Dynamic assignment of friction coefficient using sensor data for use in simulation
Systems and techniques are described for improving the accuracy of autonomous vehicle simulations by dynamically assigning friction coefficients to road features based on sensor data. A method of the disclosed technology can include steps for associating a predetermined friction coefficient to road features; receiving sensor data from a sensor on an autonomous vehicle; identifying, from the sensor data, the presence of a road feature; assigning in a simulation, a friction coefficient corresponding to the road feature based on the predetermined friction coefficient associated with road feature; and generating, based on the assigned friction coefficient, a simulation of a trip by the autonomous vehicle as the autonomous vehicle traverses the road feature.
1. A computer-implemented method comprising:
associating a predetermined friction coefficient to each road feature of a plurality of road features;
receiving sensor data from a sensor on an autonomous vehicle, wherein the sensor data is related to at least one road feature of the plurality of road features;
identifying, from the sensor data, a presence of the at least one road feature in a real-world environment;
assigning in a simulation, a friction coefficient corresponding to the at least one road feature based on the predetermined friction coefficient associated with the at least one road feature;
generating, based on the assigned friction coefficient, a simulation of a trip by the autonomous vehicle as the autonomous vehicle traverses the at least one road feature, the simulation indicative of an interaction between the autonomous vehicle and the at least one road feature, wherein the simulation accounts for driving conditions in the real-world environment based on use of the assigned friction coefficient for the at least one road feature;
receiving force data from a friction sensor on the autonomous vehicle; and
validating the assigned friction coefficient used in the simulation by using the force data from the friction sensor, wherein the force data is further processed to determine the real-world friction coefficient for the at least one road feature.
2. The computer-implemented method of claim 1 , wherein the sensor comprises at least one of a camera sensor and a light detection and ranging (LIDAR) sensor.
3. The computer-implemented method of claim 1 , wherein the plurality of road features includes at least one of road surface material, pavement markers, and road artifacts.
4. The computer-implemented method of claim 1 , further comprising applying a machine learning model to the sensor data to identify the at least one road feature.
5. The computer-implemented method of claim 4 , further comprising performing image processing to determine a reflectivity of the at least one road feature, the reflectivity indicative of an environmental condition of the at least one road feature.
6. The computer-implemented method of claim 1 , further comprising receiving environmental sensor data from a second sensor on an autonomous vehicle, wherein the second sensor comprises at least one of a rain sensor, temperature sensor, and humidity sensor.
7. The computer-implemented method of claim 6 , further comprising:
receiving an operational state of a component on the autonomous vehicle, the component comprising at least one of a windshield wiper and climate control blower; and
identifying, from the environmental sensor data and the operational state of the component, an environmental condition of the at least one road feature, wherein the environmental condition includes at least one of a wet condition, ice condition, and snow condition.
8. The computer-implemented method of claim 7 , further comprising:
receiving geographical weather data; and
confirming, from the geographical weather data, the environmental condition of the at least one road feature.
9. A non-transitory computer-readable storage medium comprising at least one instruction for causing one or more processors to:
associate a predetermined friction coefficient to each road feature of a plurality of road features based on an environmental condition for each road feature;
receive sensor data from at least one of a sensor mounted on an autonomous vehicle, wherein the sensor data is related to at least one road feature of the plurality of road features;
identify, from the sensor data, the presence and environmental condition of the at least one road feature in a real-world environment;
assign in a simulation, a friction coefficient corresponding to the at least one road feature based on the predetermined friction coefficient associated with the environmental condition of the at least one road feature;
generate, based on the assigned friction coefficient, a simulation of a trip by the autonomous vehicle as the autonomous vehicle traverses the at least one road feature, the simulation indicative of an interaction between the autonomous vehicle and the at least one road feature, wherein the simulation accounts for driving conditions in the real-world environment based on use of the assigned friction coefficient for the at least one road feature;
receive environmental sensor data from a second sensor on an autonomous vehicle, wherein the second sensor comprises at least one of a rain sensor, temperature sensor, and humidity sensor;
receive an operational state of a component on the autonomous vehicle, the component comprising at least one of a windshield wiper and climate control blower; and
identify, from the environmental sensor data and the operational state of the component, the environmental condition of the at least one road feature, wherein the environmental condition includes at least one of a wet condition, ice condition, and snow condition.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the plurality of road features includes at least one of road surface material, pavement markers, and road artifacts.
11. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions are further configured to cause the one or more processors to apply a machine learning model to the sensor data to identify the at least one road feature.
12. The non-transitory computer-readable storage medium of claim 11 , wherein the instructions are further configured to cause the one or more processors to perform image processing to determine a reflectivity of the at least one road feature, the reflectivity indicative of the environmental condition of the at least one road feature.
13. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions are further configured to cause the one or more processors to:
receive geographical weather data; and
confirm, from the geographical weather data, the environmental condition of the at least one road feature.
14. A system comprising:
at least one processor;
at least one memory storing computer-readable instructions that, when executed by the at least one processor, causes the at least one processor to:
associate a predetermined friction coefficient to each road feature of a plurality of road features based on an environmental condition for each road feature;
receive sensor data from at least one of a sensor mounted on an autonomous vehicle, wherein the sensor data is related to at least one road feature of the plurality of road features;
identify, from the sensor data, the presence and environmental condition of the at least one road feature in a real-world environment;
assign in a simulation, a friction coefficient corresponding to the at least one road feature based on the predetermined friction coefficient associated with the environmental condition of the at least one road feature;
generate, based on the assigned friction coefficient, a simulation of a trip by the autonomous vehicle as the autonomous vehicle traverses the road feature, the simulation indicative of an interaction between the autonomous vehicle and the at least one road feature, wherein the simulation accounts for driving conditions in the real-world environment based on use of the assigned friction coefficient for the at least one road feature;
receive environmental sensor data from a second sensor on an autonomous vehicle, wherein the second sensor comprises at least one of a rain sensor, temperature sensor, and humidity sensor;
receive an operational state of a component on the autonomous vehicle, the component comprising at least one of a windshield wiper and climate control blower; and
identify, from the environmental sensor data and the operational state of the component, the environmental condition of the at least one road feature, wherein the environmental condition includes at least one of a wet condition, ice condition, and snow condition.
15. The system of claim 14 , wherein the plurality of road features includes at least one of road surface material, pavement markers, and road artifacts.
16. The system of claim 14 , wherein the instructions are further configured to cause the at least one processor to:
apply a machine learning model to the sensor data to identify the at least one road feature; and
perform image processing to determine a reflectivity of the at least one road feature, the reflectivity indicative of the environmental condition of the at least one road feature.
17. The system of claim 14 , wherein the instructions are further configured to cause the at least one processor to:
receive geographical weather data; and
confirm, from the geographical weather data, the environmental condition of the at least one road feature.