US-20260123572-A1 - Object Classification Based Dynamic Machine Positioning

US20260123572A1US 20260123572 A1US20260123572 A1US 20260123572A1US-20260123572-A1

Abstract

Systems, devices, and methods for autonomous mowing in turf environments are described. The mowing vehicle integrates manual controls, a display, and a controller connected to a sensor system all-around coverage. Sensors feed a vision processing unit that detects, classifies, and maps transient and non-transient objects. Modules within the vision processing unit handle object detection, classification, boundary generation, path planning, actuation, user interaction, and job quality monitoring. Path planning adapts to dynamic conditions, other machines, and changing object sizes, while the actuation module executes adjusted paths in real time. The user interface enables operator oversight and settings adjustments, with cloud connectivity for data storage and reuse. Job quality is assessed through sensor and image data, enabling corrective actions.

Inventors

Joel J. Sandoval
Timothy J. Lewis
Bradley A. Powers
Kent Michael Anderson

Assignees

DEERE & COMPANY

Dates

Publication Date: 20260507
Application Date: 20251015

Claims (20)

1 . A method for performing autonomous actions in a turf environment, the method comprising: traversing, with an autonomous mowing machine, the turf environment along a planned path performing autonomous actions, the turf environment comprising a plurality of objects; capturing, using an imaging system on the autonomous mowing machine, while the autonomous mowing machine is performing autonomous actions, images representing the plurality of objects; for each object of the plurality: determining, using the captured images, whether the object is a transient object or a non-transient object; responsive to determining the object is a transient object, determining a first additional autonomous action to perform in the turf environment; and response to determining the object is a non-transient object, determining a second additional autonomous action different from the first additional autonomous action to perform in the turf environment; and performing, using the autonomous mowing machine traversing the planned path, the first additional autonomous action or the second additional autonomous action.
2 . The method of claim 1 , wherein determining whether the object is a transient object or a non-transient object comprises using both depth information and visual information from the imaging system.
3 . The method of claim 1 , wherein the first additional autonomous action for an object identified as transient a transient object comprises at least one of: stopping the autonomous mowing machine, slowing the autonomous mowing machine, rerouting around the transient object, or waiting for a movement of the transient object.
4 . The method of claim 1 , wherein the second additional autonomous action for an object identified as a non-transient object comprises at least one of: modifying the planned path to a predefined distance to the non-transient object, avoiding the non-transient object by another predetermined distance, updating a boundary map, or storing location information of the non-transient object in a data storage.
5 . The method of claim 1 , further comprises: determining that the non-transient object is in motion; in response, modifying a label of the non-transient object to transient object; and modifying the planned path and actuate the modified planned path.
6 . The method of claim 1 , further comprises: determining that the non-transient object is instead a transient object; in response, modifying a label of the transient object to non-transient object; and in response, performing the first additional autonomous action instead of the second additional autonomous action.
7 . The method of claim 1 , wherein determining whether the object is a transient object or a non-transient object further comprises: receiving, from a client device in communication with the autonomous mowing machine, a modification to a label of the determination.
8 . The method of claim 7 , wherein the autonomous mowing machine performs the first additional autonomous action or the second additional autonomous action based on the modification to the label received from the client device.
9 . A non-transitory computer readable storage medium comprising instructions for performing autonomous actions in a turf environment, the instructions, when executed by one or more processors, causing the processors to perform steps comprising: traversing, with an autonomous mowing machine, the turf environment along a planned path performing autonomous actions, the turf environment comprising a plurality of objects; capturing, using an imaging system on the autonomous mowing machine, while the autonomous mowing machine is performing autonomous actions, images representing the plurality of objects; for each object of the plurality: determining, using the captured images, whether the object is a transient object or a non-transient object; responsive to determining the object is a transient object, determining a first additional autonomous action to perform in the turf environment; and response to determining the object is a non-transient object, determining a second additional autonomous action different from the first additional autonomous action to perform in the turf environment; and performing, using the autonomous mowing machine traversing the planned path, the first additional autonomous action or the second additional autonomous action.
10 . The non-transitory computer readable storage medium of claim 9 , wherein determining whether the object is a transient object or a non-transient object comprises using both depth information and visual information from the imaging system.
11 . The non-transitory computer readable storage medium of claim 9 , wherein the first additional autonomous action for an object identified as transient a transient object comprises at least one of: stopping the autonomous mowing machine, slowing the autonomous mowing machine, rerouting around the transient object, or waiting for a movement of the transient object.
12 . The non-transitory computer readable storage medium of claim 9 , wherein the second additional autonomous action for an object identified as a non-transient object comprises at least one of: modifying the planned path to a predefined distance to the non-transient object, avoiding the non-transient object by another predetermined distance, updating a boundary map, or storing location information of the non-transient object in a data storage.
13 . The non-transitory computer readable storage medium of claim 9 wherein the one or more processors perform steps comprising: determining that the non-transient object is in motion; in response, modifying a label of the non-transient object to transient object; and modifying the planned path and actuate the modified planned path.
14 . The non-transitory computer readable storage medium of claim 9 , wherein the one or more processors perform steps comprising: determining that the non-transient object is instead a transient object; in response, modifying a label of the transient object to non-transient object; and in response, performing the first additional autonomous action instead of the second additional autonomous action.
15 . The non-transitory computer readable storage medium of claim 9 , wherein determining whether the object is a transient object or a non-transient object further causes the one or more processors to perform steps comprising: receiving, from a client device in communication with the autonomous mowing machine, a modification to a label of the determination.
16 . The method of claim 7 , wherein the autonomous mowing machine performs the first additional autonomous action or the second additional autonomous action based on the modification to the label received from the client device.
17 . An autonomous mowing machine comprising: an imaging system configured to capture images representing a plurality of objects in a turf environment; a navigation system configured for controlling traversal of the autonomous mowing machine in the turf environment; one or more processors; a non-transitory computer readable storage medium comprising instructions for performing autonomous actions in the turf environment, the instructions, when executed by one or more processors, causing the processors to perform steps comprising: traversing, using the navigation system, the turf environment along a planned path performing autonomous actions, the turf environment comprising a plurality of objects; capturing, using the imaging system and while the autonomous mowing machine is performing autonomous actions, images representing the plurality of objects; for each object of the plurality: determining, using the captured images, whether the object is a transient object or a non-transient object; responsive to determining the object is a transient object, determining a first additional autonomous action to perform in the turf environment; and response to determining the object is a non-transient object, determining a second additional autonomous action different from the first additional autonomous action to perform in the turf environment; and performing, using the autonomous mowing machine traversing the planned path, the first additional autonomous action or the second additional autonomous action.
18 . The autonomous mowing machine of claim 17 , wherein determining whether the object is a transient object or a non-transient object further causes the one or more processors to use both depth information and visual information from the imaging system.
19 . The autonomous mowing machine of claim 17 , wherein the first additional autonomous action for an object identified as transient a transient object comprises at least one of: stopping the autonomous mowing machine, slowing the autonomous mowing machine, rerouting around the transient object, or waiting for a movement of the transient object.
20 . The autonomous mowing machine of claim 17 , wherein the second additional autonomous action for an object identified as a non-transient object comprises at least one of: modifying the planned path to a predefined distance to the non-transient object, avoiding the non-transient object by another predetermined distance, updating a boundary map, or storing location information of the non-transient object in a data storage.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Application Ser. No. 63/717,549 filed Nov. 7, 2024, and U.S. Provisional Application Ser. No. 63/718,101 filed on Nov. 8, 2024, both of which are incorporated by reference in its entirety. TECHNICAL FIELD The present disclosure relates generally to systems, methods, and devices for object classification based dynamic machine positioning. More specifically it relates to adapting autonomous pathing based on real time identification of objects. BACKGROUND Grass mowing machines, or mowers, may be manual and/or autonomous and are used to cut grass, also called turf. Some mowers may mow an area to be mowed according to a coverage plan or path plan. In such a scenario, mowers may encounter boundaries, which may be a boundary indicating a property line or a boundary around an obstacle or keep out area within an area to be mowed. Moreover, mowers may encounter obstacles. Such obstacles may be known to the mower in advance of encountering the obstacle, such as those described above with pre-identified boundaries, or such obstacles may be unexpected. Moreover, obstacles, even if known, may move or change size. In some situations, grass mowing machines may leave an area of uncut grass around a boundary and/or obstacle. Often, this uncut grass must then be trimmed. Trimming can increase the time required to completely cut an area of turf. In some mowing applications, such as residential, commercial, and/or golf mowing, mowing is accomplished by a party that mows a plurality of areas. For example, a professional landscaping company may use one or more mowing devices to cut turf. Such a company may service a plurality of properties. Such a party may use one or more autonomous mowers to cut turf. In such a scenario, it may be beneficial to configure a property, job, and/or machine setup within one or more machines. SUMMARY In some aspects, the techniques described herein relate to a method for performing autonomous actions in a turf environment, the method including: traversing, with an autonomous mowing machine, the turf environment along a planned path performing autonomous actions, the turf environment including a plurality of objects; capturing, using an imaging system on the autonomous mowing machine, while the autonomous mowing machine is performing autonomous actions, images representing the plurality of objects; for each object of the plurality: determining, using the captured images, whether the object is a transient object or a non-transient object; responsive to determining the object is a transient object, determining a first additional autonomous action to perform in the turf environment; and response to determining the object is a non-transient object, determining a second additional autonomous action different from the first additional autonomous action to perform in the turf environment; and performing, using the autonomous mowing machine traversing the planned path, the first additional autonomous action or the second additional autonomous action. In some aspects, the techniques described herein relate to a method, wherein determining whether the object is a transient object or a non-transient object includes using both depth information and visual information from the imaging system. In some aspects, the techniques described herein relate to a method, wherein the first additional autonomous action for an object identified as transient a transient object includes at least one of: stopping the autonomous mowing machine, slowing the autonomous mowing machine, rerouting around the transient object, or waiting for a movement of the transient object. In some aspects, the techniques described herein relate to a method, wherein the second additional autonomous action for an object identified as a non-transient object includes at least one of: modifying the planned path to a predefined distance to the non-transient object, avoiding the non-transient object by another predetermined distance, updating a boundary map, or storing location information of the non-transient object in a data storage. In some aspects, the techniques described herein relate to a method, further includes: determining that the non-transient object is in motion; in response, modifying a label of the non-transient object to transient object; and modifying the planned path and actuate the modified planned path. In some aspects, the techniques described herein relate to a method, further includes: determining that the non-transient object is instead a transient object; in response, modifying a label of the transient object to non-transient object; and in response, performing the first additional autonomous action instead of the second additional autonomous action. In some aspects, the techniques described herein relate to a method, wherein determining whether the object is a transient object or a non-transient object further includes: receiving, from a cl