Systems and methods for active road surface maintenance with cloud-based mobility digital twin
An active road surface maintenance system and method developed for connected vehicles with the aid of a mobility digital twin (MDT) framework. A method performed in a cloud-based digital space includes receiving data regarding a physical object from a physical space connected to a vehicle. The method also includes processing the data using machine learning to model road surface conditions, in which respective penalty values are assigned to corresponding road surfaces, a respective penalty value being higher the lower a condition of the corresponding road surface. The method also includes deriving instructions based on the modeled road surface conditions and the respective penalty values to guide actuation of the vehicle along a trajectory. The method further includes transmitting the instructions to the physical space connected to the vehicle to guide actuation of the vehicle.
1. A method performed in a cloud-based digital space, comprising:
receiving data regarding a physical object from a physical space within which a vehicle is operating;
processing the data using machine learning to model road surface conditions, in which respective penalty values are assigned to corresponding road surfaces, a respective penalty value being inversely related to a condition of the corresponding road surface, wherein the penalty values are used to generate a rewards function that categorizes the modeled road surface conditions;
deriving instructions based on the modeled road surface conditions and applying the rewards function to guide actuation of the vehicle along a trajectory; and
transmitting the instructions to the physical space connected to the vehicle to guide actuation of the vehicle.
2. The method of claim 1 , wherein the processing of the data further comprises storing the data in a data lake.
3. The method of claim 2 , wherein the data lake further comprises stored historical data.
4. The method of claim 3 , wherein the processing of the data includes processing of the stored historical data in addition to the stored data received from the physical space.
5. The method of claim 1 , wherein the physical object comprises at least one of a vehicle, a human, and a traffic device.
6. The method of claim 1 , wherein the data is collected by one or more sensors communicating with the physical object.
7. The method of claim 6 , wherein the collected data is real-time information relating to one or more of the following: road surfaces, traffic flow, weather, ego vehicle, perception of neighboring vehicle, or occupant of ego vehicle.
8. The method of claim 1 , wherein the received data is obtained from one or more monitoring devices associated with the physical object and/or from one or more vehicle-to-anything (V2X) communications regarding the physical object.
9. The method of claim 1 , further comprising effecting the actuation of the vehicle along the trajectory when the vehicle is an autonomous vehicle, or prompting a human driver of the vehicle to drive along the trajectory when the vehicle is operated by the human driver.
10. The method of claim 1 , further comprising:
when the vehicle is operated by a human driver, displaying each respective lane of the road surfaces along the trajectory with an indicator that indicates the road surface condition of the respective lane.
11. The method of claim 1 , wherein the processing further comprises processing the data using machine learning and historical data to model the road surface conditions and predict future road surface conditions, and using the predicted future road surface conditions to target road surfaces for maintenance.
12. The method of claim 1 , further comprising applying a fusion process to the received data and filtering out noisy data.
13. The method of claim 12 , wherein the fusion process is effected using a Kalman filter-based sensor fusion algorithm.
14. A cloud-based system effectuating an end-to-end framework, comprising:
a cloud-based platform hosting one or more digital twins corresponding to one or more physical objects from a physical space within which a vehicle is operating, wherein one of the digital twins comprises a data lake and an active road maintenance microservice;
a communications layer communicatively connecting the one or more digital twins to the one or more physical objects, wherein:
the communications layer transmits data regarding the one or more physical objects to at least the one or more corresponding digital twins, and
the communications layer transmits instructions that have been derived from processing of the transmitted data by at least the active road maintenance microservice to the physical space connected to the vehicle; and
wherein the active road maintenance microservice:
processes the data using machine learning to model road surface conditions, in which a rewards function assigns respective rewards values to corresponding road surfaces, a respective rewards value corresponding to a condition of the corresponding road surface, and
derives the instructions based on the modeled road surface conditions and on optimizing the rewards function to guide actuation of the vehicle along a trajectory.
15. The cloud-based system of claim 14 , wherein the one or more physical objects comprise at least one of a vehicle, a human, and a traffic device.
16. The cloud-based system of claim 14 , wherein the data lake further comprises stored historical data, and wherein the processing of the data further comprises storing the transmitted data in the data lake and processing the stored historical data in addition to the stored transmitted data.
17. The cloud-based system of claim 14 ,
wherein the data is collected by one or more sensors communicating with the one or more physical objects,
wherein the sensors are equipped on one or more of roads, vehicles, vehicle occupants, or pedestrians, and
wherein the sensors are one or more of perception sensor, ultrasonic sensor, camera, radar, LIDAR, in-pavement surface temperature and condition sensor, in-pavement surface chemical and concentration sensor, wearable device, road surface sensor, in-cabin sensor, mobile app, loop detector, condition sensor.
18. The cloud-based system of claim 14 , further comprising when the vehicle is a non-autonomous vehicle, displaying each respective lane of the road surfaces along the trajectory with an indicator that indicates the road surface condition of the respective lane.
19. A method performed in a cloud-based system effectuating an end-to-end framework, comprising:
in a digital space:
receiving data regarding a physical object from a physical space within which a vehicle is operating;
processing the data using machine learning to model road surface conditions, including using a rewards function generated by penalty values to assign respective rewards values to corresponding road surfaces that categorizes the modeled road surface conditions, a respective rewards value being related to a condition of the corresponding road surface;
deriving instructions based on applying the rewards function to guide actuation of the vehicle along a trajectory;
transmitting the instructions to the physical space connected to the vehicle to guide actuation of the vehicle;
in the physical space:
receiving the transmitted instructions;
determining whether the vehicle is an autonomous vehicle or a non-autonomous vehicle; and
when the vehicle is an autonomous vehicle navigating the vehicle along the trajectory using the instructions, or when the vehicle is a non-autonomous vehicle prompting a human driver to navigate the vehicle along with trajectory using the instructions.
20. The method of claim 19 , further comprising:
when the vehicle is a non-autonomous vehicle, displaying each respective lane of the road surfaces along the trajectory with an indicator that indicates the road surface condition of the respective lane.