Mixed-mode driving of a vehicle having autonomous driving capabilities
Among other things, a vehicle having autonomous driving capabilities is operated in a mixed driving mode.
1. A method comprising:
receiving sensor information from one or more sensors from each vehicle in a fleet of vehicles, each vehicle comprising an autonomous driving capability, wherein the sensor information indicates a state of occupancy of the vehicle indicating that the vehicle is occupied;
determining, at a server and based on the state of occupancy and a collision risk to at least one vehicle in the fleet of vehicles or objects surrounding the at least one vehicle, a next driving mode transition from a current driving mode, a next driving mode comprising at least one of an autonomous driving mode, a manual driving mode, and a driving mode that uses a combination of autonomous driving capabilities and manual driving capabilities, wherein determining the next driving mode transition includes determining, based on the state of occupancy of the at least one vehicle, a threshold of driving smoothness for the next driving mode transition for the at least one vehicle;
gradually adjusting a change in speed of the at least one vehicle during the driving mode transition from the current driving mode to the next driving mode in accordance with the threshold of driving smoothness; and
sending signals wirelessly to the at least one vehicle of the fleet identifying, based on the determined next driving mode transition and the determined smoothing operation, the next driving mode for the at least one vehicle.
2. The method of claim 1 , further comprising:
determining a sequence of the next driving mode transitions for each of the vehicles; and
sending signals wirelessly to each of the vehicles identifying, based on the determined next driving mode transitions, the next driving modes in the sequence of the next driving mode transitions.
3. The method of claim 1 , wherein the next driving mode transition of the at least one vehicle is determined based on data representing one or a combination of two or more of the following factors: (a) a characteristic of one or more occupants for the at least one vehicle, (b) a characteristic of one or more parcels on board the at least one vehicle, (c) a condition of a driving environment of the at least one vehicle, and (d) a condition of the at least one vehicle.
4. The method of claim 3 , wherein the characteristic of one or more occupants of the at least one vehicle comprises at least one of: a preference of the occupant for a particular driving mode, a health-related condition of the occupant, or impairment of the occupant's ability to manually drive the at least one vehicle.
5. The method of claim 3 , wherein the characteristic of one or more parcels on board the at least one vehicle comprises a destructive quality of the parcel.
6. The method of claim 1 , further comprising sending signals wirelessly to one or more of the vehicles of the fleet to require that the one or more of the vehicles operate only according to the next driving mode.
7. The method of claim 1 , wherein determining the next driving mode transition comprises validating a license to manually drive a vehicle of the fleet.
8. The method of claim 1 , wherein determining the next driving mode transition comprises evaluating a driving environment of a vehicle of the fleet.
9. The method of claim 1 , wherein determining the next driving mode transition comprises evaluating if one or more autonomous driving capabilities is disabled or enabled in a vehicle of the fleet.
10. The method of claim 1 , wherein determining the next driving mode transition comprises evaluating a trajectory towards a goal position under the next driving mode.
11. The method of claim 1 , wherein determining the next driving mode comprises evaluating authentication of the one or more occupants under the next driving mode.
12. The method of claim 1 , wherein determining the next driving mode transition comprises inferring one or more intermediate driving modes between the current driving mode and the next driving mode.
13. The method of claim 1 , wherein determining the next driving mode transition comprises using a probabilistic model to optimally determine the next driving mode.
14. The method of claim 1 , wherein the determined next driving mode transition is rejected when the next driving mode is infeasible or unsafe.
15. The method of claim 1 , further comprising receiving instructions of determining the next driving mode transition from a fleet operator.
16. The method of claim 1 , wherein determining the driving mode transition for the at least one vehicle from the current driving mode to the next driving mode comprises inferring one or more intermediate driving modes between the current driving mode and the next driving mode.
17. An apparatus comprising:
one or more processors; and
a memory storage in data communication with the one or more processors, the memory storage storing instructions executable by the one or more processors and that upon such execution cause the one or more processors to perform operations of:
receiving sensor information from one or more sensors from each vehicle in a fleet of vehicles, each vehicle comprising an autonomous driving capability, wherein the sensor information indicates a state of occupancy indicating that the vehicle is occupied;
determining, at a server and based on the state of occupancy and a collision risk to at least one vehicle in the fleet of vehicles or objects surrounding the at least one vehicle, a next driving mode transition from a current driving mode, a next driving mode comprising at least one of an autonomous driving mode, a manual driving mode, and a driving mode that uses a combination of autonomous driving capabilities and manual driving capabilities, wherein determining the next driving mode transition includes determining, based on the state of occupancy of the at least one vehicle, a threshold of driving smoothness for the next driving mode transition for the at least one vehicle;
gradually adjusting a change in speed of the at least one vehicle during the driving mode transition from the current driving mode to the next driving mode in accordance with the threshold of driving smoothness; and
sending signals wirelessly to the at least one vehicle of the fleet identifying, based on the determined next driving mode transition and the determined smoothing operation, the next driving mode for the at least one vehicle.
18. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations of:
receiving sensor information from one or more sensors from each vehicle in a fleet of vehicles, each vehicle comprising an autonomous driving capability, wherein the sensor information indicates a state of occupancy of the vehicle indicating that the vehicle is occupied;
determining, at a server and based on the received sensor information, the state of occupancy and a collision risk to at least one vehicle in the fleet of vehicles or objects surrounding the at least one vehicle, a next driving mode transition from a current driving mode, a next driving mode comprising at least one or an autonomous driving mode, a manual driving mode, and a driving mode that uses a combination of autonomous driving capabilities and manual driving capabilities, wherein determining the next driving mode transition includes determining, based on the state of occupancy of the at least one vehicle, a threshold of driving smoothness for the next driving mode transition for the at least one vehicle;
gradually adjusting a change in speed of the at least one vehicle during the driving mode transition from the current driving mode to the next driving mode in accordance with the threshold of driving smoothness; and
sending signals wirelessly to the at least one vehicle of the fleet identifying, based on the determined next driving mode transition and the determined smoothing operation, the next driving mode for the at least one vehicle.
19. The method of claim 1 , wherein determining the next driving mode transition further includes determining, based on the received sensor information, the state of occupancy of the vehicle; and wherein a change of speed of a smoothing operation for a first vehicle is lower when a state of occupancy for the first vehicle is at one or more occupants than a change of speed of a smoothing operation for a second vehicle when a state of occupancy for the second vehicle is zero occupants.
20. The apparatus of claim 17 , wherein determining the next driving mode transition further includes determining, based on the received sensor information, the state of occupancy of the vehicle; and wherein a change of speed of a smoothing operation for a first vehicle is lower when a state of occupancy for the first vehicle is at one or more occupants than a change of speed of a smoothing operation for a second vehicle when a state of occupancy for the second vehicle is zero occupants.
21. The non-transitory computer storage medium of claim 18 , wherein determining the next driving mode transition further includes determining, based on the received sensor information, the state of occupancy of the vehicle; and wherein a change of speed of a smoothing operation for a first vehicle is lower when a state of occupancy for the first vehicle is at one or more occupants than a change of speed of a smoothing operation for a second vehicle when a state of occupancy for the second vehicle is zero occupants.