Roadside infrastructure deployment

Patent metadata

Field	Value
Publication number	US-11637754-B2
Application number	US-202117150292-A
Country	US
Kind code	B2
Filing date	Jan 15, 2021
Priority date	Jan 15, 2021
Publication date	Apr 25, 2023
Grant date	Apr 25, 2023

Abstract

A set of first candidate topologies of first candidate roadside infrastructure nodes at respective mounting locations in a geographic area is randomly generated. For each of the first candidate topologies, first simulations, including detection of objects according to selected sensor parameters, installation parameters, and environment parameters for the candidate nodes at the respective mounting locations, are executed. First fitness scores are determined for each of the first candidate topologies by comparing results of the first simulations to ground truth data. Upon identifying one of the first fitness scores as exceeding a threshold, the candidate topology associated with the identified first fitness score is identified for deployment.

First claim

The invention claimed is:

1. A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor to:
randomly generate a set of first candidate topologies of first candidate roadside infrastructure nodes at respective mounting locations in a geographic area;
for each of the first candidate topologies, execute first simulations including detection of objects according to selected sensor parameters, installation parameters, and environment parameters for the candidate nodes at the respective mounting locations;
determine first fitness scores for each of the first candidate topologies by comparing results of the first simulations to ground truth data;
upon identifying one of the first fitness scores as exceeding a threshold, identify the candidate topology associated with the identified first fitness score for deployment;
upon determining that none of the first fitness scores exceed the threshold, select some but not all of the first candidate topologies according to the first fitness scores;
generate a set of second candidate topologies at least in part by randomly mutating the installation parameters for the candidate roadside infrastructure nodes in each of the selected first individual topologies;
for each of the second candidate topologies, execute second simulations including detection of objects according to the selected sensor parameters, installation parameters, and environment parameters for the candidate nodes at the respective mounting locations;
determine second fitness scores for each of the second candidate topologies by comparing results of the second simulations to ground truth data; and
upon identifying one of the second fitness scores as exceeding a threshold, identify the candidate topology associated with the identified second fitness score for deployment.

2. The system of claim 1 , wherein the instructions further include instructions to:
upon determining that none of the second fitness scores exceed the threshold, select some but not all of the second candidate topologies according to the second fitness scores;
generate a set of third candidate topologies at least in part by randomly mutating the installation parameters for the candidate roadside infrastructure nodes in each of the selected second individual topologies;
for each of the third candidate topologies, execute third simulations including detection of objects according to the selected sensor parameters, installation parameters, and environment parameters for the candidate nodes at the respective mounting locations;
determine second fitness scores for each of the third candidate topologies by comparing results of the third simulations to ground truth data; and
upon identifying one of the third fitness scores as exceeding a threshold, identify the candidate topology associated with the identified third fitness score for deployment.

3. The system of claim 1 , wherein the instructions further include instructions to generate the set of second candidate topologies further at least in part by randomly generating the set of second candidate topologies.

4. The system of claim 1 , wherein the environment parameters include respective locations of one or more objects.

5. The system of claim 1 , wherein the environment parameters include respective dimensions of one or more objects.

6. The system of claim 1 , wherein the environment parameters include one or more of a time of day, an ambient temperature, an amount of ambient light, and a sensor noise factor.

7. The system of claim 1 , wherein the environment parameters include one or more of noise, latency, or packet drop ratio.

8. The system of claim 1 , wherein the selected sensor parameters include at least one of a sensor type, a sensor power requirement, a sensor field of view, and a sensor range.

9. The system of claim 1 , wherein the installation parameters specify whether communication is wired or wireless.

10. The system of claim 1 , wherein the installation parameters include an edge node status that indicates that a roadside infrastructure node is one of an edge node or not an edge node.

11. The system of claim 1 , wherein the instructions further include instructions to determine the first fitness scores according to a fitness function.

12. A method, comprising:
randomly generating a set of first candidate topologies of first candidate roadside infrastructure nodes at respective mounting locations in a geographic area;
for each of the first candidate topologies, executing first simulations including detection of objects according to selected sensor parameters, installation parameters, and environment parameters for the candidate nodes at the respective mounting locations;
determining first fitness scores for each of the first candidate topologies by comparing results of the first simulations to ground truth data;
upon identifying one of the first fitness scores as exceeding a threshold, identifying the candidate topology associated with the identified first fitness score for deployment;
upon determining that none of the first fitness scores exceed the threshold, selecting some but not all of the first candidate topologies according to the first fitness scores;
generating a set of second candidate topologies at least in part by randomly mutating the installation parameters for the candidate roadside infrastructure nodes in each of the selected first individual topologies;
for each of the second candidate topologies, executing second simulations including detection of objects according to the selected sensor parameters, installation parameters, and environment parameters for the candidate nodes at the respective mounting locations;
determining second fitness scores for each of the second candidate topologies by comparing results of the second simulations to ground truth data; and
upon identifying one of the second fitness scores as exceeding a threshold, identifying the candidate topology associated with the identified second fitness score for deployment.

13. The method of claim 12 , further comprising:
upon determining that none of the second fitness scores exceed the threshold, selecting some but not all of the second candidate topologies according to the second fitness scores;
generating a set of third candidate topologies at least in part by randomly mutating the installation parameters for the candidate roadside infrastructure nodes in each of the selected second individual topologies;
for each of the third candidate topologies, executing third simulations including detection of objects according to the selected sensor parameters, installation parameters, and environment parameters for the candidate nodes at the respective mounting locations;
determining second fitness scores for each of the third candidate topologies by comparing results of the third simulations to ground truth data; and
upon identifying one of the third fitness scores as exceeding a threshold, identifying the candidate topology associated with the identified third fitness score for deployment.

14. The method of claim 12 , further comprising generating the set of second candidate topologies further at least in part by randomly generating the set of second candidate topologies.

15. The method of claim 12 , wherein the environment parameters include one or more of: (a) respective locations of one or more objects, (b) respective dimensions of one or more objects, (c) one or more of a time of day, an ambient temperature, an amount of ambient light, and a sensor noise factor, or (d) one or more of noise, latency, or packet drop ratio

Assignees

• Ford Global Tech Llc

Inventors

• Pandey Gaurav
• Remillard Jeffrey Thomas
• Parchami Mostafa
• Kourous-Harrigan Helen E
• Lockwood John Anthony

Classifications

• H04L41/12 Primary

  Discovery or management of network topologies · CPC title

• H04W4/40

  for vehicles, e.g. vehicle-to-pedestrians [V2P] · CPC title

• H04L41/145 Primary

  involving simulating, designing, planning or modelling of a network · CPC title

• H04W4/38

  for collecting sensor information · CPC title

• H04W4/021

  Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences · CPC title