first area of the road based on the first sensor data;
- determine a second level of risk associated with the second area of the road based on the second sensor data;
- select a first computing method to predict road agent behavior in one of the first area of the road and the second area of the road having a higher risk level, and selecting a second computing method to predict road agent behavior in the other of the first area of the road and the second area of the road having a lower risk level, the first computing method having a higher prediction accuracy than the second computing method;
- execute the first computing method and the second computing method to predict road agent behavior in the first area of the road and the second area of the road;
- and
- adjust driving behavior of the autonomous vehicle based on a first output of the first computing method and a second output of the second computing method.
Dependencies are inferred from the claim text.