SYSTEM AND METHOD FOR USING V2X AND SENSOR DATA
A method and system for traffic control includes receiving at a processing unit sensor data of a site on a road network and receiving at the processing unit a V2X communication. Locations of road users are calculated from the sensor data and the V2X communication enabling the detection of connected and non-connected road users. Once connected and non-connected road users are detected at a site, this information can be used to control traffic.
1 . A method of controlling traffic at a site of a road network, the method comprising, by a processing unit:
receiving sensor data informative of road users in a vicinity of the site and processing the sensor data to detect sensor data-based (SD) road users and to associate the detected SD road users with SD user parameters, wherein said SD user parameters comprise SD locations respectively associated with SD users;
receiving V2X communications comprising V2X data informative of connected road users and processing the V2X data to obtain V2X data-based (VD) parameters of connected road users characterized by respective VD parameters, wherein said VD parameters comprise VD locations respectively associated with the connected users;
matching SD and VD locations to identify, among the SD road users detected in the vicinity of the site, a plurality of connected road users characterized by matched, at least, SD and VD locations and a plurality of non-connected road users characterized by SD locations without VD locations matching thereto;
calculating an adoption rate of V2X technology, the adoption rate being indicative of a portion of the connected road users among road users, wherein calculating the adoption rate comprises:
calculating a total number of SD road users detected during a given period in the vicinity of the site and a number of connected road users detected during the given period in the vicinity of the site at the site; and
calculating the adoption rate of V2X technology by comparing the total number of the detected SD road users and the number of connected road therein.
2 . The method of claim 1 , wherein SD parameters and VD parameters further comprise at least one of speed, acceleration, bearing, classification, past trajectory and predicted trajectory; and wherein the connected users are characterized by matching between SD and VD locations and between at least one other pair of corresponding SD and VD parameters.
3 . The method of claim 1 , further comprising using the adoption rate calculated over time to train a machine learning model configured to predict a number of road users in the vicinity of the site at a certain time.
4 . The method of claim 3 , wherein the machine learning model is configured to predict the number of road users based on at least one of: time of day, detected amount of connected road users and detected amount of SD road users.
5 . The method of claim 3 , further comprising refining the machine learning model in accordance with a prediction error indicative of a difference between the predicted number of road users and the actual number of detected SD road users.
6 . The method of claim 3 , further comprising using the predicted number of road users to generate a signal to control a road network infrastructure.
7 . The method of claim 3 , wherein the machine learning model is configured to predict a number of road users at a predetermined location in the vicinity of the site at a certain time.
8 . The method of claim 7 , wherein the predetermined location is out of a field-of-view of at least one sensor providing the received sensor data.
9 . The method of claim 7 , wherein the predetermined location is out of a field-of-view of all sensor providing the received sensor data.
10 . One or more computing devices comprising processors and memory, the one or more computing devices configured, via computer-executable instructions, to perform operations for operating, in a cloud computing environment, a system controlling traffic at a site of a road network, the system further configured to operate in accordance with a method comprising:
receiving sensor data informative of road users in a vicinity of the site and processing the sensor data to detect sensor data-based (SD) road users and to associate the detected SD road users with SD user parameters, wherein said SD user parameters comprise SD locations respectively associated with SD users;
receiving V2X communications comprising V2X data informative of connected road users and processing the V2X data to obtain V2X data-based (VD) parameters of connected road users characterized by respective VD parameters, wherein said VD parameters comprise VD locations respectively associated with the connected users;
matching SD and VD locations to identify, among the SD road users detected in the vicinity of the site, a plurality of connected road users characterized by matched, at least, SD and VD locations and a plurality of non-connected road users characterized by SD locations without VD locations matching thereto;
calculating an adoption rate of V2X technology, the adoption rate being indicative of a portion of the connected road users among road users, wherein calculating the adoption rate comprises:
calculating a total number of SD road users detected during a given period in the vicinity of the site and a number of connected road users detected during the given period in the vicinity of the site at the site; and
calculating the adoption rate of V2X technology by comparing the total number of the detected SD road users and the number of connected road therein.
11 . The one or more computing devices of claim 10 , wherein SD parameters and VD parameters further comprise at least one of speed, acceleration, bearing, classification, past trajectory and predicted trajectory; and wherein the connected users are characterized by matching between SD and VD locations and between at least one other pair of corresponding SD and VD parameters.
12 . The one or more computing devices of claim 10 , wherein the system is further configured to use the adoption rate calculated over time to train a machine learning model configured to predict a number of road users in the vicinity of the site at a certain time.
13 . The one or more computing devices of claim 12 , wherein the machine learning model is configured to predict the number of road users based on at least one of: time of day, detected amount of connected road users and detected amount of SD road users.
14 . The one or more computing devices of claim 12 , wherein the system is further configured to refine the machine learning model in accordance with a prediction error indicative of a difference between the predicted number of road users and the actual number of detected SD road users.
15 . The one or more computing devices of claim 12 , wherein the system is further configured to generate a signal to control a road network infrastructure in accordance with the predicted number of road users.
16 . The one or more computing devices of claim 12 , wherein the machine learning model is configured to predict a number of road users at a predetermined location in the vicinity of the site at a certain time.
17 . The method of claim 7 , wherein the predetermined location is out of a field-of-view of at least one sensor providing the received sensor data.
18 . The method of claim 7 , wherein the predetermined location is out of a field-of-view of all sensors providing the received sensor data.
19 . A non-transitory computer readable medium comprising instructions that, when executed by a processing unit, cause the processing unit to enable controlling a traffic at a site of a road network in accordance with a method comprising:
receiving sensor data informative of road users in a vicinity of the site and processing the sensor data to detect sensor data-based (SD) road users and to associate the detected SD road users with SD user parameters, wherein said SD user parameters comprise SD locations respectively associated with SD users;
receiving V2X communications comprising V2X data informative of connected road users and processing the V2X data to obtain V2X data-based (VD) parameters of connected road users characterized by respective VD parameters, wherein said VD parameters comprise VD locations respectively associated with the connected users;
matching SD and VD locations to identify, among the SD road users detected in the vicinity of the site, a plurality of connected road users characterized by matched, at least, SD and VD locations and a plurality of non-connected road users characterized by SD locations without VD locations matching thereto;
calculating an adoption rate of V2X technology, the adoption rate being indicative of a portion of the connected road users among road users, wherein calculating the adoption rate comprises:
calculating a total number of SD road users detected during a given period in the vicinity of the site and a number of connected road users detected during the given period in the vicinity of the site at the site; and
calculating the adoption rate of V2X technology by comparing the total number of the detected SD road users and the number of connected road therein.