System for mapping traffic lights and associated traffic light cycle times
AssigneeMobileye Vision Technologies Ltd.
InventorsDavid Huberman, Ouriel Barzilay
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for autonomous vehicle navigation. The systems and methods may map a lane mark, may map a directional arrow, selectively harvest road information based on data quality, map road segment free spaces, map traffic lights and determine traffic light relevancy, and map traffic lights and associated traffic light cycle times.
Claims26
A system for mapping traffic lights and associated traffic light cycle times for use in autonomous vehicle navigation, the system comprising at least one processor programmed to:
- receive, from a first vehicle, at least one location identifier associated with a traffic light detected along a road segment;
- receive, from the first vehicle, at least one indicator of traffic light state timing associated with the detected traffic light, wherein the at least one indicator of traffic light state timing is determined based on analysis of at least one image captured from an environment of the first vehicle, the analysis including application of at least one of a trained system or a computer vision algorithm;
- update an autonomous vehicle road navigation model relative to the road segment, wherein the update is based on the at least one location identifier and based on the at least one indicator of traffic light state timing associated with the traffic light detected along the road segment;
- and
- distribute the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles,
- wherein:
- the at least one processor is further programmed to determine whether the detected traffic light is sensor-operated,
- the determination of whether the detected traffic light is sensor-operated is based on the at least one indicator of traffic light state timing and based on navigational information, received from the first vehicle, indicative of one or more aspects of motion of the first vehicle along the road segment, and
- the determination of whether the detected traffic light is sensor-operated is based on information received from the first vehicle indicating a detection of a sensor structure associated with a road surface in a vicinity of the detected traffic light.
A method for mapping traffic lights and associated traffic light cycle times for use in autonomous vehicle navigation, the method comprising:
- receiving, from a first vehicle, at least one location identifier associated with a traffic light detected along a road segment;
- receiving, from the first vehicle, at least one indicator of traffic light state timing associated with the detected traffic light, wherein the at least one indicator of traffic light state timing is determined based on analysis of at least one image captured from an environment of the first vehicle, the analysis including application of at least one of a trained system or a computer vision algorithm;
- updating an autonomous vehicle road navigation model relative to the road segment, wherein the update is based on the at least one location identifier and based on the at least one indicator of traffic light state timing associated with the traffic light detected along the road segment;
- and
- distributing the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles,
- wherein:
- the method further comprises determining whether the detected traffic light is sensor-operated;
- and
- the determination of whether the detected traffic light is sensor-operated is based on:
- the at least one indicator of traffic light state timing,
- navigational information, received from the first vehicle, indicative of one or more aspects of motion of the first vehicle along the road segment, and
- information received from the first vehicle indicating a detection of a sensor structure associated with a road surface in a vicinity of the detected traffic light.
Dependencies are inferred from the claim text.