Systems and methods for road surface dependent motion planning
Systems and methods are directed to motion planning for an autonomous vehicle. In one example, a computer-implemented method for road surface dependent motion planning includes obtaining, by a computing system comprising one or more computing devices, surface friction data. The method further includes determining, by the computing system, one or more constraints for motion planning based at least in part on the surface friction data. The method further includes generating, by the computing system, a motion plan for an autonomous vehicle based at least in part on the one or more constraints.
1. A computer-implemented method for road surface dependent motion planning to control an autonomous vehicle, the method comprising:
obtaining a first set of predetermined constraints previously determined based at least in part on data indicating comfort limits for at least one rider in the autonomous vehicle, wherein the first set of predetermined constraints comprise a combination of a longitudinal force limit for acceleration and a lateral force limit for steering of the autonomous vehicle;
obtaining surface friction data associated with operation of the autonomous vehicle;
adjusting, based at least in part on the surface friction data, the first set of predetermined constraints to determine an updated combination of an updated longitudinal force limit for acceleration and an updated lateral force limit for steering of the autonomous vehicle;
generating a trajectory for the autonomous vehicle based at least in part on the updated combination of the updated longitudinal force limit for acceleration and the updated lateral force limit for steering of the autonomous vehicle; and
controlling the autonomous vehicle based at least in part on the trajectory.
2. The computer-implemented method of claim 1 , further comprising:
obtaining data indicating operating constraints of the autonomous vehicle, and
wherein the generating of the trajectory is based at least in part on the operating constraints of the autonomous vehicle.
3. The computer-implemented method of claim 2 , wherein the operating constraints include an expected transient acceleration of the autonomous vehicle over time.
4. The computer-implemented method of claim 1 , wherein the surface friction data is indicative of one or more estimates of road surface friction during operations of the autonomous vehicle, and wherein obtaining the surface friction data comprises:
obtaining sensor data associated with operation of the autonomous vehicle, wherein the sensor data is indicative of environmental conditions within the surrounding environment of the autonomous vehicle; and
generating the surface friction data indicative of the one or more estimates of road surface friction during operation of the autonomous vehicle based at least in part on the sensor data.
5. The computer-implemented method of claim 1 , further comprising providing data indicative of the trajectory to one or more vehicle control systems to control a movement for the autonomous vehicle.
6. An autonomous vehicle that comprises a vehicle computing system comprising:
one or more processors; and
one or more memories including instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, the operations comprising:
obtaining a first set of predetermined constraints previously determined based at least in part on data indicating comfort limits for at least one rider in the autonomous vehicle, wherein the first set of predetermined constraints comprise a combination of a longitudinal force limit for acceleration and a lateral force limit for steering of the autonomous vehicle;
obtaining surface friction data associated with operation of the autonomous vehicle;
adjusting, based at least in part on the surface friction data, the first set of predetermined constraints to determine one or more updated constraints for motion planning for the autonomous vehicle, wherein the one or more updated constraints comprise an updated combination of an updated longitudinal force limit for acceleration and an updated lateral force limit for steering of the autonomous vehicle;
generating a trajectory for the autonomous vehicle based at least in part on the one or more updated constraints for motion planning; and
controlling the autonomous vehicle based at least in part on the trajectory.
7. The autonomous vehicle of claim 6 , the operations further comprising:
obtaining data indicating operating constraints of the autonomous vehicle, and
wherein the generating of the trajectory is based at least in part on the operating constraints of the autonomous vehicle.
8. The autonomous vehicle of claim 7 , wherein the operating constraints include an expected transient acceleration of the autonomous vehicle over time.
9. The autonomous vehicle of claim 6 , wherein the surface friction data is indicative of one or more estimates of road surface friction during operations of the autonomous vehicle, and wherein obtaining the surface friction data comprises:
obtaining sensor data associated with operation of the autonomous vehicle, wherein the sensor data is indicative of environmental conditions within the surrounding environment of the autonomous vehicle; and
generating the surface friction data indicative of more estimates of road surface friction during operation of the autonomous vehicle based at least in part on the sensor data.
10. The autonomous vehicle of claim 6 , the operations further comprising:
providing data indicative of the trajectory to one or more vehicle control systems to control a movement for the autonomous vehicle.
11. The autonomous vehicle of claim 6 , wherein the lateral force limit for steering of the autonomous vehicle is prioritized over the longitudinal force limit for acceleration of the autonomous vehicle when applying the updated constraints during the generating of the trajectory.
12. A computing system comprising:
one or more processors; and
one or more memories including instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, the operations comprising:
obtaining a first set of predetermined constraints previously determined based at least in part on data indicating comfort limits for at least one rider in an autonomous vehicle, wherein the first set of predetermined constraints comprise a combination of a longitudinal force limit for acceleration and a lateral force limit for steering of the autonomous vehicle;
obtaining surface friction data associated with operation of the autonomous vehicle;
adjusting based at least in part on the surface friction data, the first set of predetermined constraints to determine an updated combination of an updated longitudinal force limit for acceleration and an updated lateral force limit for steering of the autonomous vehicle
generating a trajectory for the autonomous vehicle based at least in part on the updated combination of the updated longitudinal force limit for acceleration and the updated lateral force limit for steering of the autonomous vehicle; and
controlling the autonomous vehicle based at least in part on the trajectory.
13. The computing system of claim 12 , the operations further comprising:
obtaining data indicating operating constraints of the autonomous vehicle, and
wherein the generating of the trajectory is based at least in part on the operating constraints of the autonomous vehicle.