Road construction detection systems and methods

Patent metadata

Field	Value
Publication number	US-10282999-B2
Application number	US-201715461762-A
Country	US
Kind code	B2
Filing date	Mar 17, 2017
Priority date	Mar 17, 2017
Publication date	May 7, 2019
Grant date	May 7, 2019

Abstract

Systems and method are provided for controlling a vehicle. In one embodiment, a method of detecting road construction includes receiving sensor data relating to an environment associated with a vehicle, determining that construction-related objects are present within the environment based on the sensor data, and determining whether a travel-impacting construction zone is present within the environment based on the presence of the construction-related objects in the environment.

First claim

What is claimed is:

1. A method of detecting road construction comprising:
receiving, from a sensor system, sensor data including optical sensor data, relating to an environment associated with a vehicle;
determining, with a processor, that construction-related objects are present within the environment based on the sensor data by applying the optical sensor data to a pre-trained machine-learning model stored within the vehicle;
determining, with a processor, whether a construction zone is present within the environment and whether the construction zone is a travel-impacting construction zone based on the presence of the construction-related objects in the environment and a number, a position, and a type of the construction-related objects;
determining, with a processor, an impact on a route from the construction zone;
classifying, with a processor, the impact on a route from the construction zone as:

a partial lane blockage when the construction zone causes a partial lane blockage, a lane blockage when the construction zone causes a lane closure, and a road blockage when the construction zone causes a blocked road; and
transmitting a geographical location of the construction zone and the classified impact from the construction zone over a network to an external server.

2. The method of claim 1 , further including receiving, at the vehicle, route information associated with a destination, the route information configured to avoid the travel-impacting construction zone.

3. The method of claim 1 , further including transmitting information related to the travel-impacting construction zone over a network to a server.

4. The method of claim 1 , wherein determining that the construction-related objects are present within the environment includes providing the sensor data to an artificial neural network model.

5. The method of claim 4 , wherein the sensor data is provided to a convolutional neural network model.

6. The method of claim 1 , wherein determining that construction-related objects are present within the environment includes determining the presence of at least one of: a traffic cone, a traffic barrier, a traffic barrel, a construction sign, a reflective vest, a construction helmet, an arrow-board trailer, and a piece of construction equipment.

7. The method of claim 1 , wherein the sensor data includes optical sensor data.

8. The method of claim 7 , wherein the sensor data includes lidar sensor data.

9. A system for controlling a vehicle, comprising:
a construction-related object module, including a processor and machine-readable software instructions stored on non-transitory media that, when executed by the processor, are configured to receive sensor data including optical sensor data relating to an environment associated with the vehicle and determine that construction-related objects are present within the environment based on the sensor data by applying the optical sensor data to a pre-trained machine-learning model stored within the vehicle; and
a construction zone determination module, including a processor and machine-readable software instructions stored on non-transitory media that, when executed by the processor, are configured to:
determine whether a construction zone is present within the environment and whether the construction zone is a travel-impacting construction zone based on the presence of the construction-related objects in the environment and a number, a position, and a type of the construction-related objects;
determine an impact on a route from the construction zone;
classify the impact on a route from the construction zone as: a partial lane blockage when the construction zone causes a partial lane blockage, a lane blockage when the construction zone causes a lane closure, and a road blockage when the construction zone causes a blocked road; and
transmit a geographical location of the construction zone and the classified impact from the construction zone over a network to an external server.

10. The system of claim 9 , further including a communication system configured to transmit information related to the travel-impacting construction zone over a network to a server.

11. The system of claim 10 , wherein the construction-related object module includes an artificial neural network model.

12. The system of claim 11 , wherein the artificial neural network model is a convolutional neural network.

13. The system of claim 9 , wherein the construction-related objects includes at least one of: a traffic cone, a traffic barrier, a traffic barrel, a construction sign, a reflective vest, a construction helmet, an arrow-board trailer, and a piece of construction equipment.

14. The system of claim 9 , wherein the sensor data comprises optical sensor data.

15. An autonomous vehicle, comprising:
at least one sensor that provides sensor data, including optical sensor data; and
a controller that, by a processor and based on the sensor data:
receives sensor data relating to an environment associated with a vehicle;
determines that construction-related objects are present within the environment based on the sensor data by applying the optical sensor data to a pre-trained machine-learning model stored within the vehicle;
determines whether a construction zone is present within the environment and whether the construction zone is a travel-impacting construction zone based on the presence of the construction-related objects in the environment and a number, a position, and a type of the construction-related objects;
determines an impact on a route from the construction zone;
classifies the impact on a route from the construction zone as: a partial lane blockage when the construction zone causes a partial lane blockage, a lane blockage when the construction zone causes a lane closure, and a road blockage when the construction zone causes a blocked road; and
transmits a geographical location of the construction zone and the classified impact from the construction zone over a network to an external server.

16. The autonomous vehicle of claim 15 , further including a communication system configured to transmit information related to the travel-impacting construction zone over a network to a server.

17. The autonomous vehicle of claim 16 , further including a navigation system configured to receive, from the server, route information associated with a destination, the route information configured to avoid the travel-impacting construction zone.

18. The autonomous vehicle of claim 15 , wherein the controller implements a convolutional neural network model.

19. The autonomous vehicle of claim 15 , wherein the at least one sensor includes at least one of an optical sensor and a lidar sensor.

20. The autonomous vehicle of claim 15 , wherein the construction-related objects includes at least one of: a traffic cone, a traffic barrier, a traffic barrel, a construction sign, a reflective vest, a construction helmet, an arrow-board trailer, and a piece of construction equipment.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Creusot Clement

Classifications

• G06V10/82

  using neural networks · CPC title

• G06F18/24143

  Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN] · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G08G1/09623

  Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle (G08G1/0967 takes precedence) · CPC title

• G08G1/0112

  from the vehicle, e.g. floating car data [FCD] · CPC title