Intervention in operation of a vehicle having autonomous driving capabilities
Among other things, a determination is made that intervention in an operation of one or more autonomous driving capabilities of a vehicle is appropriate. Based on the determination, a person is enabled to provide information for an intervention. The intervention is caused in the operation of the one or more autonomous driving capabilities of the vehicle.
1. A vehicle comprising:
at least one processor; and
a non-transitory computer-readable storage medium storing instructions which when executed by the at least one processor cause the at least one processor to:
operate the vehicle in an autonomous mode;
receive a command using a vehicle-to-infrastructure (V2I) communication device of the vehicle, the command instructing the vehicle to maneuver to a goal location;
determine that the vehicle fails to maneuver to the goal location; and
responsive to determining that the vehicle fails to maneuver to the goal location, transmit a teleoperation request to a teleoperation server and implement one or more fallback operations for controlling the vehicle in the autonomous mode while waiting for one or more teleoperations for controlling the vehicle in the autonomous mode from the teleoperation server, wherein the one or more fallback operations are different from the one or more teleoperations, wherein each fallback operation is associated with at least one system process and a cost, and wherein the one or more fallback operations are selected from a list of fallback operations based on their respective cost and an availability of the at least one system process associated with each of the one or more fallback operations, wherein the cost represents a reduced amount of perception accuracy of perceiving objects in an environment near the vehicle when implementing the one or more fallback operations.
2. The vehicle of claim 1 , wherein the one or more fallback operations include at least two fallback operations, wherein costs of the at least two fallback operations are added or weighted-summed.
3. The vehicle of claim 1 , wherein the teleoperation request comprises one or more trajectory sampling points for the vehicle.
4. The vehicle of claim 1 , wherein maneuvering to the goal location comprises:
treating a current location of the vehicle as prior knowledge; and
using an inference algorithm to update the current location of the vehicle based on the command.
5. The vehicle of claim 1 , wherein maneuvering to the goal location comprises inferring a speed profile from the command.
6. The vehicle of claim 1 , wherein maneuvering to the goal location comprises inferring a steering angle from the command using a learning algorithm.
7. The vehicle of claim 1 , wherein maneuvering to the goal location comprises enabling, editing or disabling a hardware component or a software process.
8. The vehicle of claim 1 , wherein maneuvering to the goal location comprises overwriting a travel preference or a travel rule.
9. The vehicle of claim 1 , wherein maneuvering to the goal location comprises editing data comprising one or more of a map, sensor data in the vehicle or a related AV system, trajectory data in the vehicle or the related AV system, vision data in the vehicle or the related AV system, or any past data in the vehicle or the related AV system.
10. A non-transitory computer-readable storage medium storing instructions, which when executed by one or more processors cause the one or more processors to:
operate a vehicle in an autonomous mode;
receive a command using a vehicle-to-infrastructure (V2I) communication device of the vehicle, the command instructing the vehicle to maneuver to a goal location;
determine that the vehicle fails to maneuver to the goal location; and
responsive to determining that the vehicle fails to maneuver to the goal location, transmit a teleoperation request to a teleoperation server and implement one or more fallback operations for controlling the vehicle in the autonomous mode while waiting for one or more teleoperations for controlling the vehicle in the autonomous mode from the teleoperation server, wherein the one or more fallback operations are different from the one or more teleoperations, wherein each fallback operation is associated with at least one system process and a cost, and wherein the one or more fallback operations are selected from a list of fallback operations based on their respective cost and an availability of the at least one system process associated with each of the one or more fallback operations, wherein the cost represents a reduced amount of perception accuracy of perceiving objects in an environment near the vehicle when implementing the one or more fallback operations.
11. The non-transitory computer-readable storage medium of claim 10 , wherein the teleoperation request comprises a current location of the vehicle.
12. The non-transitory computer-readable storage medium of claim 10 , wherein the teleoperation request comprises one or more trajectory sampling points for the vehicle.
13. The non-transitory computer-readable storage medium of claim 10 , wherein maneuvering to the goal location comprises:
treating a current location of the vehicle as prior knowledge; and
using an inference algorithm to update the current location of the vehicle based on the command.
14. The non-transitory computer-readable storage medium of claim 10 , wherein maneuvering to the goal location comprises inferring a speed profile from the command.
15. The non-transitory computer-readable storage medium of claim 10 , wherein maneuvering to the goal location comprises inferring a steering angle from the command using a learning algorithm.
16. The non-transitory computer-readable storage medium of claim 10 , wherein maneuvering to the goal location comprises enabling, editing or disabling a hardware component or a software process.
17. The non-transitory computer-readable storage medium of claim 10 , wherein maneuvering to the goal location comprises overwriting a travel preference or a travel rule.
18. The non-transitory computer-readable storage medium of claim 10 , wherein maneuvering to the goal location comprises editing data comprising one or more of a map, sensor data in the vehicle or a related AV system, trajectory data in the vehicle or the related AV system, vision data in the vehicle or the related AV system, or any past data in the vehicle or the related AV system.
19. A method comprising:
operating, by one or more processors, a vehicle in an autonomous mode;
receiving, by the one or more processors, a command using a vehicle-to-infrastructure (V2I) communication device of the vehicle, the command instructing the vehicle to maneuver to a goal location;
determining, by the one or more processors, that the vehicle fails to maneuver to the goal location; and
responsive to determining that the vehicle fails to maneuver to the goal location, transmitting, by the one or more processors, a teleoperation request to a teleoperation server and implement one or more fallback operations for controlling the vehicle in the autonomous mode while waiting for one or more teleoperations for controlling the vehicle in the autonomous mode from the teleoperation server, wherein the one or more fallback operations are different from the one or more teleoperations, wherein each fallback operation is associated with at least one system process and a cost, and wherein the one or more fallback operations are selected from a list of fallback operations based on their respective cost and an availability of the at least one system process associated with each of the one or more fallback operations, wherein the cost represents a reduced amount of perception accuracy of perceiving objects in an environment near the vehicle when implementing the one or more fallback operations.