Human supervision of an automated driving system
The present disclosure provides systems and methods that enable human supervision of a highly capable automated driving system. In particular, the systems and methods of the present disclosure enable a human (e.g., a passenger, driver/operator, or remote supervisor of an autonomous vehicle) to easily and quickly transition control of the autonomous vehicle from a primary motion plan that controls the vehicle towards a primary destination to a secondary motion plan that controls the vehicle to a safe state. As such, the systems and methods of the present disclosure enable advanced human supervision of autonomous vehicle behavior in which a human can cause an autonomous vehicle to operate in a risk-reduced manner or otherwise maneuver to a safe state, without requiring the human to actually assume manual control of the vehicle.
1. A computing system, comprising:
a first motion planning module configured to determine a first motion plan that controls an autonomous vehicle towards a first destination, wherein the first motion plan is determined based at least in part on sensor data;
a second motion planning module configured to determine a second motion plan that controls the autonomous vehicle towards a second destination that is different than the first destination, wherein the second motion plan is determined based at least in part on the sensor data and is separately determinable from the first motion plan; and
a motion plan controller configured to:
receive data representing the first motion plan and the second motion plan;
prior to receiving an input from a passenger of the autonomous vehicle, issue one or more first control signals to control the autonomous vehicle according to the first motion plan;
determine that the input is received from the passenger of the autonomous vehicle; and
in response to determining that the input is received, issue one or more second control signals to abort the first motion plan and to control the autonomous vehicle according to the second motion plan.
2. The computing system of claim 1 , wherein the first motion planning module and the second motion planning module share sensor data but separately determine the first motion plan and the second motion plan.
3. The computing system of claim 1 , wherein:
the second motion plan comprises an emergency motion plan; and
the input from the passenger of the autonomous vehicle comprises an input indicative of an emergency event.
4. The computing system of claim 1 , wherein:
the first motion planning module is configured to determine a plurality of first motion plans respectively for a plurality of time periods;
the second motion planning module is configured to determine a plurality of second motion plans respectively for the plurality of time periods;
the motion plan controller is configured to issue the one or more first control signals to control the autonomous vehicle according to the first motion plans for each time period prior to receipt of the input from the passenger of the autonomous vehicle; and
the motion plan controller is configured to issue the one or more second control signals to control the autonomous vehicle according to the second motion plans for each time period subsequent to receipt of the input from the passenger of the autonomous vehicle.
5. The computing system of claim 1 , wherein control of the autonomous vehicle according to the second motion plan brings the autonomous vehicle to rest while remaining within a current lane.
6. The computing system of claim 1 , wherein control of the autonomous vehicle according to the second motion plan causes the autonomous vehicle to exit a flow of traffic.
7. The computing system of claim 1 , wherein the first motion planning module comprises a first optimization planner that optimizes a first set of cost functions to determine the first motion plan, and wherein second motion planning module comprises a second optimization planner that optimizes a second set of cost functions to determine the second motion plan, the first optimization planner different and distinct from the second optimization planner.
8. The computing system of claim 1 , wherein the second motion planning module is configured to determine a plurality of second motion plans that respectively control the autonomous vehicle to a plurality of different locations.
9. The computing system of claim 8 , wherein:
the input from the passenger selects one of the plurality of second motion plans; and
the motion plan controller is configured to issue the one or more second controls signals to control the autonomous vehicle according to the second motion plan selected by the input.
10. The computing system of claim 1 , wherein the second motion plan controls the autonomous vehicle to a safe state.
11. The computing system of claim 10 , wherein:
the first motion plan comprises a first trajectory that moves the autonomous vehicle towards the first destination; and
the second motion plan comprises a second trajectory that moves the autonomous vehicle to the safe state.
12. An autonomous vehicle, the autonomous vehicle comprising:
a first motion planning module configured to determine a first motion plan that controls the autonomous vehicle towards a first destination, wherein the first motion plan is determined based at least in part on sensor data;
a second motion planning module configured to determine a second motion plan that controls the autonomous vehicle towards a second destination that is different than the first destination, wherein the second motion plan is determined based at least in part on the sensor data and is separately determinable from the first motion plan; and
a motion plan controller configured to:
receive data representing the first motion plan and the second motion plan;
prior to receiving an input from a passenger of the autonomous vehicle, issue one or more first control signals to control the autonomous vehicle according to the first motion plan;
determine that the input is received from the passenger of the autonomous vehicle; and
in response to determining that the input is received, issue one or more second control signals to abort the first motion plan and to control the autonomous vehicle according to the second motion plan.
13. The autonomous vehicle of claim 12 , wherein the first motion planning module and the second motion planning module share sensor data but separately determine the first motion plan and the second motion plan.
14. The autonomous vehicle of claim 12 , wherein the second motion plan controls the autonomous vehicle to a safe state.
15. The autonomous vehicle of claim 12 , wherein:
the second motion plan comprises an emergency motion plan; and
the input from the passenger of the autonomous vehicle comprises an input indicative of an emergency event.
16. The autonomous vehicle of claim 12 , wherein:
the first motion planning module is configured to determine a plurality of first motion plans respectively for a plurality of time periods;
the second motion planning module is configured to determine a plurality of second motion plans respectively for the plurality of time periods;
the motion plan controller is configured to issue the one or more first control signals to control the autonomous vehicle according to the first motion plans for each time period prior to receipt of the input from the passenger of the autonomous vehicle; and
the motion plan controller is configured to issue the one or more second control signals to control the autonomous vehicle according to the second motion plans for each time period subsequent to receipt of the input from the passenger of the autonomous vehicle.
17. The autonomous vehicle of claim 12 , wherein control of the autonomous vehicle according to the second motion plan brings the autonomous vehicle to rest while remaining within a current lane.
18. The autonomous vehicle of claim 12 , wherein control of the autonomous vehicle according to the second motion plan causes the autonomous vehicle to exit a flow of traffic.
19. The autonomous vehicle of claim 12 , wherein the first motion planning module comprises a first optimization planner that optimizes a first set of cost functions to determine the first motion plan, and wherein second motion planning module comprises a second optimization planner that optimizes a second set of cost functions to determine the second motion plan, the first optimization planner different and distinct from the second optimization planner.
20. A computer implemented method implemented by a computing system that comprises a first motion planning module and a second motion planning module that is redundant to the first motion planning module, wherein the first motion planning module is configured to determine a first motion plan, wherein the second motion planning module is configured to determine a second motion plan, and wherein the first motion planning module and the second motion planning module share sensor data but separately determine the first motion plan and the second motion plan, the method comprising:
receiving, by a motion plan controller, data representing the first motion plan and the second motion plan;
prior to receiving an input from a passenger of an autonomous vehicle, issuing, by the motion plan controller, one or more first control signals to control the autonomous vehicle according to the first motion plan;
determining, by the motion plan controller, that the input is received from the passenger of the autonomous vehicle; and
in response to determining that the input is received, issuing, by the motion plan controller, one or more second control signals to abort the first motion plan and to control the autonomous vehicle according to the second motion plan.