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 determining and implementing a fallback plan for an autonomous vehicle, the method comprising:
producing a set of operational plans and a set of fallback plans, comprising, at each of a set of multiple intervals:
collecting sensor data from a set of sensors associated with the autonomous vehicle;
processing the sensor data at a computing system to:
determine an operational plan of the set of operational plans for the autonomous vehicle;
determine a fallback plan of the set of fallback plans for the autonomous vehicle; and
transmit the fallback plan to memory associated with a low level safety platform;
checking for a set of trigger conditions, the set of trigger conditions comprising at least one of:
a loss of communication between the computing system and the low level safety platform;
an error associated with a set of control commands generated by the computing system;
in response to determining that none of the set of trigger conditions is satisfied, navigating the autonomous vehicle according to a most recently determined operational plan of the set of operational plans;
while navigating the autonomous vehicle according to the most recently determined operational plan, checking for the set of trigger conditions, wherein in response to detecting satisfaction of a trigger condition of the set of trigger conditions, navigating the autonomous vehicle according to a most recently determined fallback plan of the set of fallback plans, wherein the fallback plan deviates from a path of the operational plan.
2. The method of claim 1 , wherein the set of control commands is associated with an operational plan of the set of operational plans.
3. The method of claim 1 , wherein determining the fallback plan comprises:
referencing a map to determine a set of predetermined locations within the map;
selecting a location from the set of predetermined locations; and
generating a path from the autonomous vehicle to the selected location.
4. The method of claim 3 , wherein selecting the location from the predetermined set of locations comprises determining an availability associated with the location.
5. The method of claim 4 , wherein the availability is determined based an occupancy prediction associated with the location.
6. The method of claim 5 , further comprising calculating the occupancy prediction based on features associated with a set of dynamic objects in an environment of the autonomous vehicle detected based on the sensor data.
7. The method of claim 6 , wherein the availability is further determined based on a dimension associated with the autonomous vehicle.
8. The method of claim 6 , wherein the availability is further determined based on satisfaction of a minimum passing clearance for the autonomous vehicle to reach the location.
9. The method of claim 1 , wherein detecting satisfaction of the trigger condition is performed at the computing system.
10. The method of claim 9 , wherein the low level safety platform comprises an embedded controller, the embedded controller separate and distinct from the computing system.
11. A system for determining and implementing a fallback plan for an autonomous vehicle, the system comprising:
a first computing system configured to:
collect sensor data from a set of sensors associated with the autonomous vehicle;
process the sensor data to:
determine an operational plan for the autonomous vehicle;
determine a fallback plan for the autonomous vehicle; and
transmit the fallback plan to memory associated with a second computing system;
check for a set of trigger conditions, the set of trigger conditions comprising at least one of:
a loss of communication between the first computing system and the second computing system; and
an error associated with a set of control commands generated by the first computing system;
in response to determining that none of the set of trigger conditions is satisfied, navigate the autonomous vehicle according to the operational plan; and
while navigating the autonomous vehicle according to the operational plan, check for the set of trigger conditions, wherein in response to detecting satisfaction of a trigger condition of the set of trigger conditions, initiate operation of the second computing system;
the second computing system configured to:
in response to the satisfaction of the trigger condition, retrieve the fallback plan from the memory; and
navigate the autonomous vehicle according to the fallback plan, wherein the fallback plan deviates from a path of the operational plan.
12. The system of claim 11 , wherein navigating the autonomous vehicle according to the fallback plan comprises maneuvering the autonomous vehicle to come to a stop at a predetermined location, the predetermined location determined based on referencing a map.
13. The system of claim 11 , wherein the fallback plan is part of a set of fallback plans, wherein retrieving the fallback plan comprises retrieving a most recently generated fallback plan from the set of fallback plans.
14. The system of claim 11 , wherein the set of control commands is associated with the operational plan.
15. The system of claim 11 , wherein determining the fallback plan comprises:
referencing a map to determine a set of predetermined locations within the map;
selecting a location from the set of predetermined locations; and
generating a path from the autonomous vehicle to the selected location.
16. The system of claim 15 , wherein selecting the location from the predetermined set of locations comprises determining an availability associated with the location.
17. The system of claim 16 , wherein the availability is determined based an occupancy prediction associated with the location.
18. The system of claim 17 , wherein the first computing system is further configured to calculate the occupancy prediction based on features associated with a set of dynamic objects detected based on the sensor data.
19. The system of claim 15 , wherein the availability is determined based on at least one of: an occupancy prediction associated with the location; a dimension associated with the autonomous vehicle; and a satisfaction of a minimum passing clearance for the autonomous vehicle to reach the location.
20. The system of claim 11 , wherein the second computing system comprises an embedded controller, the embedded controller separate and distinct from the first computing system.