System and method for mapping obstructions in a work area to corresponding locations
A system and method are provided for mapping obstructions in a work area traversed by a work machine such as a sprayer, combine or other machine having a ground-engaging work implement. While the work machine traverses the work area, and via output signals from sensors associated with the work machine, obstructions are detected at (e.g., using perception sensing on a combine, etc.) and/or below (e.g., using vibration sensing on a planter, dozer, etc.) a ground surface. A mapped data structure associated with the work area is accordingly modified, wherein a sensed location and one or more identified characteristics for each respective one of the detected obstructions are mapped to corresponding locations in the mapped data structure. The sensors may include vibration sensors or implement actuator position sensors to detect an obstruction contacted by the work machine, and/or perception sensors to detect obstructions on the surface/within a field of view.
1 . A method of mapping obstructions in a work area traversed by a work machine, the method comprising:
while the work machine traverses the work area, and via output signals from one or more sensors associated with the work machine, detecting one or more obstructions at and/or below a ground surface; and
modifying a mapped data structure associated with the work area, wherein a sensed location and one or more identified characteristics for each respective one of the one or more detected obstructions are mapped to corresponding locations in the mapped data structure, and wherein the mapped data structure comprises a multidimensional coordinate system;
wherein the sensed location is determined based on a location of the obstruction relative to the work machine and a current location of the work machine in the multidimensional coordinate system of the mapped data structure; and
determining an intervention event at least in part by comparing at least one of the one or more identified characteristics for a respective obstruction to corresponding intervention states.
2 . The method of claim 1 , wherein the work machine comprises a machine frame and at least one ground-engaging work implement moveable with respect to the machine frame.
3 . The method of claim 2 , wherein the one or more sensors comprise a vibration sensor, at least one of the one or more obstructions is detected via output signals from the vibration sensor, and an identified location of the work machine upon detecting the at least one of the one or more obstructions corresponds to the sensed location for the at least one of the one or more obstructions, the method further comprising:
modifying the mapped data structure to map sensed vibrations at respective locations within the work area to corresponding locations in the mapped data structure;
determining a baseline vibration level or range associated with the work area; and
detecting the at least one of the one or more obstructions based at least in part on comparison of a respective vibration value to the baseline vibration level or range.
4 . The method of claim 2 , wherein the one or more sensors comprise a position sensor associated with a work implement actuator, and at least one of the one or more obstructions is detected via an error value for a detected position of the work implement actuator with respect to a commanded position of the work implement actuator.
5 . The method of claim 1 , wherein the one or more sensors comprise a perception sensor having a field of view in a forward direction with respect to the work machine, and at least one of the one or more obstructions is automatically detected via classification of objects within the field of view.
6 . The method of claim 1 , comprising iterative development of a model over time to correlate input data sets, corresponding to the output signals from the one or more sensors, with labeled outcomes, wherein the labeled outcomes are selected from among obstructions having one or more corresponding characteristics, and wherein obstructions during a current traverse of the work area by the work machine are detected by reference to the model based on current input data sets corresponding to the output signals from the one or more sensors.
7 . The method of claim 6 , wherein at least one of the one or more characteristics corresponds to a severity of a respective obstruction.
8 . The method of claim 1 , wherein at least one intervention state comprises a user specified threshold for an obstruction size.
9 . The method of claim 1 , comprising modifying the mapped data structure associated with the work area, wherein indicia corresponding to at least one type of intervention event is mapped to corresponding obstructions and respective locations within the mapped data structure.
10 . The method of claim 1 , comprising controlling one or more components of the work machine based on at least one type of determined intervention event.
11 . A system for mapping obstructions in a work area, the system comprising:
one or more sensors associated with a work machine; and
one or more processors functionally linked to the one or more sensors and configured, while the work machine traverses the work area,
via output signals from the one or more sensors, to detect one or more obstructions at and/or below a ground surface, and
modify a mapped data structure associated with the work area, wherein a sensed location and one or more identified characteristics for each respective one of the one or more detected obstructions are mapped to corresponding locations in the mapped data structure, and wherein the mapped data structure comprises a multidimensional coordinate system;
wherein the sensed location is determined based on a location of the obstruction relative to the work machine and a current location of the work machine in the multidimensional coordinate system of the mapped data structure; and
wherein the one or more processors are further configured to determine an intervention event at least in part by comparing at least one of the one or more identified characteristics for a respective obstruction to corresponding intervention states.
12 . The system of claim 11 , wherein at least one of the one or more processors is associated with a cloud computing network.
13 . The system of claim 11 , wherein at least one of the one or more processors is associated with a work machine controller.
14 . The system of claim 11 , wherein the work machine comprises a machine frame and at least one ground-engaging work implement moveable with respect to the machine frame.
15 . The system of claim 14 , wherein the one or more sensors comprise a vibration sensor, at least one of the one or more obstructions is detected via output signals from the vibration sensor, and an identified location of the work machine upon detecting the at least one of the one or more obstructions corresponds to the sensed location for the at least one of the one or more obstructions.
16 . The system of claim 11 , wherein the one or more sensors comprise a perception sensor having a field of view in a forward direction with respect to the work machine, and at least one of the one or more obstructions is automatically detected via classification of objects within the field of view.
17 . The system of claim 11 , wherein the one or more processors are configured for iterative development of a model over time to correlate input data sets, corresponding to the output signals from the one or more sensors, with labeled outcomes, wherein the labeled outcomes are selected from among obstructions having one or more corresponding characteristics, and wherein obstructions during a current traverse of the work area by the work machine are detected by reference to the model based on current input data sets corresponding to the output signals from the one or more sensors.
18 . A method of mapping obstructions in a work area traversed by a work machine, the method comprising:
iterative development of a model over time to correlate input data sets, corresponding to output signals from one or more sensors associated with the work machine, with labeled outcomes, wherein the labeled outcomes are selected from among obstructions having one or more corresponding characteristics;
during a current traverse of the work area by the work machine, and by reference to the model based on current input data sets corresponding to the output signals from the one or more sensors, detecting one or more obstructions at and/or below a ground surface; and
modifying a mapped data structure associated with the work area, wherein a sensed location and one or more identified characteristics for each respective one of the one or more detected obstructions are mapped to corresponding locations in the mapped data structure, and wherein the mapped data structure comprises a multidimensional coordinate system;
wherein the sensed location is determined based on a location of the obstruction relative to the work machine and a current location of the work machine in the multidimensional coordinate system of the mapped data structure.
19 . The method of claim 18 , wherein the work machine comprises a machine frame and at least one ground-engaging work implement moveable with respect to the machine frame, the one or more sensors comprise a vibration sensor, at least one of the one or more obstructions is detected via output signals from the vibration sensor, and an identified location of the work machine upon detecting the at least one of the one or more obstructions corresponds to the sensed location for the at least one of the one or more obstructions;
the method further comprising:
modifying the mapped data structure to map sensed vibrations at respective locations within the work area to corresponding locations in the mapped data structure;
determining a baseline vibration level or range associated with the work area; and
detecting the at least one of the one or more obstructions based at least in part on comparison of a respective vibration value to the baseline vibration level or range.
20 . The method of claim 18 , wherein the work machine comprises a machine frame and at least one ground-engaging work implement moveable with respect to the machine frame, the one or more sensors comprise a position sensor associated with a work implement actuator, and at least one of the one or more obstructions is detected via an error value for a detected position of the work implement actuator with respect to a commanded position of the work implement actuator.