Tracking for traffic lights
View Patent ↗The present invention relates to method and system for controlling speed of vehicle by using GPS location, real-time traffic light status and machine learning techniques to recommend cruising speed to vehicle without stopping at the traffic lights. The method includes determining status of traffic lights located on route of traffic junctions and associated time period for status of traffic lights based on data received from sensors. The method includes broadcasting status of traffic lights and associated time period. The method includes calculating in real-time a recommended cruising speed of the vehicle based on GPS location associated with vehicle, status of traffic lights and associated time period, and a time period required by vehicle to arrive at the traffic lights using machine learning techniques. The method includes providing in real-time the recommended cruising speed to vehicle. The method includes adaptively controlling in real-time speed of vehicle to recommended cruising speed.
1 . A method for controlling speed of a vehicle, the method comprising:
receiving, by a processor, a GPS location associated with the vehicle, wherein the GPS location is determined using an electronic device disposed within the vehicle;
determining, by the processor, a status of at least one traffic light located on at least one traffic junctions and associated time period for the status of the at least one traffic lights based on data received from a plurality of sensors;
calculating in real-time, by the processor, a recommended cruising speed of the vehicle based on the GPS location associated with the vehicle, the status of at least one traffic light and associated time period, and a time period required by the vehicle to arrive at the at least one traffic lights using a machine learning algorithm;
providing in real-time, by the processor, the recommended cruising speed to the vehicle; and
adaptively controlling the vehicle to the recommended cruising speed by utilizing at least one control technique selected from the set of control techniques consisting of: accelerating the vehicle from a current vehicle speed to the recommended cruising speed by increasing a throttle of the vehicle; and, decelerating the vehicle from the current vehicle speed to the recommended cruising speed by application of braking.
2 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the GPS location associated with the vehicle is transmitted to the central server.
3 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the calculation of the cruising speed of the vehicle is based on a traffic density associated with the GPS location of the vehicle.
4 . The method for controlling speed and braking of the vehicle as claimed in claim 1 , wherein the calculation of the recommended cruising speed of the vehicle is based on at least one external variable selected form the set of external variables consisting of: general traffic congestion, external variables including emergency vehicles on the route, accidents along the route, weather conditions on the route, and stalled vehicles on the route.
5 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the recommended cruising speed of the vehicle enables traversing the route without stopping at any of the at least one traffic light.
6 . The method for controlling speed of the vehicle as in claim 5 wherein the central server uses a machine language algorithm to determine the speed.
7 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the recommended cruising speed is calculated by the central server and provided to the vehicle.
8 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein providing the recommended cruising speed to the vehicle comprises at least one notification selected from the set of notifications consisting of: displaying the recommended cruising speed on an instrument cluster of the vehicle; and generating an audio alert to communicate the recommended cruising speed to a rider of the vehicle.
9 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein at least one operation is performed on the data received from the plurality of sensors, wherein the at least one operation is selected from the set of operations consisting of: pre-processing operations, correlating the data from the plurality of sensors and from the central server, and verifying in real-time the data.
10 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the plurality of sensors comprises at least one sensor selected from the set of sensors consisting of: an image sensor, a LIDAR sensor, and a RADAR sensor.
11 . The method for controlling speed of the vehicle as claimed in claim 1 , further comprising:
determining a count of the at least one traffic light located on route of the vehicle based on the data from plurality of sensors; and
calculating an estimated time to reach each of the at least one traffic light based on weather conditions, accident conditions, and at least one obstacle on the route using the machine learning model.
12 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the at least one traffic light is configured to change the status dynamically based on the traffic density at a particular traffic junction.
13 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the machine learning model is configured to:
assign weights to each of the datapoints in the data from the plurality of sensors and validate each of the datapoints by cross referencing with the data from the central server;
compute a validity score for each datapoints in the data from the plurality of sensos;
eliminate at least one data point associated with a validity score being less than a pre-defined value;
replacing the eliminated values with the data points obtained from the central server to eliminate inaccurate data.
14 . The method for controlling speed of the vehicle as claimed in claim 1 , wherein the machine learning model is trained using a feedback loop using at least one of a supervised learning mechanism, a semi-supervised learning mechanism or an unsupervised learning mechanism.
15 . The method for controlling speed of the vehicle as claimed in claim 1 , further comprising receiving an input from the rider of the vehicle to select at least one traffic light that the vehicle is approaching for obtaining the status of the selected at least one traffic light.
16 . An electronic device to control speed of the vehicle, the electronic device comprising:
a hardware processor; and
a memory communicatively coupled to the hardware processor, wherein the memory stores processor instructions, which, on execution, causes the hardware processor to:
receive a GPS location associated with the vehicle, wherein the GPS location is determined using an electronic device disposed within the vehicle;
determine a status of at least one traffic light located on at least one traffic junction and associated time period for the status of the at least one traffic light based on data received from a plurality of sensors;
calculate in real-time a recommended cruising speed of the vehicle based on the GPS location associated with the vehicle, the status of at least one traffic light and associated time period, and a time period required by the vehicle to arrive at the at least one traffic light using a machine learning algorithm;
provide in real-time the recommended cruising speed to the vehicle; and
adaptively control in real-time the speed of the vehicle to the recommended cruising speed, said adaptive control being based on at least one quantum of date selected from the set of quanta consisting of: a riding mode of the vehicle, traction control status of the vehicle, and ABS inputs from a braking system of the vehicle.
17 . A non-transitory computer readable medium including instruction stored thereon that when processed by at least one hardware processor cause an electronic device to perform an operation comprising:
receiving a GPS location associated with the vehicle, wherein the GPS location is determined using an electronic device disposed within the vehicle;
determining a status of at least one traffic light located on at least one traffic junction and associated time period for the status of the at least one traffic light based on data received from a plurality of sensors;
calculating in real-time a recommended cruising speed of the vehicle based on the GPS location associated with the vehicle, the status of at least one traffic light and associated time period, and a time period required by the vehicle to arrive at the at least one traffic light using a machine learning algorithm;
providing in real-time the recommended cruising speed to the vehicle; and
adaptively controlling in real-time the speed of the vehicle to the recommended cruising speed, said adaptive controlling being based on at least one quantum of date selected from the set of quanta consisting of: a riding mode of the vehicle, traction control status of the vehicle, and ABS inputs from a braking system of the vehicle.