Autonomous vehicle operation feature evaluation
First Claim
1. A computer-implemented method for testing the effectiveness of one or more autonomous operation features for controlling vehicles by simulating operation of the one or more autonomous operation features in a virtual vehicle in a plurality of virtual test environments associated with a plurality of environmental conditions, comprising:
- receiving, at one or more processors, a set of computer-readable instructions for implementing the one or more autonomous operation features, wherein the set of computer-readable instructions comprises one or more software routines configured to receive one or more input signals from at least one sensor and generate one or more output signals for controlling a vehicle;
receiving, at one or more processors of a sensor input simulator, the plurality of virtual test environments;
for each virtual test environment of the plurality of virtual test environments, automatically testing the one or more autonomous operation features without input from a user by;
generating, by one or more processors of the sensor input simulator, a fully virtual vehicle simulation including the virtual vehicle within the virtual test environment;
executing, by the one or more processors, the one or more software routines to respond to test input signals for the virtual vehicle within the fully virtual vehicle simulation;
receiving, at the one or more processors from the sensor input simulator, a plurality of test input signals for the virtual test environment, wherein the test input signals simulate the one or more signals from at least one sensor corresponding to a test scenario associated with the virtual test environment;
generating, by the one or more software routines executing on the one or more processors, one or more test output signals for the virtual vehicle in response to the received test input signals for the virtual test environment;
predicting, by the one or more processors of the sensor input simulator, one or more responses of the virtual vehicle in the virtual test environment to the one or more test output signals;
determining, by one or more processors of a server, a measure of the effectiveness of the one or more autonomous operation features based at least in part upon the one or more predicted responses of the virtual vehicle to the one or more test output signals associated with the plurality of virtual test environments; and
adjusting, by the one or more processors of the server, a risk profile associated with a vehicle having the one or more autonomous operation features based upon the determined measure of effectiveness by updating the risk profile to include one or more risk levels associated with autonomous operation of the vehicle by the one or more autonomous operation features.
1 Assignment
0 Petitions
Accused Products
Abstract
Methods and systems for testing the operation of autonomous or semi-autonomous operation features in a virtual test environment are provided. Computer-executable instructions for implementing the features may be received and executed on a test device. Test input signals may be presented to software routines associated with the features, which may generate output signals including control commands. The output signals may be used to predict the response of a vehicle in the virtual test environment, which may include a simulation of vehicle responses to the output signals. Measures of the effectiveness of the features may be determined based upon the predicted responses of the vehicle, which may then be used to determine risk levels associated with the features.
857 Citations
20 Claims
-
1. A computer-implemented method for testing the effectiveness of one or more autonomous operation features for controlling vehicles by simulating operation of the one or more autonomous operation features in a virtual vehicle in a plurality of virtual test environments associated with a plurality of environmental conditions, comprising:
-
receiving, at one or more processors, a set of computer-readable instructions for implementing the one or more autonomous operation features, wherein the set of computer-readable instructions comprises one or more software routines configured to receive one or more input signals from at least one sensor and generate one or more output signals for controlling a vehicle; receiving, at one or more processors of a sensor input simulator, the plurality of virtual test environments; for each virtual test environment of the plurality of virtual test environments, automatically testing the one or more autonomous operation features without input from a user by; generating, by one or more processors of the sensor input simulator, a fully virtual vehicle simulation including the virtual vehicle within the virtual test environment; executing, by the one or more processors, the one or more software routines to respond to test input signals for the virtual vehicle within the fully virtual vehicle simulation; receiving, at the one or more processors from the sensor input simulator, a plurality of test input signals for the virtual test environment, wherein the test input signals simulate the one or more signals from at least one sensor corresponding to a test scenario associated with the virtual test environment; generating, by the one or more software routines executing on the one or more processors, one or more test output signals for the virtual vehicle in response to the received test input signals for the virtual test environment; predicting, by the one or more processors of the sensor input simulator, one or more responses of the virtual vehicle in the virtual test environment to the one or more test output signals; determining, by one or more processors of a server, a measure of the effectiveness of the one or more autonomous operation features based at least in part upon the one or more predicted responses of the virtual vehicle to the one or more test output signals associated with the plurality of virtual test environments; and adjusting, by the one or more processors of the server, a risk profile associated with a vehicle having the one or more autonomous operation features based upon the determined measure of effectiveness by updating the risk profile to include one or more risk levels associated with autonomous operation of the vehicle by the one or more autonomous operation features. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer system for testing the effectiveness of one or more autonomous operation features for controlling vehicles by simulating operation of the one or more autonomous operation features in a virtual vehicle in a plurality of virtual test environments associated with a plurality of environmental conditions, comprising:
-
one or more processors; a sensor input simulator configured to receive the plurality of virtual test environments and, for each virtual test environment;
(i) generate a fully virtual vehicle simulation including the virtual vehicle within the virtual test environment and (ii) predict responses of the virtual vehicle within the virtual test environment; anda non-transitory program memory coupled to the one or more processors and storing executable instructions that when executed by the one or more processors cause the computer system to; receive a set of computer-readable instructions for implementing the one or more autonomous operation features, wherein the set of computer-readable instructions comprises one or more software routines configured to receive one or more input signals from at least one sensor and generate one or more output signals for controlling a vehicle; for each virtual test environment of the plurality of virtual test environments, automatically testing the one or more autonomous operation features without input from a user by; execute the one or more software routines to respond to test input signals for the virtual vehicle within the fully virtual vehicle simulation; receive a plurality of test input signals for the virtual test environment from the sensor input simulator, wherein the test input signals simulate the one or more signals from at least one sensor corresponding to a test scenario associated with the virtual test environment; generate one or more test output signals for the virtual vehicle using the one or more software routines in response to the received test input signals for the virtual test environment; cause the sensor input simulator to predict one or more responses of the virtual vehicle in the virtual test environment to the one or more test output signals; determine a measure of the effectiveness of the one or more autonomous operation features based at least in part upon the one or more predicted responses of the virtual vehicle to the one or more test output signals associated with the plurality of virtual test environments; and adjust a risk profile associated with a vehicle having the one or more autonomous operation features based upon the determined measure of effectiveness by updating the risk profile to include one or more risk levels associated with autonomous operation of the vehicle by the one or more autonomous operation features. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A tangible, non-transitory computer-readable medium storing executable instructions for testing the effectiveness of one or more autonomous operation features for controlling vehicles by simulating operation of the one or more autonomous operation features in a virtual vehicle in a plurality of virtual test environments associated with a plurality of environmental conditions that, when executed by at least one processor of a computer system, cause the computer system to:
-
receive a set of computer-readable instructions for implementing the one or more autonomous operation features, wherein the set of computer-readable instructions comprises one or more software routines configured to receive one or more input signals from at least one sensor and generate one or more output signals for controlling a vehicle; cause a sensor input simulator to receive the plurality of virtual test environments; for each virtual test environment of the plurality of virtual test environments, automatically testing the one or more autonomous operation features without input from a user by; cause the sensor input simulator to generate a fully virtual vehicle simulation including the virtual vehicle within the virtual test environment; execute the one or more software routines to respond to test input signals for the virtual vehicle within the fully virtual vehicle simulation; receive a plurality of test input signals for the virtual test environment from the sensor input simulator, wherein the test input signals simulate the one or more signals from at least one sensor corresponding to a test scenario associated with the virtual test environment; generate one or more test output signals for the virtual vehicle using the one or more software routines in response to the received test input signals for the virtual test environment; cause the sensor input simulator to predict one or more responses of the virtual vehicle in the virtual test environment to the one or more test output signals; determine a measure of the effectiveness of the one or more autonomous operation features based at least in part upon the one or more predicted responses of the virtual vehicle to the one or more test output signals associated with the plurality of virtual test environments; and adjust a risk profile associated with a vehicle having the one or more autonomous operation features based upon the determined measure of effectiveness by updating the risk profile to include one or more risk levels associated with autonomous operation of the vehicle by the one or more autonomous operation features. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification