Fall back trajectory systems for autonomous vehicles
View Patent ↗Aspects of the disclosure provide systems and methods for providing suggested locations for pick up and destination locations. Pick up locations may include locations where an autonomous vehicle can pick up a passenger, while destination locations may include locations where the vehicle can wait for an additional passenger, stop and wait for a passenger to perform some task and return to the vehicle, or for the vehicle to drop off a passenger. As such, a request for a vehicle may be received from a client computing device. The request may identify a first location. A set of one or more suggested locations may be selected by comparing the predetermined locations to the first location. The set may be provided to the client computing device.
1. A method of controlling a vehicle, the method comprising:
generating, by a primary computing system, a nominal trajectory from a location for a vehicle in order to achieve a mission goal, the nominal trajectory being generated based on information received by the primary computing system from a perception system of the vehicle configured to detect objects in the vehicle's external environment;
generating, by the primary computing system, a fall back trajectory from the location for the vehicle in order to safely stop the vehicle, the fall back trajectory being generated based on the information received by the primary computing system from the perception system of the vehicle, wherein the nominal trajectory and the fall back trajectory are identical between the location and a divergent point and where the nominal trajectory and the fall back trajectory diverge after the divergent point;
sending, by the primary computing system, the fall back trajectory to a secondary computing system;
receiving, by the secondary computing system, the fall back trajectory; controlling, by the secondary computing system, the vehicle according to the fall back trajectory;
waiting, by the secondary computing system, for an updated trajectory from the primary computing system while controlling the vehicle according to the fall back trajectory; and
when the vehicle reaches a threshold point on the fall back trajectory and an updated trajectory has not yet been received by the secondary computing system, continuing to control the vehicle, by the secondary computing system, according to the fall back trajectory in order to safely stop the vehicle.
2. The method of claim 1 , further comprising, when an updated trajectory is received after the threshold point is reached, ignoring, by the secondary computing system the updated trajectory.
3. The method of claim 1 , further comprising:
receiving, by the secondary computing system, after the threshold point is reached, data from a sensor indicating that an object is detected by the sensor; and
in response to receiving the data from the sensor, applying, by the secondary computing system, the brakes of the vehicle in order to stop the vehicle immediately.
4. The method of claim 3 , wherein the sensor is not part of the perception system and is a dedicated sensor of the secondary computing system.
5. The method of claim 1 , wherein the divergent location corresponds to a time along the fall back trajectory during which the primary computing system should send an updated fall back trajectory during normal operation of the primary computing system.
6. The method of claim 1 , further comprising:
prior to receiving the fall back trajectory, receiving, by the secondary computing system from the primary computing system, a first fall back trajectory having a first divergent location where the first fall back trajectory diverges from a first nominal trajectory generated by the primary computing system;
controlling, by the secondary computing system, the vehicle according to the first fall back trajectory; and
prior to reaching the first divergent location, receiving, by the secondary computing system the fall back trajectory as an updated trajectory.
7. The method of claim 6 , further comprising replacing, by the secondary computing system, the nominal trajectory with the updated trajectory in order to control the vehicle according to the fall back trajectory.
8. The method of claim 1 , wherein the threshold point corresponds to a physical location of the vehicle that is a predetermined threshold distance from the location of the vehicle when the fall back trajectory is received.
9. The method of claim 1 , wherein the threshold point corresponds to a point in time that is a predetermined threshold amount of time from the time when the fall back trajectory is received by the secondary computing system.
10. The method of claim 1 , wherein the threshold point corresponds to a point of divergence between the nominal trajectory and the fall back trajectory.
11. A system for controlling a vehicle, the system comprising:
a primary computing system having one or more processors configured to:
generate a nominal trajectory from a location for a vehicle in order to achieve a mission goal, the nominal trajectory being generated based on information received by the primary computing system from a perception system of the vehicle configured to detect objects in the vehicle's external environment,
generate a fall back trajectory from the location for the vehicle in order to safely stop the vehicle, the fall back trajectory begin generated based on the information received by the primary computing system from the perception system of the vehicle, wherein the nominal trajectory and the fall back trajectory are identical between the location and a divergent location and where the nominal trajectory and the fall back trajectory diverge after the divergent location, and
sending the fall back trajectory to a secondary computing system; and
the secondary computing system having one or more processors configured to:
receive the fall back trajectory;
control the vehicle according to the fall back trajectory;
wait for an updated trajectory from the primary computing system while controlling the vehicle; and
when the vehicle reaches a threshold point on the fall back trajectory and an updated trajectory has not yet been received by the secondary computing system, continue to control the vehicle according to the fall back trajectory in order to safely stop the vehicle.
12. The system of claim 11 , wherein the one or more processors of the secondary computing system are further configured to, when an updated trajectory is received after the threshold point is reached, ignore the updated trajectory.
13. The system of claim 11 , wherein the one or more processors of the secondary computing system are further configured to:
receiving after the threshold value is reached, data from a sensor indicating that an object is detected by the sensor; and
in response to receiving the data from the sensor, applying the brakes of the vehicle in order to stop the vehicle immediately.
14. The system of claim 13 , further comprising the sensor and wherein the sensor is not part of the perception system and is a dedicated sensor of the secondary computing system.
15. The system of claim 11 , wherein the divergent location corresponds to a time along the fall back trajectory during which the primary computing system should send an updated fall back trajectory during normal operation of the primary computing system.
16. The system of claim 11 , wherein the one or more processors of the secondary computing system are further configured to:
prior to receiving the fall back trajectory, receive, from the primary computing system, a first fall back trajectory having a first divergent location where the first fall back trajectory diverges from a first nominal trajectory generated by the primary computing system;
control the vehicle according to the first fall back trajectory; and
prior to reaching the first divergent location, receive the fall back trajectory as an updated trajectory.
17. The system of claim 16 , wherein the one or more processors of the secondary computing system are further configured to replace the nominal trajectory with the updated trajectory in order to control the vehicle according to the fall back trajectory.
18. The system of claim 11 , further comprising the vehicle and the perception system.
19. A method comprising:
receiving, by one or more processors of the secondary computing system from the primary computing system, a fall back trajectory from a location of the vehicle in order to safely stop the vehicle, wherein a portion of the fall back trajectory from the location of the vehicle to a divergent location is identical to a portion of a nominal trajectory from the location of the vehicle to the divergent location, the nominal trajectory allows the vehicle to achieve a mission goal, and the nominal trajectory and the fall back trajectory diverge after the divergent location;
controlling, by the one or more processors of the secondary computing system, the vehicle according to the portion of the fall back trajectory in order to achieve the mission goal;
waiting, by the one or more processors of the secondary computing system, for an updated trajectory from the primary computing system while controlling the vehicle; and
when the vehicle reaches a threshold point on the fall back trajectory and an updated trajectory has not yet been received by the one or more processors of the secondary computing system, continuing, by the one or more processors of the secondary computing system, to control the vehicle according to the fall back trajectory in order to safely stop the vehicle.
20. The method of claim 19 , further comprising when an updated trajectory is received after the threshold point is reached, ignoring, by the one or more processors of the secondary computing system, the updated trajectory.