System and method for optimizing autonomous vehicle capabilities in route planning
Systems and methods described herein determine an optimal lane trajectory and route for an autonomous vehicle under changing road conditions and forecast autonomous car performance along a route. A road's profile is analyzed to determine a safe lateral lane position. In ice or snow, a vehicle may follow ruts made by previous vehicles, even if following such ruts does not place a vehicle in a lane's center. In warmer weather, a vehicle may drive outside the ruts to avoid risks of aquaplaning. Dynamic road conditions and AV support along a route are used to maximize AV use and to forecast AV performance. A vehicle control system calculates sensor limitations and uses these sensor limitations when calculating which route to select.
1. A method of navigating an autonomous vehicle having at least a first type of environment perception sensor, the method comprising:
receiving a plurality of sensor performance reports including a road segment identifier and sensor range data for the first type of environment perception sensor on the identified road segment;
for each of a plurality of road segments, using the received sensor performance reports to determine at least a first average sensor range for the first type of sensor;
selecting a route for the autonomous vehicle based at least in part on the first average sensor range for at least one road segment on the route; and
causing the autonomous vehicle to follow the selected route.
2. The method of claim 1 , wherein selecting a route comprises:
identifying at least two alternate routes to a destination, wherein each route includes a plurality of road segments;
selecting a route from among the alternate routes based at least in part on the first average sensor range for the road segments included in the alternate routes.
3. The method of claim 1 , wherein causing the autonomous vehicle to follow the selected route comprises transmitting information identifying the selected route to the autonomous vehicle.
4. The method of claim 1 , wherein causing the autonomous vehicle to follow the selected route comprises driving the autonomous vehicle along the selected route.
5. The method of claim 1 , wherein the first type of environment perception sensor is a RADAR sensor.
6. The method of claim 1 , wherein the first type of environment perception sensor is a LIDAR sensor.
7. The method of claim 1 , wherein the sensor performance reports further comprise sensor range data of at least a second type of environment perception sensor on the identified road segment, the method further comprising:
for each of a plurality of road segments, using the received sensor performance reports to determine a second average sensor range for the second type of sensor;
wherein selection of the route is further based at least in part on the second average sensor range for at least one road segment on the route only if the autonomous vehicle has the second type of environment perception sensor.
8. The method of claim 1 , further comprising receiving a plurality of autonomous function reports including a road segment identifier and information regarding the availability of at least one autonomous function on the identified road segment;
wherein selection of the route is further based at least in part on the availability of the at least one autonomous function for at least one road segment on the route.
9. The method of claim 8 , wherein the autonomous function comprises a function selected from the group consisting of: intersection assistance, lane keeping, traffic jam assistance, highway pilot, and lane change assistance.
10. The method of claim 8 , wherein the information regarding the availability of the autonomous function comprises a percentage of the identified road segment over which the autonomous function is available.
11. The method of claim 1 , further comprising:
receiving information regarding weather conditions at a road segment; and
generating a prediction of expected sensor performance of at least the first type of environment perception sensor on the road segment;
wherein the selection of the route is based at least in part on the prediction of expected sensor performance.
12. The method of claim 1 , further comprising:
receiving at least one report regarding presence of a rut at a lateral position on a road segment on the selected route;
wherein selection of the route comprises selecting a lane trajectory of the autonomous vehicle based at least in part on the lateral position of the rut.
13. The method of claim 1 , further comprising:
receiving at least one report regarding disruption of an environment perception sensor at a lateral position on a road segment on the selected route;
wherein selection of the route comprises selecting a lane trajectory of the autonomous vehicle based at least in part on the lateral position associated with disruption of the environment perception sensor.
14. A system for navigating an autonomous vehicle having at least a first type of environment perception sensor, the system comprising at least one processor and a non-transitory computer-readable storage medium storing instructions operative when executed on the processor to perform functions comprising:
receiving a plurality of sensor performance reports including a road segment identifier and sensor range data of the first type of environment perception sensor on the identified road segment;
for each of a plurality of road segments, using the received sensor performance reports to determine at least a first average sensor range for the first type of sensor;
selecting a route for the autonomous vehicle based at least in part on the first average sensor range for at least one road segment on the route; and
causing the autonomous vehicle to follow the selected route.
15. The system of claim 14 , wherein selecting a route comprises:
identifying at least two alternate routes to a destination, wherein each route includes a plurality of road segments;
selecting a route from among the alternate routes based at least in part on the first average sensor range for the road segments included in the alternate routes.