Obstacle detection based on other vehicle behavior
The disclosed technology provides solutions for vehicle routing and in particular, for facilitating obstacle avoidance maneuvering by an autonomous vehicle (AV). In some implementations, a process of the disclosed technology can include steps for collecting environmental data about an environment around an autonomous vehicle, wherein the environmental data comprises data pertaining to a roadway navigated by the autonomous vehicle and one or more other vehicles navigating the roadway, processing the environmental data to generate an area grid comprising one or more grid sections, wherein each grid section corresponds with a different area of the roadway, and determining a risk-profile for the one or more grid sections based on the environmental data. Systems and machine-readable media are also provided.
1. An autonomous vehicle, comprising:
one or more environmental sensors;
at least one memory; and
at least one processor coupled to the at least one memory and the one or more environmental sensors, the at least one processor configured to:
collect environmental data, via the environmental sensors, about an environment around the autonomous vehicle, wherein the environmental data comprises data pertaining to a roadway navigated by the autonomous vehicle and one or more other vehicles navigating the roadway;
process the environmental data to generate an area grid comprising one or more grid sections, wherein each grid section corresponds with a different area of the roadway;
determine a risk-profile comprising a quantitative score for each of the one or more grid sections based on a behavior of the one or more other vehicles navigating the roadway and the environmental data wherein the quantitative score for each of the one or more grid sections is further based on a number of the one or more other vehicles observed avoiding the area of the roadway corresponding to each of the one or more grid sections and one or more conditions of the roadway;
determine a route for the autonomous vehicle to travel based on a comparison of the quantitative score for each of the one or more grid sections; and
navigate the autonomous vehicle along the determined route such that the autonomous vehicle traverses the one or more grid sections associated with a lower risk-profile score relative to the other grid sections.
2. The autonomous vehicle of claim 1 , wherein the at least one processor is further configured to:
resolve a route needed to avoid at least one of the one or more grid sections based on the associated risk-profile.
3. The autonomous vehicle of claim 1 , wherein the risk-profile for the one or more grid sections is based on avoidance behaviors associated with the one or more other vehicles navigating the roadway.
4. The autonomous vehicle of claim 1 , wherein the risk-profile for the one or more grid sections is based on one or more features associated with the one or more grid sections.
5. The autonomous vehicle of claim 4 , wherein the one or more features comprises: a pothole, standing water, debris, or a combination thereof.
6. The autonomous vehicle of claim 4 , wherein the one or more features comprises: a visibility score.
7. The autonomous vehicle of claim 1 , wherein the environmental data comprises Light Detection and Ranging (LiDAR) data, camera data, thermal camera data, radar data, or a combination thereof.
8. A computer-implemented method, comprising:
collecting environmental data, via one or more vehicle-mounted environmental sensors, about an environment around an autonomous vehicle, wherein the environmental data comprises data pertaining to a roadway navigated by the autonomous vehicle and one or more other vehicles navigating the roadway;
processing the environmental data to generate an area grid comprising one or more grid sections, wherein each grid section corresponds with a different area of the roadway;
determining a risk-profile comprising a quantitative score for each of the one or more grid sections based on a behavior of the one or more other vehicles navigating the roadway and the environmental data wherein the quantitative score for each of the one or more grid sections is further based on a number of the one or more other vehicles observed avoiding the area of the roadway corresponding to each of the one or more grid sections and one or more conditions of the roadway;
determining a route for the autonomous vehicle to travel based on a comparison of the quantitative score for each of the one or more grid sections; and
navigating the autonomous vehicle along the determined route such that the autonomous vehicle traverses the one or more grid sections associated with a lower risk-profile score relative to the other grid sections.
9. The computer-implemented method of claim 8 , further comprising:
resolving a route needed to avoid at least one of the one or more grid sections based on the associated risk-profile.
10. The computer-implemented method of claim 8 , wherein the risk-profile for the one or more grid sections is based on avoidance behaviors associated with the one or more other vehicles navigating the roadway.
11. The computer-implemented method of claim 8 , wherein the risk-profile for the one or more grid sections is based on one or more features associated with the one or more grid sections.
12. The computer-implemented method of claim 11 , wherein the one or more features comprises: a pothole, standing water, debris, or a combination thereof.
13. The computer-implemented method of claim 11 , wherein the one or more features comprises: a visibility score.
14. The computer-implemented method of claim 8 , wherein the environmental data comprises Light Detection and Ranging (LiDAR) data, camera data, thermal camera data, radar data, or a combination thereof.
15. A non-transitory computer-readable storage medium comprising at least one instruction for causing a computer or processor to:
collect environmental data about an environment around an autonomous vehicle, wherein the environmental data comprises sensor data pertaining to a roadway navigated by the autonomous vehicle and one or more other vehicles navigating the roadway;
process the environmental data to generate an area grid comprising one or more grid sections, wherein each grid section corresponds with a different area of the roadway;
determine a risk-profile comprising a quantitative score for each of the one or more grid sections based on a behavior of the one or more other vehicles navigating the roadway and the environmental data wherein the quantitative score for each of the one or more grid sections is further based on a number of the one or more other vehicles observed avoiding the area of the roadway corresponding to each of the one or more grid sections and one or more conditions of the roadway;
determine a route for the autonomous vehicle to travel based on a comparison of the quantitative score for each of the one or more grid sections; and
navigate the autonomous vehicle along the determined route such that the autonomous vehicle traverses the one or more grid sections associated with a lower risk-profile score relative to the other grid sections.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the at least one instruction is further configured to cause the processor to:
resolve a route needed to avoid at least one of the one or more grid sections based on the associated risk-profile.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the risk-profile for the one or more grid sections is based on avoidance behaviors associated with the one or more other vehicles navigating the roadway.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the risk-profile for the one or more grid sections is based on one or more features associated with the one or more grid sections.
19. The non-transitory computer-readable storage medium of claim 18 , wherein the one or more features comprises: a pothole, standing water, debris, or a combination thereof.
20. The non-transitory computer-readable storage medium of claim 18 , wherein the one or more features comprises: a visibility score.