Complementary control system for an autonomous vehicle

1. A method for operating an autonomous vehicle (AV), the method comprising, by a complementary controller:

receiving, from a primary controller, information comprising an active trajectory of an AV, the active trajectory being a path that the AV intends to follow for a planning horizon;

using the active trajectory to identify one or more regions in an environment of the AV, the one or more regions comprising the following: a fallback monitoring region (FMR) and an active monitoring region (AMR);

generating one or more instructions for causing the AV to execute a collision mitigation action in response to an object being detected within the AMR; and

transmitting the one or more instructions to an AV platform (AVP) for execution,

wherein the FMR corresponds to a first length from a first current position of the AV to a first stopping point and the first stopping point is a point on the active trajectory that is reached by the AV at a first allowed deceleration rate when the collision mitigation action is executed;

wherein the AMR corresponds to a second length from a second current position of the AV to a second stopping point and the second stopping point is a point on the active trajectory that is reached by the AV at a second allowed deceleration rate when the collision mitigation action is executed; and

wherein the first length is greater than the second length.

2. The method of claim 1 , further comprising, by a primary controller:

receiving a first set of sensor data from a primary sensor system and a second set of sensor data from a secondary sensor system;

generating, based on the first set of sensor data and the second set of sensor data, the active trajectory; and

transmitting, to the complementary controller, primary navigation instructions for navigating the AV along the active trajectory for transmission to the AVP.

3. The method of claim 2 , further comprising, by the complementary controller:

receiving, from the primary controller, the primary navigation instructions for transmission to the AVP; and

while transmitting the one or more instructions to the AVP, stopping transmission of the received primary navigation instructions to the AVP.

4. The method of claim 2 , further comprising, by the complementary controller, generating the one or more instructions for causing the AV to execute the collision mitigation action when the primary navigation instructions include a deceleration instruction that is greater than a maximum allowed deceleration.

5. The method of claim 1 , further comprising, by the complementary controller generating the one or more instructions only in response to a risk of collision between the object and the AV being greater than a threshold.

6. The method of claim 5 , wherein the risk of collisions is determined to be greater than the threshold based on at least one of the following: a state of the object; a state of the AV; environmental conditions; sensing pipeline performance; or detection pipeline performance.

7. The method of claim 1 , further comprising, by the complementary controller, in response to a second object being present within an area of the FMR that does not include the AMR, generating the one or more instructions for causing the AV to execute the collision mitigation action only if an instruction for executing a minimum risk collision (MRC) state has been received by the complementary controller.

8. The method of claim 7 , wherein the instruction for executing the MRC state is received from a primary controller upon detection of an error in one or more functions of the primary controller.

9. The method of claim 1 , further comprising, by the complementary controller, stopping transmission of the one or more instructions to the AVP in response to determining an error within the complementary controller, the error comprising at least one of the following: a pose determination error; a sensor error; a sensor communication error; a primary controller communication error; or a perception error.

10. The method of claim 1 , wherein the second allowed deceleration rate is greater than the first allowed deceleration rate.

11. A system for operating an autonomous vehicle (AV), the system comprising: an AV comprising:

a secondary sensor system,

a primary controller, and

a complementary controller, the complementary controller being configured to:

receive, from the primary controller, information comprising an active trajectory of the AV, the active trajectory being a path that the AV intends to follow for a planning horizon;

use the active trajectory to identify one or more regions in an environment of the AV, the one or more regions comprising the following: a fallback monitoring region (FMR) and an active monitoring region (AMR);

generate one or more instructions for causing the AV to execute a collision mitigation action in response to an object being detected within the AMR; and

transmit the one or more instructions to an AV platform (AVP) for execution,

wherein the FMR corresponds to a first length from a first current position of the AV to a first stopping point and the first stopping point is a point on the active trajectory that is reached by the AV at a first allowed deceleration rate when the collision mitigation action is executed;

wherein the AMR corresponds to a second length from a second current position of the AV to a second stopping point and the second stopping point is a point on the active trajectory that is reached by the AV at a second allowed deceleration rate when the collision mitigation action is executed; and

wherein the first length is greater than the second length.

12. The system of claim 11 , wherein the primary controller is configured to:

receive a first set of sensor data from a primary sensor system and a second set of sensor data from the secondary sensor system;

generate, based on the first set of sensor data and the second set of sensor data, the active trajectory; and

transmit, to the complementary controller, primary navigation instructions for navigating the AV along the active trajectory for transmission to the AVP.

13. The system of claim 11 , wherein the second allowed deceleration rate is greater than the first allowed deceleration rate.

14. A computer program product comprising a memory and programming instructions that are configured to cause a processor to:

receive, from a primary controller, information comprising an active trajectory of an autonomous vehicle (AV), the active trajectory being a path that the AV intends to follow for a planning horizon;

use the active trajectory to identify one or more regions in an environment of the AV, the one or more regions comprising the following: a fallback monitoring region (FMR) and an active monitoring region (AMR);

generate one or more instructions for causing the AV to execute a collision mitigation action in response to an object being detected within the AMR; and

transmit the one or more instructions to an AV platform (AVP) for execution,

wherein the FMR corresponds to a first length from a first current position of the AV to a first stopping point and the first stopping point is a point on the active trajectory that is reached by the AV at a first allowed deceleration rate when the collision mitigation action is executed;

wherein the AMR corresponds to a second length from a second current position of the AV to a second stopping point and the second stopping point is a point on the active trajectory that is reached by the AV at a second allowed deceleration rate when the collision mitigation action is executed; and

wherein the first length is greater than the second length.

15. The computer program product of claim 14 , further comprising programming instructions that when executed by the processor cause the processor to generate the one or more instructions only in response to a risk of collision between the object and the AV being greater than a threshold.

16. The computer program product of claim 14 , wherein the second allowed deceleration rate is greater than the first allowed deceleration rate.