Systems and methods for traction detection and control in a self-driving vehicle
Methods and systems are provided for traction detection and control of a self-driving vehicle. The self-driving vehicle has drive motors that drive drive-wheels according to a drive-motor speed. Traction detection and control can be obtained by measuring the vehicle speed with a sensor such as a LiDAR or video camera, and measuring the wheel speed of the drive wheels with a sensor such as a rotary encoder. The difference between the measured vehicle speed and the measured wheel speeds can be used to determine if a loss of traction has occurred in any of the wheels. If a loss of traction is detected, then a recovery strategy can be selected from a list of recovery strategies in order to reduce the effects of the loss of traction.
1. A vehicle comprising:
at least one wheel for moving the vehicle;
at least one drive motor for driving the at least one wheel; and
a processor in communication with the at least one drive motor, the processor configured to:
control the at least one drive motor to move the vehicle along a path within an environment;
determine that, at a pre-determined time in the future, the vehicle will experience a condition associated with traction loss along the path;
evaluate the condition to determine a nature of the traction loss for the vehicle;
based on the nature of the traction loss and the vehicle:
determine one or more priorities for minimizing traction loss at the pre-determined time; and
select at least one traction-control strategy to address the one or more priorities from one or more traction-control strategies, wherein each traction-control strategy is assigned a score generated based on one or more previous applications of that traction-control strategy for the nature of the traction loss and the vehicle; and
at the pre-determined time:
implement a corrective action in accordance with the at least one traction-control strategy,
continue to evaluate a result of the corrective action; and
in response to determining the corrective action is ineffective, continue to determine a current priority for minimizing traction loss and to select a current traction-control strategy to address the current priority.
2. The vehicle of claim 1 , wherein:
the condition is associated with a location along the path; and
determining that the vehicle will experience the condition comprises determining, that at the pre-determined time, the vehicle is expected to navigate through the location.
3. The vehicle of claim 2 , wherein the vehicle further comprises at least one memory coupled to the processor, the at least one memory storing a map of the environment, the map including information about the location and the associated condition, and determining the location and condition is based on the information included in the map.
4. The vehicle of claim 3 , wherein the information in the map is based on previous traction-loss events experienced by other vehicles at the location.
5. The vehicle of claim 2 , wherein the vehicle comprises one or more sensors, and the processor is configured to identify the condition at the location based on sensor data received from the one or more sensors.
6. The vehicle of claim 5 , wherein the processor is configured to:
receive, from the one or more sensor, sensor data associated with the location;
compare the sensor data to pre-stored sensor data associated with a known condition causing traction loss;
determine a match between the sensor data and the pre-stored sensor data; and
in response to determining the match, determine that the location is associated with the condition causing traction loss.
7. The vehicle of claim 2 , wherein the processor is further configured to generate a notification about the condition and the location to allow a human operator to rectify the condition at the location.
8. The vehicle of claim 2 , wherein the processor is further configured to determine a new path that avoids the location.
9. The vehicle of claim 1 , wherein the pre-determined time in the future corresponds to a time of day when the condition is expected to occur.
10. The vehicle of claim 1 , wherein the score associated with the one or more traction-control strategies is further based on an estimate of how the condition would affect the vehicle.
11. A method for traction detection and control of a vehicle comprising:
controlling, via a processor, at least one drive motor of the vehicle to move the vehicle along a path within an environment, the at least one drive motor being configured to drive at least one wheel of the vehicle;
determining, by the processor, that at a pre-determined time in the future, the vehicle will experience a condition associated with traction loss along the path;
evaluating, by the processor, the condition to determine a nature of the traction loss for the vehicle;
based on the nature of the traction loss and the vehicle:
determining, by the processor, one or more priorities for minimizing traction loss at the pre-determined time; and
selecting, by the processor, at least one traction-control strategy to address the one or more priorities from one or more traction-control strategies, wherein each traction-control strategy is assigned a score generated based on one or more previous applications of that traction-control strategy for the nature of the traction loss and the vehicle; and
at the pre-determined time:
implementing, by the processor, a corrective action in accordance with the at least one traction-control strategy;
continue to evaluate a result of the corrective action; and
in response to determining the corrective action is ineffective, continuing to determine a current priority for minimizing traction loss and to select a current traction-control strategy to address the current priority.
12. The method of claim 11 , wherein:
the condition is associated with a location along the path; and
determining that the vehicle will experience the condition comprises determining, by the processor, that at the pre-determined time, the vehicle is expected to navigate through the location.
13. The method of claim 12 , further comprising:
accessing, by the processor, a map of the environment, the map being stored on at least one memory of the vehicle coupled to the processor, wherein the map includes information about the location and the associated condition, and
determining, by the processor, the location and associated condition based on the information included in the map.
14. The method of claim 13 , wherein the information in the map is based on previous traction-loss events experienced by other vehicles at the location.
15. The method of claim 12 , wherein:
the vehicle comprises one or more sensors, and
the method further comprises identifying, by the processor, the condition at the location based on sensor data received from the one or more sensors.
16. The method of claim 15 , further comprising
receiving, by the processor from the one or more sensor, sensor data associated with the location;
comparing, by the processor, the sensor data to pre-stored sensor data associated with a known condition causing traction loss;
determining, by the processor, a match between the sensor data and the pre-stored sensor data; and
in response to determining the match, determining, by the processor, that the location is associated the condition causing traction loss.
17. The method of claim 12 , further comprising generating, by the processor, a notification about the condition and the location to allow a human operator to rectify the condition at the location.
18. The method of claim 12 , further comprising determining, by the processor, a new path that avoids the location.
19. The method of claim 11 , wherein the pre-determined time in the future corresponds to a time of day when the condition is expected to occur.
20. The method of claim 11 , wherein the score associated with the one or more traction-control strategies is further based on an estimate of how the condition would affect the vehicle.