Machine learning network based carriage control apparatus for maintenance striping
A control system for positioning a marker over a pre-existing roadway surface mark. The control system has one or more imagers having a field of view for imaging an area of roadway mark surface encompassing the roadway mark and a computer having a machine learning network to process the roadway mark image and position the marker over the pre-existing roadway mark.
1. A control system for positioning a marker over a pre-existing roadway surface mark, the control system comprising:
an imager having a field of view for imaging the roadway surface mark;
a sensor for determining the lateral location of the marker;
a computer responsive to the imager and to the sensor and programmatically configured to (a) process the image using a machine learning network and (b) produce an error signal based upon the lateral location difference between the processed image of the pre-existing roadway surface mark and the marker; and
an actuator attached to the marker and responsive to the error signal for positioning the marker over the pre-existing roadway mark;
wherein the machine learning network is a supervised machine learning network system configured to process illumination conditions of the roadway surface consisting of: shadows, color changes of the roadway surface, intersections, imager field of view variations, blending of the roadway mark into the roadway surface, and background clutter and noise.
2. The control system of claim 1 , wherein the sensor is configured to process an image of an electromagnetic radiation source attached to the marker.
3. The control system of claim 2 , wherein the electromagnetic radiation source is a laser.
4. The control system of claim 2 , wherein the electromagnetic radiation source is a laser line generator.
5. The control system of claim 1 , further comprising a deterministic timing source in communication with the computer, wherein the deterministic timing source synchronously or asynchronously time stamps images of the roadway surface.
6. The control system of claim 1 , wherein the supervised machine learning network system comprises a convolutional neural network.
7. An apparatus for placing marks over a pre-existing roadway surface mark comprising:
a moving vehicle;
an imager affixed to the vehicle and having a field of view for imaging the roadway surface mark;
a marker positioned on the vehicle for dispensing roadway mark material;
a sensor for determining the lateral location of the marker;
a computer responsive to the imager and programmatically configured to (a) process the image using a machine learning network and (b) produce an error signal based upon the lateral location difference between the processed image of the pre-existing roadway surface mark and the marker; and
an actuator attached to the marker and responsive to the error signal for positioning the marker over the pre-existing roadway mark;
wherein the machine learning network comprises a supervised machine learning network system configured to process illumination conditions consisting of: shadows, color changes of the roadway surface, intersections, imager field of view variations, blending of the roadway mark into the roadway surface, and background clutter and noise.
8. The control system of claim 7 , wherein the sensor is configured to process an image of an electromagnetic radiation source attached to the marker.
9. The apparatus of claim 8 , further comprising an electromagnetic radiation source attached to the marker.
10. The apparatus of claim 9 , wherein the electromagnetic radiation source is a laser.
11. The apparatus of claim 9 , wherein the electromagnetic radiation source is a laser line generator.
12. The apparatus of claim 9 , further comprising a deterministic timing source in communication with the imager, wherein the deterministic timing source synchronously or asynchronously time stamps images of the roadway surface.
13. The apparatus of claim 7 , wherein the supervised machine learning network system is a convolutional neural network.
14. An apparatus for replicating pre-existing skip line roadway marks comprising:
a moving vehicle;
an imager affixed to the vehicle and having a field of view for imaging the roadway surface mark;
a marker positioned on the vehicle for dispensing roadway mark material and responsive to a dispensing signal;
a sensor for determining the lateral location of the marker;
a computer responsive to the imager and the sensor and programmatically configured to (a) process the roadway mark surface image using a machine learning network, (b) produce an error signal based upon the lateral location difference between the processed image of the pre-existing roadway surface mark and the marker, and (c) produce a dispensing signal from the processed image for dispensing roadway mark material over the pre-existing roadway skip line marks; and
an actuator attached to the marker and responsive to the error signal for positioning the marker over the pre-existing roadway mark;
wherein the machine learning network comprises a supervised machine learning network system configured to process illumination conditions consisting of: shadows, color changes of the roadway surface, intersections, imager field of view variations, blending of the roadway mark into the roadway surface, and background clutter and noise.
15. The apparatus of claim 14 , wherein the supervised machine learning network system is a convolutional neural network.