Autonomous vehicle safety platform system and method
A system 100 for autonomous vehicle operation can include: a low-level safety platform 130 ; and can optionally include and/or interface with any or all of: an autonomous agent 102 , a sensor system, a computing system 120 , a vehicle communication network 140 , a vehicle control system 150 , and/or any suitable components. The system functions to facilitate fallback planning and/or execution at the autonomous agent. Additionally or alternatively, the system can function to transition the autonomous agent between a primary (autonomous) operation mode and a fallback operation mode.
1. A method for repeatedly generating a fallback plan for an autonomous vehicle, the method comprising:
generating a set of fallback plans, comprising, at each of a set of multiple times during operation of the autonomous vehicle:
generating a fallback plan of the set of fallback plans, comprising:
based on a location of the autonomous vehicle, determining a set of safe state candidates for the autonomous vehicle;
evaluating each of the set of safe state candidates to determine an available subset of the set of safe state candidates;
selecting a safe state from the available subset; and
generating a polynomial path from the location to the selected safe state, wherein the fallback plan comprises the polynomial path;
operating the autonomous vehicle according to a primary plan, the primary plan separate and distinct from the fallback plan; and
checking for a trigger condition, wherein in an event that the trigger condition is satisfied, utilizing a most recently generated fallback plan.
2. The method of claim 1 , wherein the set of safe state candidates is determined based on referencing a map based on the location.
3. The method of claim 2 , wherein each of the set of safe state candidates satisfies at least one of:
having a distance to an intersection that is above a first predetermined distance threshold; and
having a distance to a crosswalk that is above a second predetermined distance threshold.
4. The method of claim 1 , wherein evaluating each of the set of safe state candidates to determine the available subset comprises eliminating a safe state candidate from inclusion in the available subset based on a set of dynamically determined features associated with at least one of: the autonomous vehicle or a set of objects detected in an environment of the autonomous vehicle.
5. The method of claim 4 , wherein the set of dynamically determined features comprises a determination that an object of the set of objects is arranged between the autonomous vehicle and the safe state candidate.
6. The method of claim 5 , wherein the determination comprises a prediction.
7. The method of claim 4 , wherein the set of dynamically determined features comprises a set of occupancy predictions for the set of objects, where the set of occupancy predictions indicates if an object of the set of objects is predicted to be arranged within the safe state candidate.
8. The method of claim 4 , wherein the available subset of the set of safe state candidates is determined based on at least one of: an autonomous vehicle dimension and a satisfaction of a minimum passing clearance associated with the autonomous vehicle reaching the safe state candidate.
9. The method of claim 8 , wherein evaluating each of the set of safe state candidates to determine the available subset further comprises calculating a set of scores for each of the available subset, wherein the selected safe state is selected based on the set of scores.
10. A system for repeatedly generating a fallback plan for an autonomous vehicle, the system comprising:
a first processing system, the first processing system configured to:
generate a set of fallback plans, comprising, at each of a set of multiple times during operation of the autonomous vehicle:
generate a fallback plan of the set of fallback plans, comprising:
based on a location of the autonomous vehicle, generate a set of safe state candidates for the autonomous vehicle;
evaluate each of the set of safe state candidates to determine an available subset of the set of safe state candidates;
select a safe state from the available subset; and
generate a polynomial path from the location to the selected safe state, wherein the fallback plan comprises the polynomial path;
operate the autonomous vehicle according to a primary plan, the primary plan separate and distinct from the fallback plan; and
check for a trigger condition, wherein in an event that the trigger condition is satisfied, triggering the operation of a second processing system;
the second processing system, the second processing system configured to:
implement a most recently generated fallback plan from the set of fallback plans.
11. The system of claim 10 , wherein the second processing system is separate and distinct from the first processing system.
12. The system of claim 11 , wherein the second processing system comprises an embedded controller.
13. The system of claim 10 , wherein the set of safe state candidates is determined based on referencing a map based on the location.
14. The system of claim 13 , wherein each of the set of safe state candidates satisfies at least one of:
having a distance to an intersection that is above a first predetermined distance threshold; and
having a distance to a crosswalk that is above a second predetermined distance threshold.
15. The system of claim 10 , wherein evaluating each of the set of safe state candidates to determine the available subset comprises eliminating a safe state candidate from inclusion in the available subset based on a set of dynamically determined features associated with at least one of: the autonomous vehicle or a set of objects detected in an environment of the autonomous vehicle.
16. The system of claim 15 , wherein the set of dynamically determined features comprises a determination that an object of the set of objects is arranged between the autonomous vehicle and the safe state candidate.
17. The system of claim 16 , wherein the determination comprises a prediction.
18. The system of claim 15 , wherein the set of dynamically determined features comprises a set of occupancy predictions for the set of objects, where the set of occupancy predictions indicates if an object of the set of objects is predicted to be arranged within the safe state candidate.
19. The system of claim 15 , wherein the available subset of the set of safe state candidates is determined based on at least one of: an autonomous vehicle dimension and a satisfaction of a minimum passing clearance associated with the autonomous vehicle reaching the safe state candidate.
20. The system of claim 19 , wherein evaluating each of the set of safe state candidates to determine the available subset further comprises calculating a set of scores for each of the available subset, wherein the selected safe state is selected based on the set of scores.