Method for determining an optimal location to wait for a left turn to minimize traffic impact
A system, a method and a computer program product are provided to determine a left turn decision for a user or autonomous vehicle attempting to turn at an intersection of a road. For example, the system obtains contextual features and/or sensor data related to the intersection of the road. An optimal location on the road is determined for the user or autonomous vehicle to position the vehicle to make the left turn decision, based on the contextual features and/or the sensor data. A left turn risk factor is determined based on the location on the road for the user or autonomous vehicle to position the vehicle to make a left turn. An alert is presented to the user or autonomous vehicle regarding the left turn risk factor with a left turn advisory message.
1 . A system to determine a left turn decision for a user driving a vehicle attempting to turn at an intersection of a road, the system comprising:
at least one memory configured to store computer executable instructions; and
at least one processor configured to execute the computer executable instructions to:
obtain a plurality of contextual features and a plurality of sensor data related to the intersection of the road, wherein the plurality of contextual features and the plurality of sensor data related to the intersection of the road includes vehicle dimensions of a user's vehicle and one or more dimensions of one or more vehicles proximate to the intersection;
determine a location on the road for the user to position the vehicle to make the left turn decision, based on the plurality of contextual features and the plurality of sensor data, wherein the location provides a predetermined spatial clearance around the user's vehicle sufficient for the one or more vehicles proximate to the intersection to pass the user's vehicle while the user waits to perform a left turn;
determine a left turn risk factor for the location on the road for the user to position the vehicle using a trained machine learning model to determine the location on the road and the left turn risk factor; and
alert the user to the left turn risk factor with a left turn advisory message, where the left turn advisory message comprises an estimated wait time at the location on the road before a left turn is possible, where the estimated wait time is based on the left turn risk factor.
2 . The system of claim 1 , where the computer executable instructions to alert the user to the left turn risk factor with the left turn advisory message comprise computer executable instructions to re-route the user, if the left turn risk factor exceeds a risk threshold, to a different intersection.
3 . The system of claim 1 , where the computer executable instructions to determine a location on the road further comprises the computer executable instructions to instruct the user of the location on the road with an audible alert, a visual alert, a vehicle console display alert, an augmented reality-based alert, a heads-up display alert, a haptic alert or a combination thereof.
4 . The system of claim 1 , where the plurality of contextual features comprise one or more road dimensions, one or more intersection locations, one or more traffic signs along the road, one or more traffic lights near the intersection, street infrastructure near the intersection, lane demarcations on the road, one or more road crossing demarcations near the intersection, construction and roadwork information, a size of the vehicle, a size of a different vehicle near the vehicle, spatial dimensions available around the vehicle for the different vehicle to pass the vehicle, historical accident information near the intersection, satellite communications data, radio-frequency communications data, nearby unmanned autonomous vehicle information, weather data, driver preference information, map database information, online service information or a combination thereof.
5 . The system of claim 1 , where the plurality of sensor data comprises proximity sensor data, motion detection sensor data, accelerometer data, weather sensor data, positioning sensor data, external remote sensor data or a combination thereof.
6 . The system of claim 1 , where the computer executable instructions to use the trained machine learning model comprises computer executable instructions to use a transfer learning model based on a plurality of prior contextual features.
7 . A method for determining a left turn decision for a vehicle attempting to turn at an intersection of a road, the method comprising:
obtaining a plurality of contextual features and a plurality of sensor data related to the intersection of the road, wherein the plurality of contextual features and the plurality of sensor data related to the intersection of the road includes vehicle dimensions of a user's vehicle and one or more dimensions of one or more vehicles proximate to the intersection;
determining a location on the road for the vehicle to make the left turn decision, based on the plurality of contextual features and the plurality of sensor data, wherein the location provides a predetermined spatial clearance around the user's vehicle sufficient for the one or more vehicles proximate to the intersection to pass the user's vehicle while the user waits to perform a left turn;
determining a left turn risk factor for the location on the road for the user to position the vehicle using a trained machine learning model to determine the location on the road and the left turn risk factor; and
notifying the vehicle to the left turn risk factor with a left turn advisory message, where the left turn advisory message comprises an estimated wait time at the location on the road before a left turn is possible, where the estimated wait time is based on the left turn risk factor.
8 . The method of claim 7 , where alerting the vehicle to the left turn risk factor with the left turn advisory message comprises re-routing the vehicle, if the left turn risk factor exceeds a risk threshold, to a different intersection.
9 . The method of claim 7 , where determining the location on the road further comprises instructing the vehicle of the location on the road with an audible alert, a visual alert, a vehicle console display alert, an augmented reality-based alert, a heads-up display alert, a haptic alert or a combination thereof.
10 . The method of claim 7 , where the plurality of contextual features comprise one or more road dimensions, one or more intersection locations, one or more traffic signs along the road, one or more traffic lights near the intersection, street infrastructure near the intersection, lane demarcations on the road, one or more road crossing demarcations near the intersection, construction and roadwork information, a size of the vehicle, a size of a different vehicle near the vehicle, spatial dimensions available around the vehicle for the different vehicle to pass the vehicle, historical accident information near the intersection, satellite communications data, radio-frequency communications data, nearby unmanned autonomous vehicle information, weather data, driver preference information, map database information, online service information or a combination thereof.
11 . The method of claim 7 , where the plurality of sensor data comprises proximity sensor data, motion detection sensor data, accelerometer data, weather sensor data, positioning sensor data, external remote sensor data or a combination thereof.
12 . The method of claim 7 , where determining the location on the road comprises determining a location on the road to prevent a collision with a passing vehicle.
13 . A computer program product comprising a non-transitory computer readable medium having stored thereon computer executable instructions, which when executed by one or more processors, cause the one or more processors to carry out operations to determine a left turn decision for a user driving a vehicle attempting to turn at an intersection of a road, the operations comprising:
obtaining a plurality of contextual features and a plurality of sensor data related to the intersection of the road, wherein the plurality of contextual features and the plurality of sensor data related to the intersection of the road includes vehicle dimensions of a user's vehicle and one or more dimensions of one or more vehicles proximate to the intersection;
determining a location on the road for the user to position the vehicle to make the left turn decision, based on the plurality of contextual features and/or the plurality of sensor data, wherein the location provides a predetermined spatial clearance around the user's vehicle sufficient for the one or more vehicles proximate to the intersection to pass the user's vehicle while the user waits to perform a left turn;
determining a left turn risk factor for the location on the road for the user to position the vehicle using a trained machine learning model to determine the location on the road and the left turn risk factor; and
alerting the user to the left turn risk factor with a left turn advisory message, where the left turn advisory message comprises an estimated wait time at the location on the road before a left turn is possible, where the estimated wait time is based on the left turn risk factor.
14 . The computer program product of claim 13 , where determining the location on the road further comprises instructing the user of the location on the road with an audible alert, a visual alert, a vehicle console display alert, an augmented reality-based alert, a heads-up display alert, a haptic alert or a combination thereof.
15 . The computer program product of claim 13 , where the plurality of contextual features comprise one or more road dimensions, one or more intersection locations, one or more traffic signs along the road, one or more traffic lights near the intersection, street infrastructure near the intersection, lane demarcations on the road, one or more road crossing demarcations near the intersection, construction and roadwork information, a size of the vehicle, a size of a different vehicle near the vehicle, spatial dimensions available around the vehicle for the different vehicle to pass the vehicle, historical accident information near the intersection, satellite communications data, radio-frequency communications data, nearby unmanned autonomous vehicle information, weather data, driver preference information, map database information, online service information or a combination thereof.
16 . The computer program product of claim 13 , where the plurality of sensor data comprises proximity sensor data, motion detection sensor data, accelerometer data, weather sensor data, positioning sensor data, external remote sensor data or a combination thereof.