Identifying bidirectional channelization zones and lane directionality

1 . A system comprising:

a memory; and

one or more processors coupled to the memory, the one or more processors being configured to:

detect, based on sensor data from one or more sensors of a vehicle, a temporary traffic lane on a road configured for use by traffic to navigate the road in lieu of one or more pre-existing traffic lanes on the road, wherein at least one boundary of the temporary traffic lane is defined by a plurality of objects on the road;

detect, based on the sensor data, one or more cues indicating a direction of travel through the temporary traffic lane based on:

a first indication of a direction of travel of a vehicle traveling through the temporary traffic lane or an adjacent temporary traffic lane,

a second indication of the direction of travel through the temporary traffic lane or a second direction of travel through the adjacent temporary traffic lane, provided by a human traffic controller in a scene associated with the road, and

a third indication of the direction of travel through the temporary traffic lane or the direction of travel through the adjacent temporary traffic lane, predicted based on one or more objects on the road,

wherein:

the one or more cues comprise a first cue associated with the first indication, a second cue associated with the second indication, and a third cue associated with the third indication,

the one or more objects on the road comprise a sign placed in the scene to direct traffic through at least one of the temporary traffic lane and the adjacent temporary traffic lane, and

in detecting the one or more cues, the one or more processors are configured to detect, based on image data in the sensor data, a visual cue in the sign;

assign respective weights to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication, wherein each respective weight among the respective weights is indicative of a confidence level of a reliability of a direction of travel determined from the cue associated with the respective weight;

recognize the visual cue as a visual indication of at least one of the direction of travel through the temporary traffic lane and the second direction of travel through the adjacent temporary traffic lane, wherein the direction of travel through the adjacent temporary traffic lane is different from the direction of travel through the temporary traffic lane; and

predict the direction of travel through the temporary traffic lane or the direction of travel through the adjacent temporary traffic lane based on;

combining direction of travel information respectively corresponding to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication; and

the respective weights assigned to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication.

2 . The system of claim 1 , wherein recognizing the visual cue as the visual indication of at least one of the direction of travel through the temporary traffic lane and the second direction of travel through the adjacent temporary traffic lane comprises recognizing the visual cue as the visual indication of the second direction of travel through the adjacent temporary traffic lane, wherein the one or more processors are further configured to:

determine a direction that is opposite to the second direction of travel through the adjacent temporary traffic lane; and

predict the direction of travel through the temporary traffic lane based on the direction that is opposite to the second direction of travel through the adjacent temporary traffic lane.

3 . The system of claim 1 , wherein the second indication of directionality provided by the human traffic controller comprises at least one of a gesture of the human traffic controller and a verbal instruction of the human traffic controller.

4 . The system of claim 3 , wherein the gesture of the human traffic controller comprises pointing in a particular direction in association with at least one of the temporary traffic lane and the adjacent temporary traffic lane, and wherein the one or more processors are further configured to:

recognize, based on image data in the sensor data, the gesture as pointing in the particular direction in association with at least one of the temporary traffic lane and the adjacent temporary traffic lane; and

predict the direction of travel through the temporary traffic lane based on the gesture of the human traffic controller pointing in the particular direction in association with at least one of the temporary traffic lane and the adjacent temporary traffic lane.

5 . The system of claim 3 , wherein the second indication of directionality provided by the human traffic controller comprises the verbal instruction, and wherein the one or more processors are further configured to:

based on recorded audio in the sensor data, recognize, using a speech recognition algorithm, the verbal instruction of the human traffic controller; and

predict the direction of travel through the temporary traffic lane based on the verbal instruction of the human traffic controller.

6 . The system of claim 1 , wherein the first indication of the direction of travel of the vehicle traveling through the temporary traffic lane or the adjacent temporary traffic lane indicates the direction of travel of the vehicle through the temporary traffic lane, and wherein predicting the direction of travel through the temporary traffic lane comprises predicting the direction of travel through the temporary traffic lane at least partly based on the direction of travel of the vehicle through the temporary traffic lane.

7 . The system of claim 1 , wherein the first indication of the direction of travel of the vehicle traveling through the temporary traffic lane or the adjacent temporary traffic lane indicates the direction of travel of the vehicle through the adjacent temporary traffic lane, and wherein predicting the direction of travel through the temporary traffic lane comprises:

determining a direction that is opposite to the direction of travel of the vehicle through the adjacent temporary traffic lane; and

predicting the direction of travel through the temporary traffic lane at least partly based on the direction that is opposite to the direction of travel of the vehicle through the adjacent temporary traffic lane.

8 . The system of claim 1 , wherein the one or more processors are configured to:

determine at least one of a position and an angle of a first set of objects from the one or more objects on the road, wherein the first set of objects are located at an end of the at least one boundary of the temporary traffic lane;

determine that vehicles traveling from a pre-existing traffic lane should merge onto the temporary traffic lane based on at least one of the position and the angle of the first set of objects from the one or more objects on the road; and

predict the direction of travel through the temporary traffic lane at least partly based the determination that vehicles traveling from the pre-existing traffic lane should merge onto the temporary traffic lane, wherein the direction of travel through the temporary traffic lane matches a particular direction of travel associated with the pre-existing traffic lane.

9 . The system of claim 1 ,

wherein the sensor data comprises at least one of data from a light detection and ranging sensor, data from a radio detection and ranging sensor, image data from a camera sensor, data from a time-of-flight sensor, data from an infrared sensor, and data from an acoustic sensor.

10 . A method comprising:

detecting, based on sensor data from one or more sensors of a vehicle, a temporary traffic lane on a road configured for use by traffic to navigate the road in lieu of one or more preexisting traffic lanes on the road, wherein at least one boundary of the temporary traffic lane is defined by a plurality of objects placed on the road;

detecting, based on the sensor data, one or more cues indicating a direction of travel through the temporary traffic lane based on:

a first indication of a direction of travel of a vehicle traveling through the temporary traffic lane or an adjacent temporary traffic lane,

a second indication of the direction of travel through the temporary traffic lane or a second direction of travel through the adjacent temporary traffic lane, provided by a human traffic controller in a scene associated with the road, and

a third indication of the direction of travel through the temporary traffic lane or the second direction of travel through the adjacent temporary traffic lane, predicted based on one or more objects on the road,

wherein:

the one or more cues comprise a first cue associated with the first indication, a second cue associated with the second indication, and a third cue associated with the third indication,

the one or more objects comprise a sign placed in the scene to direct traffic through at least one of the temporary traffic lane and the adjacent temporary traffic lane, and

detecting the one or more cues comprises detecting, based on image data in the sensor data, a visual cue in the sign;

assigning respective weights to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication, wherein each respective weight among the respective weights is indicative of a confidence level of a reliability of a direction of travel determined from the cue associated with the respective weight;

recognizing the visual cue as a visual indication of at least one of the direction of travel through the temporary traffic lane and the second direction of travel through the adjacent temporary traffic lane, wherein the direction of travel through the adjacent temporary traffic lane is different from the second direction of travel through the temporary traffic lane; and

predicting, by a computer of the vehicle, the direction of travel through the temporary traffic lane or the second direction of travel through the adjacent temporary traffic lane based on:

combining direction of travel information respectively corresponding to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication; and

the respective weights assigned to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication.

11 . The method of claim 10 , wherein recognizing the visual cue as the visual indication of at least one of the direction of travel through the temporary traffic lane and the second direction of travel through the adjacent temporary traffic lane comprises recognizing the visual cue as the visual indication of the second direction of travel through the adjacent temporary traffic lane, wherein the method further comprises:

determining a direction that is opposite to the second direction of travel through the adjacent temporary traffic lane; and

predicting the second direction of travel through the temporary traffic lane based on the direction that is opposite to the second direction of travel through the adjacent temporary traffic lane.

12 . The method of claim 10 , wherein the second indication of directionality provided by the human traffic controller comprises at least one of a gesture of the human traffic controller and a verbal instruction of the human traffic controller.

13 . The method of claim 12 , wherein the gesture of the human traffic controller comprises pointing in a particular direction in association with at least one of the temporary traffic lane and the adjacent temporary traffic lane, and wherein the method further comprises:

recognizing, based on image data in the sensor data, the gesture as pointing in the particular direction in association with at least one of the temporary traffic lane and the adjacent temporary traffic lane; and

predicting the direction of travel through the temporary traffic lane based on the gesture of the human traffic controller pointing in the particular direction in association with at least one of the temporary traffic lane and the adjacent temporary traffic lane.

14 . The method of claim 12 , wherein the second indication of directionality provided by the human traffic controller comprises the verbal instruction, and wherein the method further comprises:

based on recorded audio in the sensor data, recognizing, using a speech recognition algorithm, the verbal instruction of the human traffic controller; and

predicting the direction of travel through the temporary traffic lane based on the verbal instruction of the human traffic controller.

15 . The method of claim 10 , wherein the first indication of the direction of travel of the vehicle traveling through the temporary traffic lane or the adjacent temporary traffic lane indicates the direction of travel of the vehicle through the temporary traffic lane, and wherein predicting the direction of travel through the temporary traffic lane comprises predicting the direction of travel through the temporary traffic lane at least partly based on the direction of travel of the vehicle through the temporary traffic lane.

16 . The method of claim 10 , further comprising:

determining at least one of a position and an angle of a first set of objects from the one or more objects on the road, wherein the first set of objects are located at an end of the at least one boundary of the temporary traffic lane;

determining that vehicles traveling from a pre-existing traffic lane should merge onto the temporary traffic lane based on at least one of the position and the angle of the first set of objects from the one or more objects on the road; and

predicting the direction of travel through the temporary traffic lane at least partly based the determination that vehicles traveling from the pre-existing traffic lane should merge onto the temporary traffic lane, wherein the direction of travel through the temporary traffic lane matches a particular direction of travel associated with the pre-existing traffic lane.

17 . The method of claim 10 ,

wherein the sensor data comprises at least one of data from a light detection and ranging sensor, data from a radio detection and ranging sensor, image data from a camera sensor, data from a time-of-flight sensor, data from an infrared sensor, and data from an acoustic sensor.

18 . A non-transitory computer-readable medium having stored thereon instructions which, when executed by one or more processors, cause the one or more processors to:

detect, based on sensor data from one or more sensors of a vehicle, a temporary traffic lane on a road configured for use by traffic to navigate the road in lieu of one or more preexisting traffic lanes on the road, wherein at least one boundary of the temporary traffic lane is defined by a plurality of objects placed on the road;

detect, based on the sensor data, one or more cues indicating a direction of travel through the temporary traffic lane based on:

a first indication of a direction of travel of a vehicle traveling through the temporary traffic lane or an adjacent temporary traffic lane,

a second indication of the direction of travel through the temporary traffic lane or a second direction of travel through the adjacent temporary traffic lane, provided by a human traffic controller in a scene associated with the road, and

a third indication of the direction of travel through the temporary traffic lane or the second direction of travel through the adjacent temporary traffic lane, predicted based on one or more objects on the road,

wherein:

the one or more cues comprise a first cue associated with the first indication, a second cue associated with the second indication, and a third cue associated with the third indication,

the one or more objects on the road comprise a sign placed in the scene to direct traffic through at least one of the temporary traffic lane and the adjacent temporary traffic lane, and

in detecting the one or more cues, the one or more processors detect, based on image data in the sensor data, a visual cue in the sign;

assign respective weights to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication, wherein each respective weight among the respective weights is indicative of a confidence level of a reliability of a direction of travel determined from the cue associated with the respective weight;

recognize the visual cue as a visual indication of at least one of the direction of travel through the temporary traffic lane and the second direction of travel through the adjacent temporary traffic lane, wherein the direction of travel through the adjacent temporary traffic lane is different from the second direction of travel through the temporary traffic lane; and

predict the direction of travel through the temporary traffic lane or the second direction of travel through the adjacent temporary traffic lane based on;

combining direction of travel information respectively corresponding to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication; and

the respective weights assigned to the first cue associated with the first indication, the second cue associated with the second indication, and the third cue associated with the third indication.