Motion planning constraints for autonomous vehicles
A method includes obtaining road patch type data associated with at least one road patch type, deriving, from the road patch type data, a set of road patch type parameters for the at least one road patch type, generating, based on the set of road patch type parameters, a set of risk metrics, each risk metric of the set of risk metrics corresponding to a respective road patch type parameter of the set of road patch type parameters, identifying, based at least in part on the set of risk metrics, a set of autonomous vehicle (AV) motion planning constraints selected for the at least one road patch type, and providing the set of AV motion planning constraints to update motion planning functionality performed by at least one component of an AV.
1. A system comprising:
a memory device; and
a processing device, operatively coupled to the memory device, to perform operations comprising:
obtaining road patch type data associated with at least one road patch type of road portions of a road in a driving environment of an autonomous vehicle (AV);
deriving, from the road patch type data, a set of road patch type parameters for the at least one road patch type, wherein the set of road patch type parameters for the at least one road patch type are based at least in part on lengths of a plurality of road portions of a particular road patch type of the at least one road patch type;
generating, based on the set of road patch type parameters, a set of risk metrics, each risk metric of the set of risk metrics corresponding to a respective road patch type parameter of the set of road patch type parameters;
identifying, based at least in part on the set of risk metrics, a set of AV motion planning constraints selected for the at least one road patch type; and
providing the set of AV motion planning constraints to update motion planning functionality performed by at least one component of the AV, wherein the set of AV motion planning constraints minimizes risk during autonomous operation of the AV for the at least one road patch type.
2. The system of claim 1 , wherein the at least one road patch type corresponds to at least one respective non-standard road state.
3. The system of claim 2 , wherein the at least one road patch type comprises at least one of: a wet road patch, an icy road patch, a snowy road patch, a dirt road patch, or a gravel road patch.
4. The system of claim 1 , wherein the set of road patch type parameters for the at least one road patch type comprises a set of length frequencies, each length frequency of the set of length frequencies corresponding to a rate of occurrence of a respective length or a respective length range of the at least one road patch type.
5. The system of claim 4 , wherein generating the set of risk metrics comprises determining, for each length frequency of the set of length frequencies, a respective risk value.
6. The system of claim 1 , wherein the set of AV motion planning constraints comprises at least one of: a coefficient of friction, or a set of dynamic constraints.
7. The system of claim 1 , wherein:
the operations further comprise obtaining auxiliary data for identifying the set of AV motion planning constraints; and
the set of AV motion planning constraints is identified based on the set of risk metrics and the auxiliary data.
8. The system of claim 7 , wherein the auxiliary data comprises at least one of: a set of historical AV motion planning constraints, a historical rate of encountering other agents within a driving environment, or weather information.
9. A method comprising:
obtaining, by a processing device, road patch type data associated with at least one road patch type of road portions of a road in a driving environment of an autonomous vehicle (AV);
deriving, by the processing device from the road patch type data, a set of road patch type parameters for the at least one road patch type, wherein the set of road patch type parameters for the at least one road patch type are based at least in part on lengths of a plurality of road portions of a particular road patch type of the at least one road patch type;
generating, by the processing device based on the set of road patch type parameters, a set of risk metrics, each risk metric of the set of risk metrics corresponding to a respective road patch type parameter of the set of road patch type parameters;
identifying, by the processing device based at least in part on the set of risk metrics, a set of AV motion planning constraints selected for the at least one road patch type; and
providing, by the processing device, the set of AV motion planning constraints to update motion planning functionality performed by at least one component of the AV, wherein the set of AV motion planning constraints minimizes risk during autonomous operation of the AV for the at least one road patch type.
10. The method of claim 9 , wherein the at least one road patch type corresponds to at least one respective non-standard road state.
11. The method of claim 10 , wherein the at least one road patch type comprises at least one of: a wet road patch, an icy road patch, a snowy road patch, a dirt road patch, or a gravel road patch.
12. The method of claim 9 , wherein the set of road patch type parameters for the at least one road patch type comprises a set of length frequencies, each length frequency of the set of length frequencies corresponding to a rate of occurrence of a respective length or a respective length range of the at least one road patch type.
13. The method of claim 12 , wherein generating the set of risk metrics comprises determining, for each length frequency of the set of length frequencies, a respective risk value.
14. The method of claim 9 , wherein the set of AV motion planning constraints comprises at least one of: a coefficient of friction, or a set of dynamic constraints.
15. The method of claim 9 , further comprising:
obtaining, by the processing device, auxiliary data for identifying the set of AV motion planning constraints;
wherein identifying the set of AV motion planning constraints comprises identifying the set of AV motion planning constraints based on the set of risk metrics and the auxiliary data.
16. The method of claim 15 , wherein the auxiliary data comprises at least one of: a set of historical AV motion planning constraints, a historical rate of encountering other agents within a driving environment, or weather information.
17. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by a processing device, cause the processing device to perform operations comprising:
obtaining road patch type data associated with at least one road patch type corresponding to at least one respective non-standard road state;
deriving, from the road patch type data, a set of road patch type parameters for the at least one road patch type, wherein the set of road patch type parameters for the at least one road patch type comprises a set of length frequencies, each length frequency of the set of length frequencies corresponding to a rate of occurrence of a respective length or a respective length range of the at least one road patch type;
generating, based on the set of road patch type parameters, a set of risk metrics, each risk metric of the set of risk metrics corresponding to a respective road patch type parameter of the set of road patch type parameters, wherein generating the set of risk metrics comprises determining a respective risk value for each length frequency of the set of length frequencies;
identifying, based at least in part on the set of risk metrics, a set of autonomous vehicle (AV) motion planning constraints selected for the at least one road patch type, wherein the set of AV motion planning constraints comprises at least one of: a coefficient of friction, or a set of dynamic constraints; and
providing the set of AV motion planning constraints to update motion planning functionality performed by at least one component of an AV, wherein the set of AV motion planning constraints minimizes risk during autonomous operation of the AV for the at least one road patch type.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the at least one road patch type comprises at least one of: a wet road patch, an icy road patch, a snowy road patch, a dirt road patch, or a gravel road patch.
19. The non-transitory computer-readable storage medium of claim 17 , wherein:
the operations further comprise obtaining auxiliary data for identifying the set of AV motion planning constraints; and
identifying the set of AV motion planning constraints comprises identifying the set of AV motion planning constraints based on the set of risk metrics and the auxiliary data.
20. The non-transitory computer-readable storage medium of claim 19 , wherein the auxiliary data comprises at least one of: a set of historical AV motion planning constraints, a historical rate of encountering other agents within a driving environment, or weather information.