Computer implemented method and system for suppressing false dump events

1 . A computer-implemented method comprising:

generating, by a computing system comprising a processor and memory storing instructions executable by the processor, a control signal that causes a machine, separate from the computing system, to perform a work cycle comprising a dump event;

receiving, by the computing system via a transmission from the machine, sensor data captured by one or more sensors of the machine, wherein the sensor data is indicative of operations of the machine at a worksite during performance of the work cycle in response to the control signal;

determining, by the computing system at a first time, that the sensor data indicates that the machine performed the dump event, during performance of the work cycle, at a particular time and at a particular location;

updating, by the computing system, tracking data associated with the worksite in response to determining that the sensor data indicates that the machine performed the dump event, wherein:

the tracking data is updated to indicate that a work cycle segment of the work cycle, performed by the machine, ended at the particular time and at the particular location based on the dump event;

determining, by the computing system at a second time, that the dump event was erroneously indicated by the sensor data and is a false dump event that did not occur; and

suppressing, by the computing system, the false dump event by re-determining the tracking data based on determining that the dump event was erroneously indicated by the sensor data, wherein re-determining the tracking data comprises:

retroactively adjusting the tracking data to indicate that the work cycle segment did not end at the particular time and at the particular location.

2 . The computer-implemented method of claim 1 , comprising:

determining, by the computing system at a time between the first time and the second time, that the dump event indicated by the sensor data is a suspected false dump event;

causing, by the computing system, an indication of the suspected false dump event to be displayed in a user interface; and

receiving, by the computing system, and via the user interface, user input confirming that the suspected false dump event is the false dump event,

wherein the computing system determines, at the second time, that the dump event is the false dump event based on the user input.

3 . The computer-implemented method of claim 2 , wherein the computing system uses at least one rule to determine that the dump event is the suspected false dump event.

4 . The computer-implemented method of claim 2 , wherein:

the computing system uses a machine learning model to generate a prediction that the dump event is the false dump event, the prediction being associated with a confidence level,

the computing system determines that the dump event is the suspected false dump event based on the confidence level of the prediction being below a threshold confidence level, and

the machine learning model is trained on historical data to identify data features that are predictive of false dump events.

5 . The computer-implemented method of claim 4 , comprising re-training, by the computing system, the machine learning model based on the user input confirming that the suspected false dump event is the false dump event.

6 . The computer-implemented method of claim 1 , wherein determining that the dump event is the false dump event and suppressing the false dump event comprises:

generating a prediction, with a confidence level, that the dump event is the false dump event by the computing system using a machine learning model trained on historical data to identify data features that are predictive of false dump events;

determining, by the computing system, that the confidence level of the prediction is above a threshold confidence level; and

suppressing, by the computing system, the false dump event based on the confidence level of the prediction being above the threshold confidence level.

7 . The computer-implemented method of claim 1 , wherein suppressing the false dump event, based on determining that the dump event was erroneously indicated by the sensor data, further comprises:

using additional sensor data, from the one or more sensors of the machine, to retroactively determine that the work cycle segment ended at:

a different time than the particular time, and

a different location than the particular location.

8 . The computer-implemented method of claim 1 , wherein the machine is an autonomous machine that autonomously performs instances of the work cycle, including the work cycle segment, at the worksite.

9 . A computing system, comprising:

a processor; and

a memory having stored thereon computer-executable instructions that, when executed by the processor, cause the processor to:

generate a control signal that causes a machine, separate from the computing system, to perform a work cycle comprising a dump event;

receive, via a transmission from the machine, sensor data captured by one or more sensors of the machine, wherein the sensor data is indicative of operations of the machine at a worksite during performance of the work cycle in response to the control signal;

determine, at a first time, that the sensor data indicates that the machine performed the dump event, during performance of the work cycle, at a particular time and at a particular location;

update tracking data associated with the worksite in response to determining that the sensor data indicates that the machine performed the dump event, wherein:

the tracking data is updated to indicate that a work cycle segment of the work cycle, performed by the machine, ended at the particular time and at the particular location based on the dump event;

determine, at a second time, that the dump event was erroneously indicated by the sensor data and is a false dump event that did not occur; and

suppress the false dump event by re-determining the tracking data based on determining that the dump event was erroneously indicated by the sensor data, wherein re-determining the tracking data comprises:

retroactively adjusting the tracking data to indicate that the work cycle segment did not end at the particular time and at the particular location.

10 . The computing system of claim 9 , wherein the computer-executable instructions cause the processor to:

determine, based on at least one rule at a time between the first time and the second time, that the dump event indicated by the sensor data is a suspected false dump event;

cause an indication of the suspected false dump event to be displayed in a user interface; and

receive, via the user interface, user input confirming that the suspected false dump event is the false dump event,

wherein the processor determines, at the second time, that the dump event is the false dump event based on the user input.

11 . The computing system of claim 9 , wherein the computer-executable instructions cause the processor to generate a prediction, with a confidence level, that the dump event is the false dump event using a machine learning model trained on historical data to identify data features that are predictive of false dump events.

12 . The computing system of claim 11 , wherein the computer-executable instructions cause the processor to:

determine that the confidence level of the prediction is above a threshold confidence level; and

suppress the false dump event based on the confidence level of the prediction being above the threshold confidence level.

13 . The computing system of claim 11 , wherein the computer-executable instructions cause the processor to:

determine that the confidence level of the prediction is below a threshold confidence level;

determine, at a time between the first time and the second time based on the confidence level of the prediction being below the threshold confidence level, that the dump event is a suspected false dump event;

cause an indication of the suspected false dump event to be displayed in a user interface;

receive, via the user interface, user input confirming that the suspected false dump event is the false dump event; and

suppress the false dump event based on the user input.

14 . The computing system of claim 13 , wherein the computer-executable instructions cause the processor to re-train the machine learning model based on the user input confirming that the suspected false dump event is the false dump event.

15 . The computing system of claim 9 , wherein suppressing the false dump event, based on determining that the dump event was erroneously indicated by the sensor data, further comprises:

using additional sensor data, from the one or more sensors of the machine, to retroactively determine that the work cycle segment ended at:

a different time than the particular time, and

a different location than the particular location.

16 . A system comprising:

a machine comprising:

a work tool configured to transport and dump material at a worksite;

a sensor configured to capture sensor data associated with the work tool; and

a wireless communication interface configured to transmit the sensor data; and

a computing system configured to:

generate a control signal that causes the machine to perform a work cycle comprising a dump event;

receive the sensor data captured by the sensor of the machine and transmitted by the wireless communication interface of the machine, wherein the sensor data is indicative of operations of the machine at the worksite during performance of the work cycle in response to the control signal;

determine, at a first time, that the sensor data indicates that the machine performed the dump event, during performance of the work cycle, at a particular time and at a particular location;

update tracking data associated with the worksite in response to determining that the sensor data indicates that the machine performed the dump event, wherein:

the tracking data is updated to indicate that a work cycle segment of the work cycle, performed by the machine, ended at the particular time and at the particular location based on the dump event;

determine, at a second time, that the dump event was erroneously indicated by the sensor data and is a false dump event that did not occur; and

suppress the false dump event by re-determining the tracking data based on determining that the dump event was erroneously indicated by the sensor data, wherein re-determining the tracking data comprises:

retroactively adjusting the tracking data to indicate that the work cycle segment did not end at the particular time and at the particular location.

17 . The system of claim 16 , wherein the computing system is configured to:

determine, based on at least one rule at a time between the first time and the second time, that the dump event indicated by the sensor data is a suspected false dump event;

cause an indication of the suspected false dump event to be displayed in a user interface; and

receive, via the user interface, user input confirming that the suspected false dump event is the false dump event,

wherein the computing system determines, at the second time, that the dump event is the false dump event based on the user input.

18 . The system of claim 16 , wherein the computing system is configured to generate a prediction, with a confidence level, that the dump event is the false dump event, using a machine learning model trained on historical data to identify data features that are predictive of false dump events.

19 . The system of claim 18 , wherein the computing system is configured to:

determine that the confidence level of the prediction is above a threshold confidence level; and

suppress the false dump event based on the confidence level of the prediction being above the threshold confidence level.

20 . The system of claim 18 , wherein the computing system is configured to:

determine that the confidence level of the prediction is below a threshold confidence level;

determine, at a time between the first time and the second time based on the confidence level of the prediction being below the threshold confidence level, that the dump event is a suspected false dump event;

cause an indication of the suspected false dump event to be displayed in a user interface;

receive, via the user interface, user input confirming that the suspected false dump event is the false dump event; and

suppress the false dump event based on the user input.