Autonomous machine navigation in various lighting environments
By determining the feature detection range and detection score in the navigation map, and combining visual and non-visual sensor data, the autonomous machine realizes the update of navigation maps and the division of operation areas under different lighting conditions, solving the problem of positioning uncertainty and improving the Navigation and maintenance capabilities under various lighting conditions.
Patent Information
- Application Number
- CN202080081823.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2019-11-27
- Filing Date
- 2020-11-02
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2040-11-02
AI Technical Summary
There is positioning uncertainty when existing autonomous machines navigate under different lighting conditions, especially during the transition period during the day and night and in artificial lighting environments, which limits their continuous maintenance capabilities in areas such as courtyards.
By determining the feature detection range and feature detection score in the navigation map, autonomous machines can update the navigation map under various lighting conditions, limit the location area and buffer area, and use data fusion based on visual and non-visual sensors to ensure that in different lighting conditions Be able to navigate and operate independently.
It realizes effective navigation and maintenance capabilities of autonomous machines over a wider time, improves positioning accuracy and operational reliability under different lighting conditions, and ensures continuous maintenance of the working area.
Smart Images

Figure CN114766014B_ABST
Abstract
Description
[0001] This application claims priority and / or the benefit of U.S. Provisional Patent Application No. 62 / 941,434, filed on November 27, 2019, which is incorporated herein by reference in its entirety. Technical Field
[0002] The present disclosure relates generally to autonomous machine navigation, and in particular, to autonomous machine navigation in various lighting environments. Background Art
[0003] Various machines, such as grounds maintenance machines for lawns and gardens, may perform a variety of tasks. For example, electric lawn mowers may be used by homeowners and professionals alike to maintain grassy areas within a property or yard. Some lawn mowers have the ability to autonomously perform mowing within a predetermined boundary or work area. Summary of the invention
[0004] The technology of the present disclosure generally relates to providing navigation functionality for autonomous machines. Such functionality can facilitate the operation of autonomous machines over a wider range of times of the day than existing systems. Specifically, autonomous machines using vision-based navigation can benefit from the technology to navigate in various lighting conditions, particularly outdoors which may experience daytime, nighttime, transitions between the two, and the effects of artificial lighting. Additionally, such functionality can provide users with more flexible maintenance scheduling to properly maintain work areas using autonomous machines, which can facilitate more continuous maintenance of work areas.
[0005] In one embodiment, the present disclosure provides a method for training an autonomous machine to navigate in a work area under various lighting conditions. The method includes determining data representing a navigation map of the work area. The navigation map includes an enclosed area. The method also includes determining a feature detection range based on ambient lighting parameters. The method also includes determining a feature detection score for each of one or more locations in the enclosed area based on the feature detection range. The method also includes determining one or more locatable locations in the enclosed area based on the corresponding feature detection scores. The method also includes updating the navigation map based on the one or more locatable locations to include the positioning area within the enclosed area, and storing data representing the updated navigation map.
[0006] In another embodiment, the present disclosure provides a method for navigating an autonomous machine in a work area under various lighting conditions. The method includes determining a localization area in a navigation map of the work area. The localization area is defined based on ambient lighting parameters. The method also includes determining an operating mode based on the ambient lighting parameters. The method also includes directing the machine to operate autonomously within the localization area based on the operating mode.
[0007] In another embodiment, the present invention provides a method for navigation of an autonomous machine in a work area under various lighting conditions. The method includes directing the machine to operate autonomously within an enclosed area defined in a navigation map of the work area. The method also includes determining whether vision-based positioning is available at the location of the machine based on at least an ambient lighting parameter. The method also includes, in response to determining that vision-based positioning is not available at the location of the machine, stopping autonomous movement of the machine until the machine is able to position itself at the current location.
[0008] In yet another embodiment, the present disclosure provides an autonomous machine comprising: a housing coupled to a maintenance tool; a propulsion system comprising a propulsion controller operably coupled to at least one motor; at least one camera adapted to record images under one or more ambient lighting conditions; and a controller operably coupled to the at least one camera and the propulsion controller. The controller is adapted to perform a method according to the present disclosure.
[0009] The summary is not intended to describe each embodiment or every implementation of the present disclosure. A more complete understanding of the present disclosure will become apparent and appreciated by referring to the following detailed description and claims in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Illustrative embodiments will be further described with reference to the accompanying drawings, in which:
[0011] Figure 1 is a conceptual diagram illustrating an example of an autonomous machine.
[0012] Figure 2 It shows Figure 1 A conceptual diagram of an exemplary system of an autonomous machine.
[0013] Figure 3 It shows Figure 1 A conceptual diagram of an example of a work area in which an autonomous machine may operate.
[0014] Figure 4 It shows Figure 1 An example graph of the size of an autonomous machine’s uncertainty zone changing over time.
[0015] Figure 5 It shows that the available Figure 1 A flow chart of one example of a method for an autonomous machine to generate a navigation map including a positioning area and a buffer area.
[0016] Figure 6 It shows that the available Figure 1 A flow chart of an example of a method of an autonomous machine navigating within a positioning area.
[0017] Figure 7 It shows that the available Figure 1 A flow chart of an example of a method for an autonomous machine to navigate within an enclosed area using a positioning area and a buffer area.
[0018] Figure 8 It shows that the available Figure 1 A flow chart of an example of a method for an autonomous machine to navigate within an enclosed area using a buffered area.
[0019] These figures are primarily presented for clarity and are not necessarily drawn to scale. In addition, various structures / components (including, but not limited to, fasteners, electrical components (wiring, cables, etc.), etc.) may be schematically illustrated or removed from some or all views to better illustrate various aspects of the depicted embodiments, or where such structures / components are not necessarily included for understanding the various exemplary embodiments described herein. However, the lack of illustration / description of such structures / components in a particular figure should not be construed as limiting the scope of the various embodiments in any way. DETAILED DESCRIPTION
[0020] In the following detailed description of exemplary embodiments, reference is made to the accompanying drawings which form a part hereof. It should be understood that other embodiments which are not described and / or shown herein may of course be envisaged.
[0021] All titles provided herein are for the convenience of the reader, and should not be used to limit the meaning of any text behind the title, unless so specified. In addition, unless otherwise noted, all numerals representing quantity in the specification and claims and all terms representing direction / orientation (e.g., vertical, horizontal, parallel, vertical, etc.) should be understood as modified by the term "precisely" or "approximately" in any case. Unless otherwise clearly noted in the text, the term "or" is usually used with the meaning it contains, for example, to represent "and / or". The term "and / or" (if used) refers to one or all of the listed elements, or any combination of two or more of the listed elements. The term "i.e." can be used as an abbreviation of that is to say (idest) in this article and refers to "i.e.". The term "for example" can be used as an abbreviation of exemplary (exempli gratia) and refers to "such as".
[0022] Embodiments of the present disclosure are generally directed to providing navigation functionality for autonomous machines. Such functionality can facilitate the operation of autonomous machines over a wider range of times of the day than existing systems. Specifically, autonomous machines using vision-based navigation can benefit from the technology to navigate in various lighting conditions, particularly outdoors which may experience daytime, nighttime, transitions between the two, and the effects of artificial lighting. Additionally, such functionality can provide users with more flexible maintenance scheduling to properly maintain work areas using autonomous machines, which can facilitate more continuous maintenance of work areas.
[0023] As used herein, the term "daytime" refers to the range of time between dawn and dusk. The term "daylight" refers to the range of lighting conditions associated with daytime.
[0024] Although described herein as an autonomous lawn mower in an illustrative example, such a configuration is exemplary only, as the systems and methods described herein also apply to other autonomous machines, including, for example, commercial lawn mowing products, other ground-working machines or vehicles (e.g., debris blowers / vacuums, aerators, grass combers, material spreaders, snow blowers, weed removers for weed control), indoor work vehicles such as vacuum cleaners and floor scrubbers / cleaners (e.g., indoor work vehicles that may encounter obstacles), construction and utility vehicles (e.g., trenchers), observation vehicles, and load transport (e.g., including people and objects, such as passenger vehicles and hauling equipment). In addition, the autonomous machines described herein may employ one or more of various types of navigation, such as random, modified random, or specific path planning, to perform their intended functions.
[0025] It should be noted that the terms "having," "including," "comprising," and variations thereof, do not have a limiting meaning in the following description and claims, and are used in their open-ended sense, generally meaning "including but not limited to." Additionally, "a," "an," "the," "at least one," and "one or more" are used interchangeably herein. In addition, relative terms such as "left," "right," "front," "front," "forward," "back," "rear," "backward," "top," "bottom," "side," "up," "down," "above," "below," "horizontal," "vertical," and the like may be used herein, and if used, these terms are from the perspective shown in a particular figure, or when the machine 100 is in an operating configuration (e.g., as shown in FIG. 1 ). Figure 1 , when the machine 100 is positioned with the wheels 106 and 108 resting on a generally horizontal ground surface 103). However, these terms are used only to simplify the description and are not intended to limit the interpretation of any of the embodiments described.
[0026] The techniques of this disclosure may be used with any suitable autonomous machine. Figure 1An example of an autonomous ground maintenance machine (e.g., an autonomously operated vehicle, such as autonomous lawn mower 100) of a lawn mowing system is shown (for ease of description, lawn mower 100 is shown schematically). Lawn mower 100 may include functionality for autonomous navigation in various lighting conditions (such as during the day or at night).
[0027] As shown in this view, the lawn mower 100 can include a housing 102 (e.g., a frame or chassis with a guard) that carries and / or encloses various components of the lawn mower as described below. The lawn mower 100 can also include ground support members such as wheels, rollers, or tracks. In the exemplary embodiment, the ground support members shown include one or more rear wheels 106 and one or more front wheels 108 that support the housing 102 on the ground (grass) 103. As shown, the front wheels 108 are used to support the front end portion 134 of the lawn mower housing 102, and the rear wheels 106 are used to support the rear end portion 136 of the lawn mower housing.
[0028] One or both of the rear wheels 106 may be driven by a propulsion system (e.g., including one or more electric wheel motors 104) to propel the lawn mower 100 over the ground 103. In some embodiments, the front wheel 108 may be free to rotate relative to the housing 102 (e.g., about a vertical axis). In such a configuration, the direction of the lawn mower may be controlled by differential rotation of the two rear wheels 106 in a manner similar to some existing zero turning radius (ZTR) riding lawn mowers. That is, the propulsion system may include a separate wheel motor 104 for each of the left and right rear wheels 106, so that the speed and direction of each rear wheel may be independently controlled. Additionally or alternatively, the front wheels 108 may be actively steerable by a propulsion system (e.g., including one or more steering motors 105) to assist in controlling the direction of the lawn mower 100, and / or may be driven by the propulsion system (i.e., to provide a front-wheel drive or all-wheel drive lawn mower).
[0029] A tool (e.g., a mowing element, such as a blade 110) can be coupled to a cutting motor 112 (e.g., a tool motor) carried by the housing 102. When the motors 112 and 104 are energized, the mower 100 can be propelled on the ground 103 so that vegetation (e.g., grass) passed by the mower is cut by the blade 110. Although shown herein as using only a single blade 110 and / or motor 112, within the scope of the present disclosure, a mower including multiple blades powered by a single or multiple motors is contemplated. In addition, although described herein in the context of one or more conventional "blades", other cutting elements are certainly possible without departing from the scope of the present disclosure, including, for example, discs, nylon rope or wire elements, knives, cutting reels, etc. Further, embodiments combining various cutting elements are also contemplated, for example, a rotating blade with an edge-mounted string trimmer.
[0030] The lawn mower 100 may also include a power source, which in one embodiment is a battery 114 having a lithium-based chemistry (e.g., lithium-ion). Other embodiments may utilize batteries of other chemistries, or utilize other power source technologies entirely (e.g., solar, fuel cells, internal combustion engines) without departing from the scope of the present disclosure. It should also be noted that while shown as using separate blade motors and wheel motors, such a configuration is merely exemplary, as embodiments are also contemplated in which a single tool motor provides blade and wheel power.
[0031] The lawn mower 100 may also include one or more sensors to provide location data. For example, some embodiments may include a global positioning system (GPS) receiver 116 (or other location sensor that can provide similar data) that is suitable for estimating the position of the lawn mower 100 within the working area and providing such information to the controller 120 (described below). In other embodiments, one or more of the wheels 106, 108 may include an encoder 118 that provides rotation / speed information of the wheel that can be used to estimate the position of the lawn mower within a given working area (e.g., based on an initial starting position). The lawn mower 100 may also include a sensor 115 that is suitable for detecting boundary lines, which can be used with other navigation techniques described herein.
[0032] The lawn mower 100 may include one or more front obstacle detection sensors 130 and one or more rear obstacle detection sensors 132, as well as other sensors, such as side obstacle detection sensors (not shown). The obstacle detection sensors 130, 132 may be used to detect obstacles in the path of the lawn mower 100 when the lawn mower 100 is moving in a forward direction or a reverse direction, respectively. The lawn mower 100 is capable of mowing while moving in either direction. As shown, the sensors 130, 132 may be located at a front portion 134 and a rear portion 136 of the lawn mower 100, respectively.
[0033] The sensors 130, 132 may use contact sensing, non-contact sensing, or both types of sensing. For example, depending on the state of the lawn mower 100 (e.g., within a zone or moving between zones), both contact sensing and non-contact sensing may be enabled, or only one type of sensing may be used. An example of contact sensing includes the use of a contact bumper protruding from the housing 102, or the housing itself, which may detect when the lawn mower 100 contacts an obstacle. Non-contact sensors may sometimes use sound waves or light waves to detect obstacles at a distance from the lawn mower 100 before contact with the obstacle (e.g., using infrared, radio detection and ranging (radar), light detection and ranging (lidar), etc.).
[0034] The lawn mower 100 may include one or more vision-based sensors to provide positioning data, such as position, orientation, or speed. The vision-based sensors may include one or more cameras 133 that capture or record images for use by the vision system. The cameras 133 may be described as part of the vision system of the lawn mower 100. The types of images include, for example, training images and / or operational images.
[0035] One or more cameras 133 may be used to determine ambient lighting parameters based on exposure time. One or more cameras 133 may change the exposure time until a sufficient or good image is captured. The ambient lighting parameters may be determined based on the exposure time corresponding to a good image. The ambient lighting parameters may be based on an average of exposure times taken by different cameras 133, an average of exposure times taken at different times using one or more cameras, or both.
[0036] Additionally or alternatively, one or more cameras 133 may include a photometer or may be supplemented by a separate photometer. The camera and photometer may be used to determine an ambient lighting parameter indicating the ambient light level of the surroundings of the lawn mower 100, which light level may be measured in Lux. The ambient lighting parameter may be based on an average value from one or more cameras or photometers.
[0037] In some embodiments, the ambient lighting parameter may be a predetermined value or a nominal value. For example, the ambient lighting parameter may be a factory setting representing a nominal or worst case lighting condition.
[0038] Ambient lighting parameters may also be determined based on the time of day. The relationship between ambient lighting parameters and time of day may be based on factory settings, or calibrated based on exposure time or other lighting measurements.
[0039] One or more cameras 133 may be capable of detecting visible light, invisible light (e.g., infrared light), or both. Any suitable total field of view may be used. In some embodiments, one or more cameras 133 may establish a total field of view greater than or equal to 30 degrees, 45 degrees, 60 degrees, 90 degrees, 120 degrees, 180 degrees, 270 degrees, or 360 degrees relative to a horizontal plane around an autonomous machine (e.g., lawn mower 100). In some embodiments, one or more cameras 133 may establish a total field of view less than or equal to 360 degrees, 270 degrees, 180 degrees, 120 degrees, 90 degrees, 60 degrees, 45 degrees, or 30 degrees relative to a horizontal plane around an autonomous machine. The field of view may be defined in a horizontal direction, a vertical direction, or both. For example, the total horizontal field of view may be less than or equal to 360 degrees, and the total vertical field of view may be 45 degrees. In some embodiments, the total field of view may be described in a three-dimensional (3D) geometry, such as a steradian. For example, the total field of view may be less than or equal to 4π steradian. The field of view may capture image data above and below the height of the one or more cameras 133 .
[0040] In some embodiments, the lawn mower 100 includes four cameras 133. One camera 133 may be positioned in each of one or more directions including a forward direction, a rearward direction, a first lateral direction, and a second lateral direction (e.g., relative to a base direction of the lawn mower 100). One or more camera directions may be positioned orthogonal to one or more other cameras 133 or positioned opposite to at least one other camera 133. The cameras 133 may also be offset from any of these directions (e.g., at 45 degrees or other non-perpendicular angles).
[0041] The lawn mower 100 may be directed along the path, for example, manually using the handle assembly 90. In particular, the manual direction of the lawn mower 100 may be used during a training mode to learn a work area or boundaries associated with a work area.
[0042] The camera 133 positioned in the forward direction may have a position and orientation that represents the pose of the autonomous machine. In some embodiments, the position and orientation of the camera may be defined relative to the geometric center of the lawn mower 100 or relative to one of the boundaries of the lawn mower 100 .
[0043] As used herein, the term "posture" refers to position and orientation. Posture can be a six-degree-of-freedom posture (6DOF posture), which can include all position and orientation parameters of three-dimensional space. Posture data can include three-dimensional position and three-dimensional orientation. For example, the position can include at least one position parameter selected from the following: x-axis coordinate, y-axis coordinate and z-axis coordinate (for example, using a Cartesian coordinate system). Any appropriate angular orientation representation can be used. Non-limiting examples of angular orientation representation include yaw, pitch and roll representation, Rodrigues representation, quaternion representation and direction cosine matrix (DCM) representation, which can be used alone or in combination. In one example, orientation can include at least one orientation parameter selected from yaw (for example, vertical z-axis orientation), pitch (for example, lateral y-axis orientation) and roll (for example, longitudinal x-axis orientation).
[0044] The sensors of the lawn mower 100 may also be described as vision-based sensors and non-vision-based sensors. Vision-based sensors may include a camera 133 capable of recording images. The images may be processed and used to construct a three-dimensional (3D) point cloud or for optical distance measurement (e.g., optical encoding). Non-vision-based sensors may include any sensor other than the camera 133. For example, a wheel encoder that detects wheel revolutions using optical (e.g., photodiode), magnetic, or capacitive sensing may be described as a non-vision-based sensor that does not use a camera. Wheel encoding data from the wheel encoder may also be described as distance measurement data.
[0045] Optical encoding may be used by taking a series or burst of images and comparing features in the images to determine or estimate the distance traveled between images. Optical encoding may be less susceptible to wheel slip than wheel encoders used to determine distance or speed.
[0046] In addition to the sensors described above, other sensors now known or later developed may also be incorporated into the lawn mower 100 .
[0047] The lawn mower 100 may also include a controller 120 adapted to monitor and control various lawn mower functions. The controller 120 may include a processor 122 that receives various inputs and executes one or more computer programs or applications stored in a memory 124. The memory 124 may include computer-readable instructions or applications that, when executed, for example, by the processor 122, cause the controller 120 to perform various calculations and / or issue commands. That is, the processor 122 and the memory 124 may together define a computing device operable to process input data and generate desired outputs to one or more components / devices. For example, the processor 122 may receive various input data including position data from a GPS receiver 116 and / or an encoder 118, and generate speed and steering angle commands to one or more drive wheel motors 104 to rotate the drive wheels 106 (at the same or different speeds and in the same or different directions). In other words, the controller 120 may control the steering angle and speed of the lawn mower 100 and the speed and operation of the cutting blades.
[0048] Reference may be made herein to various parameters, data, or data structures that may be processed in the controller 120 , such as by being processed by the processor 122 or stored in or retrieved from the memory 124 .
[0049] The controller 120 may use the processor 122 and the memory 124 in a variety of different systems. Specifically, one or more processors 122 and memories 124 may be included in each of the different systems. In some embodiments, the controller 120 may at least partially define a vision system, which may include the processor 122 and the memory 124. The controller 120 may also at least partially define a navigation system, which may include a processor 122 and a memory 124 separate from the processor 122 and the memory 124 of the vision system.
[0050] Each system may also be described as having its own controller 120. For example, the vision system may be described as including one controller 120, and the navigation system may be described as having another controller 120. Thus, the lawn mower 100 may be described as having multiple controllers 120. In general, as used herein, the term "controller" may be used to describe a component of a "system" that provides commands to control various other components of the system.
[0051] In view of the above, it is apparent that the functionality of the controller 120 may be implemented in any manner known to those skilled in the art. For example, the memory 124 may include any volatile, non-volatile, magnetic, optical, and / or electrical media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically erasable programmable ROM (EEPROM), flash memory, and / or any other digital media. Although shown as both the memory 124 and the processor 122 being included in the controller 120, the memory 124 and the processor 122 may be included in separate modules.
[0052] The processor 122 may include any one or more of the following: a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), and / or equivalent discrete or integrated logic circuits. In some embodiments, the processor 122 may include multiple components, such as one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, and / or one or more FPGAs, as well as any combination of other discrete or integrated logic circuits. The functions attributed to the controller 120 and / or the processor 122 herein may be implemented as software, firmware, hardware, or any combination thereof. Certain functionality of the controller 120 may also be performed using an Internet-connected cloud computing system or other distributed computing system that is operably connected to the processor 122.
[0053] exist Figure 1 , schematic connections between the controller 120 and the battery 114, one or more wheel motors 104, the blade motor 112, the optional boundary line sensor 115, the radio device 117, and the GPS receiver 116 are generally shown. The above interconnections are exemplary only, as the various subsystems of the lawn mower 100 can be connected in almost any manner, such as directly connected to each other, wirelessly connected, connected through a bus architecture (e.g., a controller area network (CAN) bus), or through any other connection configuration that permits data and / or power to be transferred between the various components of the lawn mower. Although connections to some sensors 130, 132, 133 are not shown, these sensors and other components of the lawn mower 100 can be connected in a similar manner. The radio device 117 can be connected via a cellular or other wide area network (e.g., even via the Internet), a local area network (e.g., an IEEE 802.11 "Wi-Fi" device), or a point-to-point (P2P) (e.g., BLUETOOTH TM) network to communicate with a separate user interface device 119 (e.g., a mobile device, such as a smart phone, tablet, desktop or wearable computer, etc.). In turn, the user interface device 119 can communicate with other devices through a similar network, for example, it can be used to connect the lawn mower 100 to the Internet.
[0054] The user interface device 119 may or may not be coupled to the lawn mower 100. In some embodiments, the user interface device 119 may be used to provide user input or commands from a user to the lawn mower 100. In some embodiments, the user interface device 119 may be used to provide instructions to the user, such as a visual presentation on a graphical user interface (e.g., a screen or touch screen).
[0055] In some embodiments, various functions of the one or more controllers 120 described herein may be offloaded from the lawn mower 100. For example, the recorded images may be transmitted to a remote server (e.g., in the cloud) and the images processed or stored using the radio 117. The stored images or other processed data may be received using the radio 117 and stored on the lawn mower 100 or further processed by the lawn mower 100.
[0056] In general, the controller 120 and various components or systems of the lawn mower 100 may be used to perform the various functions described herein. Figure 2 Some examples of systems of lawn mower 100 are shown in FIG.
[0057] Figure 2 Shows Figure 1 1 , an overview of the various systems of the lawn mower 100, including a vision system 150, a navigation system 152, and a propulsion system 154. Although all of the systems 150, 152, 154 are shown as an integral part of the lawn mower 100, in some embodiments, some or all of each system may also be located outside the lawn mower 100. The vision system 150 can be operably coupled to the navigation system 152, and the navigation system 152 can be operably coupled to the propulsion system 154. The lawn mower 100 can use any suitable navigation technology. In some embodiments, navigation technologies such as those described in U.S. Patent Application No. 16 / 534,515 filed on August 7, 2019 and U.S. Provisional Application No. 62 / 831,347 filed on April 9, 2019, which are incorporated herein by reference, can be used.
[0058] The sensors of the navigation system 152 may record non-vision-based data during the training mode, while the vision system 150 records images, such as training images. Although the lawn mower 100 may be manually operated by a user, in some embodiments, the navigation system 152 may autonomously guide the machine during the training mode. The vision system 150 may include one or more cameras to record or capture images. In some embodiments, a controller of the vision system 150 may provide position and / or orientation data to the navigation system 152 based on the recorded images, which may facilitate navigation of the lawn mower 100. For example, the vision system 150 may provide an estimated position and / or orientation of the lawn mower 100 to the navigation system 152 based on the vision-based sensor data.
[0059] In some embodiments, the navigation system 152 may navigate primarily using a position and / or orientation based on non-visual sensor data. For example, the non-visual sensor data may be based on output from an inertial measurement unit or a wheel encoder. During training mode and / or offline mode, for example, the controller of the navigation system 152 may use non-visual sensor data and visual data to determine boundaries for subsequent navigation of the autonomous machine in the work area. During online mode, for example, the controller of the navigation system 152 may determine a posture based on visual posture data, non-visual posture data, or both. In some embodiments, a posture may be determined based on non-visual sensor data and updated based on visual posture data, which may be described as visual-based positioning. The navigation system 152 may compare data from various sensors to correct errors and update positions, which may be described as sensor fusion. For example, a visual-based position and / or orientation may be compared with a non-visual-based position and / or orientation. In some embodiments, sensor data other than visual-based sensor data (such as GPS data) may be used to correct errors and update positions.
[0060] The navigation system 152 can extract feature data from images captured by the vision system 150. Feature data can be extracted from training images to provide training feature data. Using the training feature data, the navigation system 152 can generate a three-dimensional point cloud (3DPC) and associated data to represent the work area, which associated data may include multiple 6DOF postures of the autonomous machine. The 3DPC and posture can be recorded in a navigation map. Optionally, non-visual-based data such as GPS data, IMU data, and distance data can also be recorded in a real-world coordinate system, such as a coordinate system of a map based on the earth. Feature data can be extracted from the operating image and compared with the training feature data, which can be described as feature matching. During operation, comparison of the operating feature data with the training feature data can be used to identify the position and / or orientation of the autonomous machine for navigation.
[0061] As used herein, the term "feature" refers to two-dimensional (2D) data obtained from one or more points (particularly key points or points of interest) identified in a two-dimensional image. Features can be identified and extracted in an image using a feature detector algorithm. Depending on the specific autonomous machine and application, any appropriate feature detector algorithm available to a person of ordinary skill in the art can be used. In some embodiments, each special feature refers only to a point or point of interest in an image or 3DPC. Features can be stored as feature data containing coordinates defined relative to an image frame. In some embodiments, feature data may also include descriptors applied to, associated with, or corresponding to features. The term "feature data" refers to a data structure representing a feature, and may include a two-dimensional position and a multi-dimensional descriptor (e.g., two-dimensional or three-dimensional).
[0062] Key points for identifying features can be extracted from various objects in the image. In some embodiments, the object can be permanent, temporary, or both. In some embodiments, the object can be natural, artificial, or both. An example of a permanent feature is the corner of a house. An example of a natural feature is the edge of a tree trunk. Some examples of temporary features and artificial features include targets on stumps and trees in the ground. Artificial features can be temporarily placed and used to increase the feature density in the working area (for example, to improve the low-quality part of 3DPC). Artificial features can be energized, and, for example, can include a light emitter of visible light or invisible light that can be detected by a camera. Artificial features can not be energized, and, for example, can include visible patterns or invisible patterns that can be detected by a camera. Some artificial features can be permanently placed. As used herein, the term "invisible" refers to light that emits or reflects wavelengths that are invisible to the human eye, but it can emit or reflect wavelengths that are visible to a camera (such as an infrared camera on an autonomous machine).
[0063] As used herein, the term "descriptor" refers to two-dimensional data generated by a descriptor algorithm. A descriptor describes a feature in the context of an image. In some embodiments, a descriptor may describe pixel values in an image, image gradients, scale space information, or other data near or around a feature. For example, a descriptor may include an orientation vector for a feature or may include an image patch. Depending on the particular autonomous machine or application, any appropriate descriptor algorithm for providing the context of a feature in an image available to one of ordinary skill in the art may be used. The descriptor may be stored as part of the feature data.
[0064] Any suitable technique may be used for extracting features from an image, which may include or utilize algorithms such as Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Oriented FAST and Rotated Brief (ORB), KAZE, Accelerated KAZE (AKAZE), linear feature tracking, camera fusion, loop closure, incremental structure from motion, or other suitable algorithms. Such algorithms may, for example, provide one or more features and associated descriptors.
[0065] Feature matching may be performed using any suitable technique, which may include or utilize algorithms such as Brute-Force, Approximate Nearest Neighbor (ANN), and Fast Library for Approximate Nearest Neighbor (FLANN). A Brute-Force algorithm may match features by selecting a feature and examining all other features for matching.
[0066] As used herein, the term "three-dimensional point cloud", "3D point cloud" or "3DPC" is a data structure representing or containing three-dimensional geometric points corresponding to features extracted from an image. The 3DPC can be associated with various attributes such as pose. In some embodiments, the geometric points and pose may or may not be defined in a coordinate system based on an arbitrary reference system. In some embodiments, the 3DPC may or may not be associated with real-world scale, orientation, or both, for example, until a mapping process has been performed. The 3DPC can be generated based on feature matching data. A chart or visual map can be generated based on the 3DPC to provide a human-visible representation of the 3DPC.
[0067] The 3DPC may be generated using any suitable technique, which may include or utilize algorithms such as Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM), any of which may be used with various embodiments of the present disclosure, for example, depending on the particular autonomous machine and application.
[0068] The controller of the navigation system 152 can command the propulsion system 154 based on the updated attitude. For example, the corrected or updated position or orientation can be used by the navigation system 152 to provide propulsion commands to the propulsion system 154. The propulsion system 154 (e.g., propulsion hardware) can be defined as including, for example, the motors 112, 104 and the wheels 106, 108 ( Figure 1) or any associated drivers (e.g., motor controllers or microchips).
[0069] Figure 3 A top view conceptual diagram of some features of a navigation map 200 of a work area 202 is shown. The work area 202 may be described as an area in which an autonomous machine, such as a lawn mower 100, operates to perform certain tasks. For example, the work area 202 of the lawn mower 100 may include a yard or other grassy area. The navigation map 200 may define certain navigation constructs, such as regions and boundaries, relative to the work area 202. The navigation map 200 may be generated, for example, by the navigation system 152 ( Figure 2 ) is used to facilitate navigation, and is used by the user interface device 119 to show some or all of the navigation map to the user and to receive user input related to the navigation map.
[0070] The navigation map 200 may define one or more areas and associated boundaries for different purposes. In some embodiments, the navigation map 200 may define one or more enclosed areas, such as enclosed areas 204, 206, within the work area 202. An enclosed area may be described as an area in which the lawn mower 100 operates to perform a task. For example, the lawn mower 100 may perform a task of cutting all grass in an enclosed area. During operation, the lawn mower 100 may be directed to move within the boundaries of the enclosed area for a period of time, without, for example, crossing or intersecting the boundaries of the enclosed area.
[0071] In some embodiments, an enclosure may be described as a static enclosure that does not change as the mower 100 operates, such as enclosure 204. In some embodiments, an enclosure may be described as a dynamic enclosure that changes as the mower 100 operates, such as enclosure 206. An example of a dynamic enclosure is a moving enclosure as described in U.S. Provisional Application No. 62 / 588,680 (Ingvalson et al.), filed on November 20, 2017, and U.S. Provisional Application No. 62 / 599,938 (Ingvalson et al.), filed on December 18, 2017, which are incorporated herein by reference. A moving enclosure may be used to cover the trained enclosure 206.
[0072] In some embodiments, the navigation map 200 may define one or more exclusion areas and associated boundaries, such as exclusion area 208, within the work area 202. The exclusion area may represent an area in the work area 202 that the lawn mower 100 is to avoid or move around. For example, the exclusion area 208 may include obstacles (such as a landscaped garden) or problem areas (such as a steep slope). In an exemplary embodiment, the exclusion area 208 includes a building, such as a house. The exclusion area may be defined within an enclosure. During operation, the lawn mower 100 may be directed to move within the enclosure for a period of time without, for example, crossing or intersecting with the exclusion area boundary.
[0073] In some embodiments (not shown), the navigation map 200 may define one or more transfer areas, which may also be described as transfer paths. Typically, a transfer area is a regional path connecting two other areas, such as connecting two different enclosed areas. Maintenance tasks may or may not be performed in a transfer area. For example, the lawn mower 100 may not mow in a transfer area. In an example involving a yard divided by a driveway, the transfer area may include the entire driveway, or at least include a path across the driveway, which is located between two lawns of the lawn that the lawn mower 100 is to cross.
[0074] In some embodiments, the position and / or orientation of the lawn mower 100 may be estimated or determined based on non-visual sensor data. Uncertainty may be associated with the determined position and / or orientation. The uncertainty of the position and / or orientation may be represented by an uncertainty region 212 near the lawn mower 100. The uncertainty region 212 may correspond to a possible position of the lawn mower 100 in the navigation map 200, for example, estimated or determined based on probability. Although the uncertainty is shown and described as an area, any suitable parameter indicating the uncertainty region 212 may be used, such as one or more of an uncertainty radius or a distance.
[0075] In an exemplary embodiment, the uncertainty region 212 is represented as a circle. The circle can represent a uniform radius around the lawn mower 100, which can be used as an estimate in simple cases or when the uncertainty is evenly distributed around the lawn mower. In some embodiments (not shown), the uncertainty region 212 can have a different shape, and the lawn mower 100 may not be located at the centroid of the uncertainty region. For example, the uncertainty region 212 can have an elliptical or oval shape. The uncertainty region 212 can be determined using various sensors of the lawn mower 100, which can be used to provide error correction. The uncertainty region 212 can also be determined relative to the navigation map 200.
[0076] In some embodiments, the uncertainty region 212 can be determined based on the error correction given by the sensors of the lawn mower 100 and how the lawn mower is moving. For example, if the lawn mower 100 is measuring distance in the forward direction, the error in front of the lawn mower may be smaller due to constant measurement. The lateral error may increase as the lawn mower 100 moves until the lawn mower turns and measures the distance to the side to eliminate the error. The error can be described as an error relative to the position of the lawn mower 100 in the navigation map 200. In the case of turning to eliminate the error by moving, the error ellipse may not turn with the lawn mower 100. The uncertainty region 212 can be defined based on the coordinates of the navigation map 200. Turning the lawn mower 100 can allow the error to drop along different axes of the navigation map 200.
[0077] Over time, as the lawn mower 100 operates and traverses the work area 202, the accuracy of the determined position and / or orientation may become less certain or more uncertain, which may also be described as drift. As a result, the calculated uncertainty region 212 may increase. In the exemplary embodiment, the lawn mower 100 is shown traversing from a first position 210a to a second position 210b to a third position 210c. The uncertainty region 212 covers a first area at the first position 210a, a second area that is larger than the first area at the second position 210b, and a third area that is larger than the second area at the third position 210c.
[0078] The posture data based on vision can be used to update the posture to reduce the uncertainty region 212. For example, the posture can be updated based on the uncertainty region 212 and the uncertainty region threshold. Specifically, the uncertainty region 212 can be compared with the uncertainty region threshold. When the uncertainty region 212 exceeds the uncertainty region threshold, the lawn mower 100 can initiate a vision-based positioning process. Figure 4 As can be seen in FIG. 1 , the uncertainty region 212 (A) along the y-axis is shown to increase with time (t) along the x-axis until the uncertainty region threshold 250 is reached at time 252. After time 252, the uncertainty region 212 can be significantly reduced. The vision-based localization process can be described as using vision-based pose data independently or in combination with other non-vision-based pose data to determine and update the pose of the lawn mower 100. As long as the uncertainty region 212 exceeds the uncertainty region threshold during operation, the lawn mower 100 can repeat the vision-based localization process.
[0079] In some embodiments, the uncertainty region 212 may not be completely reduced with each positioning attempt. Some vision-based positioning may only partially reduce the uncertainty region 212. In response, the lawn mower 100 may initiate the next vision-based positioning more quickly, or may initiate vision-based positioning more frequently.
[0080] The ability to use vision-based positioning may depend on the visibility of the mower 100. For example, during the day, the mower 100 may be able to locate at a particular location, but may not be able to locate at the same location at night when less ambient light is available. The visibility of the mower 100 may be represented by a feature detection range. The feature detection range may be described as a maximum distance or target distance at which the mower 100 is able to detect a feature, which may change based on the ambient lighting. For example, during the day, the mower 100 may be described as having a first feature detection range 214, and at night or in low lighting, the mower 100 may be described as having a second feature detection range 216 that is less than the first feature detection range. In an exemplary embodiment, when the mower 100 is in the fourth position 210d, the feature 218 is within the first feature detection range 214 and the second feature detection range 216. When the mower 100 is in the fourth position 210d, the feature 220 is within the first feature detection range 214, but outside the second feature detection range 216. Each of the features 218 , 210 is schematically illustrated with an “x”.
[0081] Typically, feature detection ranges, such as feature detection ranges 214, 216, can be determined based on ambient lighting parameters that indicate the light level of the surrounding environment. In one example, one or more camera exposure times can be used to indicate the light level. In another example, one or more luminance readings from one or more photometers can be used to indicate the light level. In some embodiments, the ambient lighting parameters can be based on nighttime ambient lighting parameters. In one example, the nighttime ambient lighting parameters can correspond to predetermined ambient lighting at night, which can be a nominal value or a default value corresponding to the worst-case ambient lighting. In another example, the nighttime ambient lighting parameters can correspond to, for example, measured values in the work area 202 at night using one or more camera exposure times. In some embodiments, the ambient lighting parameters can correspond to measured values in the work area 202 during a day, for example based on one or more camera exposure times during a day.
[0082] The lawn mower 100 can be used to determine which positions and / or orientations within the work area 202 are locatable. Whether a particular position and / or orientation is locatable can depend on a feature detection score for the particular position and / or orientation. The feature detection score can be determined for a particular feature detection score based on the quality of features that can be extracted from an image captured by the lawn mower 100 at the particular position and / or orientation, the number of features, or both. If the feature detection score exceeds a minimum threshold, then it can be determined that the particular position and / or orientation is locatable. The minimum threshold can be determined based on a calculated probability that the lawn mower 100 will be able to locate at a particular position and / or orientation, or can correspond to the calculated probability, such as 50%, 60%, 70%, 80%, 90%, 95%, 99%, or even 100%.
[0083] The feature detection score may be determined based on the quality of the features within the feature detection range, the number of features, or both. In response to the number of features within the feature detection range exceeding a minimum features to be located (MFL) threshold, a particular position and / or orientation may be determined to be locatable. The MFL threshold may be any suitable number, such as one, two, three, four, or more features detectable by the lawn mower 100. In some embodiments, the MFL threshold may be in the single digits, tens, or even hundreds. In an exemplary embodiment, for example, if the MFL is three or less, the fourth position 210d may be determined to be a locatable position at night (as shown, three features 218 are within the second feature detection range 216, which may correspond to nighttime).
[0084] A heat map based on the feature detection scores may be determined relative to the navigation map 200 and stored in the navigation map 200. The heat map based on the feature detection scores may change over time and as ambient lighting parameters change.
[0085] The navigation map 200 may include an area within the enclosed area 204 indicating where the lawn mower 100 can be located under certain conditions. For example, the location area may be determined based on a position and / or orientation in which the feature detection score exceeds a minimum threshold for a specific feature detection range. In an exemplary embodiment, the navigation map 200 includes a location area 222. The location area 222 is determined based on a second detection range 216 associated with nighttime or low lighting. The location area 222 may represent an area outside the exclusion area 208 where the lawn mower 100 can be located when operating at night. Typically, each position and / or orientation may have a corresponding feature detection score. The feature detection score may be uniform or non-uniform throughout the location area 222. For example, the feature detection score may be higher in the following position and / or orientation of the lawn mower 100: one or more cameras face a building in the exclusion area 208 and capture a large number of features.
[0086] In some embodiments, the size and / or shape of the localization area 222 may change based on changes in the feature detection range 216. The feature detection range 216 may change, for example, due to changes in the minimum threshold or changes in ambient lighting parameters. In some embodiments, where ambient lighting parameters are measured, the feature detection range 216 and / or localization area 222 may change between operations or even during operations (night to night or as the night progresses), for example, due to different lighting conditions caused by moonlight, shadows, and other factors.
[0087] The navigation map 200 may include one or more buffer areas and associated boundaries. When vision-based positioning may be more limited (such as at night or low lighting), the buffer area may be helpful in guiding the lawn mower 100. Using the buffer area can allow the lawn mower 100 to operate externally in an area away from other boundaries outside the positioning area 222. In some embodiments, the buffer area may be adjacent to the boundary of the enclosed area and inside the boundary of the enclosed area. In an exemplary embodiment, the buffer area 224 is adjacent to the boundary of the enclosed area 204 and inside the boundary. Although not shown, in some embodiments, the boundary of the buffer area can be defined as adjacent to the boundary of the exclusion area (such as the exclusion area 208) and outside the boundary. Typically, the buffer area is along some or all of the boundaries of the area that is not close to, adjacent to, or intersecting with the positioning area 222.
[0088] For example, at night or in low lighting, the mower 100 may be restricted to portions of the enclosed area 204 that do not overlap with the exclusion zone 208 and the buffer zone 224. In some embodiments, at night or in low lighting, the mower 100 may be permitted to operate only outside the boundaries of the exclusion zone 208 and inside the boundaries of the buffer zone 224. During daytime hours when the mower can be positioned anywhere in the enclosed area, the mower 100 may be permitted to operate only outside the boundaries of the exclusion zone 208 and inside the boundaries of the enclosed area 204.
[0089] A buffer distance may be determined and used to position a boundary of the buffer area outside of the locate area 222. In some embodiments, the boundary of the buffer area may be spaced apart from the boundary of the locate area 222 by the buffer distance. In some embodiments, the boundary of the buffer area may be spaced apart from the boundary of the enclosure area 204 by the buffer distance. The buffer area 224 may be defined between the buffer area boundary and the boundary of the enclosure area 204. When a moving enclosure area (such as the moving enclosure area 206) is used, the moving enclosure area may be initially defined to include or increase to include an area in the locate area 222 and an area outside the locate area that does not overlap with the buffer area 224. Generally, the uncertainty area 212 may extend beyond the moving enclosure area 206, but not beyond the enclosure area 204.
[0090] The buffer distance may be determined based on a minimum or nominal distance between vision-based fixes. In some embodiments, the minimum distance between vision-based fixes may be determined based on a predetermined factory setting for the performance of a particular autonomous machine and / or based on a particular work area. For example, the distance between vision-based fixes may be calculated based on wheel encoder data and / or IMU data, which may be described as dead reckoning. In some embodiments, the buffer distance may be determined based on a fraction or percentage of the minimum distance between vision-based fixes. The buffer distance may be less than the minimum distance between vision-based fixes.
[0091] In some embodiments, the buffer distance can also be determined based on the ambient lighting parameter. For example, a buffer distance based on the minimum distance between vision-based positioning can be added in response to the ambient lighting parameter indicating low lighting. In general, the buffer distance can be increased in response to the ambient lighting parameter indicating lower available light (e.g., based on increased exposure time).
[0092] Figure 5 1 is a flow chart illustrating one example of a method 300 for generating a navigation map including one or more positioning areas and one or more buffer areas, such as used during a training mode of a lawn mower 100. An initial navigation map 302 may be determined. The navigation map may be generated based on a 3DPC representing a working area. The navigation map may include one or more enclosed area boundaries defined relative to the 3DPC and optionally one or more exclusion areas.
[0093] One or more feature detection ranges may be determined 304. A feature detection range may be determined for daytime operation, and another feature detection range may be determined for nighttime operation.
[0094] The feature detection range may be based on an ambient lighting parameter. The ambient lighting parameter may be based on, for example, a nighttime or daytime ambient lighting parameter. The nighttime ambient parameter may be based on a predetermined ambient lighting at night (e.g., a worst case or nominal value) or a measured ambient lighting at night in a work area.
[0095] One or more feature detection scores 306 may be determined for one or more locations and / or orientations. The feature detection score may be based on a particular feature detection range. In some embodiments, the feature detection score may be determined based at least on a feature detection range corresponding to nighttime operation. Typically, a larger feature detection range may result in the ability to detect more features in the navigation map.
[0096] Locatable positions and / or orientations in the navigation map may be determined 308. The locatable positions and / or orientations may be based on a corresponding feature detection score for each position and / or orientation being above a minimum threshold.
[0097] One or more positioning areas 310 may be determined. The positioning areas may be determined based on the locatable positions and / or orientations. In some embodiments, the positioning areas may include locatable positions and / or orientations having feature detection scores above a minimum threshold. The navigation map may be updated in response to determining one or more positioning areas.
[0098] One or more buffer areas 312 may be determined. At least one buffer area may be adjacent to and within the boundaries of the enclosed area, or adjacent to and outside the boundaries of the excluded area. In some embodiments, the buffer area may be determined based on the boundaries of the location area and a buffer distance, which may be described as an offset. In some embodiments, the buffer area may be determined based on the boundaries of the enclosed area or the boundaries of the excluded area and a buffer distance. The buffer distance may be determined based on a fraction of the minimum distance between locations, an ambient lighting parameter, or both. The navigation map may be updated in response to determining the one or more buffer areas.
[0099] An operational schedule may be determined using the navigation map to cover the work area 314. The operational schedule of the lawn mower may be determined automatically, based on user input, or a combination of both. Any suitable technique may be used to determine the operational schedule of the autonomous lawn mower, such as those described in U.S. Provisional Application No. 62 / 822,342 filed on March 22, 2019, which is incorporated herein by reference.
[0100] In some embodiments, the navigation map 200 may be displayed to the user, for example, using the user interface device 119, which includes a visual representation of the enclosed area, any exclusion areas, any positioning areas, and any buffer areas. The buffer areas may indicate where the mower cannot mow at night and must mow during the day. For example, depending on the mode of the mower, areas outside the positioning areas within the enclosed area may also indicate where the mower cannot mow at night and must mow during the day.
[0101] In some embodiments, a nighttime schedule for autonomous operation may be determined. The nighttime schedule may include coverage of the positioning area and may not include a buffer area. A daytime schedule for autonomous operation may be determined based on the nighttime schedule. The daytime schedule for autonomous operation may include at least a buffer area. Typically, the coverage of the daytime and nighttime schedules may be determined to complement each other to cover the work area within a specific time period. In some embodiments, the coverage of daytime operation and nighttime operation may overlap in some areas within the work area, which may help resolve uncertainty in the position and / or orientation of the lawn mower.
[0102] In some embodiments, in response to determining that the daytime schedule and nighttime schedule for autonomous operation cannot cover the work area within a specific time period, a notification may be provided to the user, for example, on the user interface device 119. For example, the user may limit the time of day allowed for mowing such that the buffer area cannot be covered. For example, the user interface device 119 may request that the user increase the specified time period to cover the work area, or increase the amount of time that can be used for operation during the day.
[0103] The lawn mower 100 may utilize the positioning area and the buffer area in different operating modes.
[0104] In one operating mode, which may be described as a restricted mode, evening mode, or night mode, the lawn mower 100 may only operate within a localized area, for example, when light levels do not exceed a light threshold.
[0105] In another operating mode, which may be described as a dynamic restricted mode, a dynamic evening mode, or a dynamic night mode, the mower 100 may operate within an enclosed area including the locating area and outside the locating area excluding the buffer area. In another operating mode, which may be described as a dynamic mode, the mower 100 may operate within a restricted enclosed area (excluding the buffer area) without a locating area, for example, when the light level exceeds a light threshold indicating daylight conditions, or when it is determined that there is no locating area or that a locating area is unavailable. The mower 100 may use any one or more of these operating modes, which may be factory set, user selected, or otherwise determined by the mower.
[0106] Figure 6 3 is a flow chart showing an example of a method 320 for navigating within a positioning area, which may be used in a restricted mode, a night mode, or a night mode for low light conditions. The method 320 may include switching to a restricted mode of operation 322. One or more positioning areas and associated boundaries may be defined within an enclosed area in a navigation map, which may be predetermined during a training mode (see FIG. 3 ). Figure 5). One or more exclusion zones and associated boundaries may also be defined within an enclosed region in the navigation map. The positioning region may be defined based on ambient lighting parameters. In some embodiments, the ambient lighting parameters may be used to determine feature detection ranges and associated feature detection scores for one or more locations and / or orientations in the working area. The feature detection scores may be compared to a minimum threshold to determine a location and / or orientation within the positioning region.
[0107] In some embodiments, the localization area may be determined based on predetermined ambient lighting parameters, such as worst case lighting parameters at night. In other embodiments, the localization area may be determined based on measured ambient lighting parameters. The measured ambient lighting parameters may be determined in response to measuring nighttime ambient lighting in the work area. In some embodiments, the localization area may be updated in response to measuring ambient lighting.
[0108] In some embodiments, the mobile enclosed area can be used to improve the coverage of the enclosed area. The mobile enclosed area can overlap with the positioning area and the enclosed area outside the positioning area.
[0109] The machine may be directed to operate autonomously only in the positioning area 324. In some embodiments, a buffer area may or may not be determined or used.
[0110] During operation, the machine may monitor whether an uncertainty zone around the machine intersects a zone boundary of the navigation map or exceeds a minimum threshold 326. The machine may initiate positioning 328, for example, in response to determining that the uncertainty zone intersects a zone boundary or exceeds a minimum threshold. The machine may continue to operate autonomously in the positioning zone after positioning 324. The machine may also continue to operate autonomously in the positioning zone 324, for example, in response to determining that the uncertainty zone does not intersect a zone boundary and does not exceed a minimum threshold.
[0111] Figure 7 3 is a flow chart illustrating an example of a method 340 for navigating within an enclosed area using a positioning area and a buffer area, which can be used in a dynamic restricted, dynamic night, or dynamic night mode for low lighting conditions. The method 340 can include switching to a dynamic restricted mode of operation 342. One or more positioning areas and one or more buffer areas and associated boundaries can be defined within an enclosed area in a navigation map, which can be predetermined during a training mode (see FIG. 34 ). Figure 5). One or more exclusion zones and associated boundaries may also be defined within an enclosed region in the navigation map. The positioning region may be defined based on ambient lighting parameters. In some embodiments, the ambient lighting parameters may be used to determine feature detection ranges and associated feature detection scores for one or more locations and / or orientations in the working area. The feature detection scores may be compared to a minimum threshold to determine a location and / or orientation within the positioning region.
[0112] The machine can be directed to operate autonomously within an enclosed area 344, for example, within the positioning area and outside the positioning area except for the buffer area. The machine can also be directed to avoid one or more buffer areas during autonomous operation.
[0113] In some embodiments, the localization area may be determined based on predetermined ambient lighting parameters, such as worst case lighting parameters at night. In other embodiments, the localization area may be determined based on measured ambient lighting parameters. The measured ambient lighting parameters may be determined in response to measuring nighttime ambient lighting in the work area. In some embodiments, the localization area may be updated in response to measuring ambient lighting.
[0114] In some embodiments, the mobile enclosed area can be used to improve the coverage of the enclosed area. The mobile enclosed area can overlap with the positioning area and the enclosed area outside the positioning area except the buffer area.
[0115] The machine may monitor whether the uncertainty region intersects a boundary 346, such as a boundary of an enclosure, a positioning region, or a buffer region. The machine may determine whether the current position and / or orientation is locatable 350, for example, in response to determining that the uncertainty region intersects the boundary. The machine may monitor whether the uncertainty region exceeds a threshold 348, for example, in response to determining that the uncertainty region does not intersect the boundary. In other embodiments (not shown), the machine may continue to operate autonomously in the enclosure region 344, for example, in response to determining that the uncertainty region does not intersect the boundary.
[0116] In some embodiments, the determination 350 of whether the machine is in a locatable position and / or orientation can be based on whether the mower is in a locating area. In some embodiments, to determine whether the machine is in a locatable position and / or orientation 350, the machine can compare the current position and / or orientation to the locating area and determine whether the machine is in the locating area. The machine can perform locating 354, for example, in response to determining that the machine is in a locatable position and / or orientation.
[0117] For example, in response to determining that the current position and / or orientation of the machine is not in a position that can be located, the movement of the machine and / or any of its moving parts (e.g., a cutting tool) can be stopped 352. The stopping of moving parts such as cutting tools can help save energy and serve as a safety measure. The machine or one or more of its moving parts can be stopped until the machine can be located at the current position. It should be understood that stopping the machine in this case means that the machine does not have to continue to traverse the ground, for example, it does not have to continue forward movement or reverse movement with or without steering, but can still rotate in place to try to regain its position and / or orientation. The machine can take various actions when stopped, such as performing movements that do not significantly change the position but can help regain the position and / or orientation, such as rocking back and forth. In another embodiment, depending on the location of the machine, the machine can move a short distance away from the enclosure boundary in order to obtain a position update.
[0118] In one example, the machine may repeatedly attempt vision-based positioning until the machine is able to locate, which may involve rotation of the machine and / or the machine's sensor about a vertical axis while acquiring vision-based data. In some embodiments, the mower may increase one or more of exposure time, gain, and aperture size, which may facilitate vision-based positioning in low light conditions. The machine may additionally or alternatively activate a light source (e.g., visible light, infrared) that illuminates the field of view of the vision-based sensor to attempt to obtain vision-based positioning in low light conditions. In another embodiment, the machine may utilize a second vision-based sensor (e.g., a replacement camera) to replace or supplement the vision-based sensor used for initial positioning. The second vision-based sensor may be located at the same location as the first vision-based sensor, but of a different type (e.g., infrared spectrum versus visible spectrum). The second vision-based sensor may be located separately from the first vision-based sensor and be the same or different type. In another example, the machine may attempt to use at least one non-vision-based sensor (such as GPS) for non-vision-based positioning. For example, when the GPS receiver does not move for a certain amount of time (e.g., "soaking" the GPS), the GPS receiver can obtain more accurate geolocation accuracy, allowing the machine to be located sufficiently to move again. In some embodiments, the machine can attempt non-vision-based positioning in response to one or more unsuccessful attempts using vision-based positioning. After successfully positioning, the machine can continue to operate autonomously in the enclosed area 344. In one embodiment, after reacquisition, the machine can move towards an area of known good positioning (e.g., an area with positioning certainty below a threshold) to avoid further instances of positioning loss.
[0119] In an alternative embodiment, as an alternative to stopping the machine's ground traversal in response to determining that the machine's current position and / or orientation is not in a locatable position, the machine may be configured to move to a second position to reacquire positioning. In one embodiment, the machine may backtrack, for example using signals from an inertial measurement unit or wheel encoders, to trace the path just moved before positioning was lost. This may still involve stopping the cutting tool and other moving parts as described above. Backtracking can occur incrementally, such as x attempts, each attempt involving backing off y feet. If this does not result in reacquisition after x attempts, ground traversal can be stopped, and reacquisition in a stationary state as described above can be attempted. In another embodiment, the machine may move away from the enclosure boundary in an attempt to reacquire positioning.
[0120] Figure 8 3 is a flow chart showing an example of a method 360 for navigating within an enclosed area using a buffer area, which may be used in a dynamic mode in low light conditions. The method 360 may be similar to the method 340, except that the method 360 may not determine a positioning area. The method 360 may include switching to a dynamic operating mode 362. For example, during a training mode (see Figure 5 ), based on the boundaries of the enclosed area or the exclusion area and the buffer distance, one or more buffer areas and associated boundaries 362 can be defined within the enclosed area in the navigation map. One or more exclusion areas and associated boundaries can also be defined within the enclosed area in the navigation map.
[0121] The machine may be directed to operate autonomously within an enclosed area (eg, except for the buffer area) 364. The machine may also be directed to avoid one or more buffer areas during autonomous operation.
[0122] In some embodiments, the mobile enclosed area can be used to improve the coverage of the enclosed area. The mobile enclosed area can overlap with the enclosed area except the buffer area.
[0123] The machine may monitor whether the uncertainty region intersects a boundary, such as a boundary of an enclosure or buffer region 366. The machine may determine whether the current position and / or orientation is localizable 370, for example, in response to determining that the uncertainty region intersects the boundary. The machine may monitor whether the uncertainty region exceeds a threshold 368, for example, in response to determining that the uncertainty region does not intersect the boundary. In other embodiments (not shown), the machine may continue to operate autonomously in the enclosure region 364, for example, in response to determining that the uncertainty region does not intersect the boundary.
[0124] In some embodiments, the determination 370 of whether the machine is in a locatable position and / or orientation can be based on whether the lawn mower is in a positioning area. In some embodiments, in order to determine whether the machine is in a locatable position and / or orientation 370, the machine can attempt to perform vision-based positioning. In some embodiments, ambient lighting parameters can be used to determine whether the current position and / or orientation is locatable. Ambient lighting parameters can be used to determine feature detection ranges and associated feature detection scores in the current position and / or orientation. The feature detection score can be compared to a minimum threshold to determine whether the current position and / or orientation is locatable. The machine can, for example, perform positioning 374 in response to determining that the machine is in a locatable position and / or orientation.
[0125] For example, in response to determining that the current position and / or orientation of the machine is not in a locatable position, the movement of the machine can be stopped 372. The machine can be stopped until the machine can be located at the current position. The machine can take various actions when stopped. In one example, the machine can repeatedly attempt vision-based positioning until the machine is able to locate. In some embodiments, the mower can increase one or more of the exposure time, gain, and aperture size, which can facilitate vision-based positioning in low light conditions. In another example, the machine can attempt to use at least one non-vision-based sensor (such as GPS) for non-vision-based positioning. In some embodiments, the machine can attempt non-vision-based positioning in response to one or more unsuccessful attempts using vision-based positioning. After successful positioning, the machine can continue to operate autonomously in the enclosed area 364.
[0126] In some embodiments, a method similar to method 360 (not shown) may be used for navigation during the day. For example, when operating during the day, a buffer area may or may not be determined or used.
[0127] Exemplary Embodiments
[0128] Although the present disclosure is not limited thereto, an understanding of various aspects of the present disclosure will be gained through the specific examples and exemplary embodiments provided below. Various modifications of the exemplary embodiments as well as additional embodiments of the present disclosure will become apparent herein.
[0129] Embodiment A1 is a method for training an autonomous machine to navigate in a work area under various lighting conditions. The method includes: determining data representing a navigation map of the work area, the navigation map including an enclosed area; determining a feature detection range based on an ambient lighting parameter; determining a feature detection score for each of one or more positions in the enclosed area based on the feature detection range; determining one or more locatable positions in the enclosed area based on the corresponding feature detection scores; and updating the navigation map based on the one or more locatable positions to include a positioning area within the enclosed area and storing data representing the updated navigation map.
[0130] Embodiment A2 includes the method of embodiment A1, further comprising determining an ambient lighting parameter based on a nighttime ambient lighting parameter. Embodiment A3 includes the method of embodiment A2, wherein the nighttime ambient lighting parameter corresponds to a predetermined ambient lighting at night. Embodiment A4 includes the method of embodiment A2, wherein the nighttime ambient parameter corresponds to ambient lighting measured in the working area at night.
[0131] Embodiment A5 includes the method of any one of embodiments A2 to A4, further comprising determining another feature detection range based on a daytime ambient lighting parameter corresponding to a time of day between dawn and dusk. Embodiment A6 includes the method of any one of the preceding A embodiments, wherein determining one or more locatable locations comprises comparing the corresponding feature detection scores to a minimum threshold.
[0132] Embodiment A7 includes the method of any of the preceding embodiments A, further comprising determining one or more buffer areas, wherein at least one buffer area is adjacent to and within a boundary of the enclosed area, or adjacent to and outside a boundary of an exclusion area. Embodiment A8 includes the method of embodiment A7, wherein determining one or more buffer areas comprises determining a buffer distance based on a minimum distance between locations, an ambient lighting parameter, or both.
[0133] Embodiment A9 includes the method of embodiment A8, wherein determining the buffer distance based on the minimum distance between the positions includes determining the buffer distance as a fraction of the minimum distance between the positions. Embodiment A10 includes the method of any of the preceding A embodiments, further comprising displaying an updated navigation map on a user interface and indicating nighttime autonomous operation relative to the position area.
[0134] Embodiment A11 includes the method of any preceding embodiment A, further comprising determining a daytime schedule for autonomous operation based on a nighttime schedule for autonomous operation relative to the location area. Embodiment A12 includes the method of embodiment A11, wherein the daytime schedule and the nighttime schedule for autonomous operation are determined to complement each other to cover the working area within a specific time period.
[0135] Embodiment A13 includes the method of embodiment A12, further comprising providing a notification to a user on a user interface in response to determining that the daytime schedule and the nighttime schedule for autonomous operation cannot cover the work area within the specific time period. Embodiment A14 includes the method of any of the preceding embodiments A, wherein determining data representing the navigation map includes determining a three-dimensional point cloud (3DPC) representing the work area.
[0136] Embodiment B1 is a method for navigating an autonomous machine in a work area under various lighting conditions. The method includes: determining a positioning area in a navigation map of the work area, wherein the positioning area is defined based on ambient lighting parameters; determining an operating mode based on the ambient lighting parameters; and directing the machine to operate autonomously within the positioning area based on the operating mode.
[0137] Embodiment B2 includes the method according to embodiment B1, and further includes determining one or more buffer areas, wherein at least one buffer area is adjacent to an enclosed area and within the enclosed area, or adjacent to an exclusion area and outside the exclusion area, wherein guiding the machine to operate autonomously includes guiding the machine to avoid the one or more buffer areas during autonomous operation at night.
[0138] Embodiment B3 includes the method of Embodiment B1 or B2, further comprising using at least one vision-based sensor to locate the machine during autonomous operation. Embodiment B3 includes the method of any of the preceding Embodiments B, further comprising: determining whether the machine can be located at a current location; and in response to determining that the machine cannot be located at the current location, stopping autonomous movement of the machine until the machine can be located at the current location.
[0139] Embodiment B4 includes the method of embodiment B3, further comprising directing the machine to operate autonomously within the enclosed area and outside the positioning area. Embodiment B5 includes the method of any one of embodiments B4 to B6, further comprising responsive to determining that the machine cannot be positioned at the current position, using at least one non-vision based sensor to position the machine.
[0140] Embodiment B6 includes the method according to any of the preceding Embodiments B, further comprising: determining an uncertainty region around the machine; comparing the uncertainty region to an uncertainty region threshold; and locating the machine in response to determining that the uncertainty region exceeds the uncertainty region threshold. Embodiment B7 includes the method according to Embodiment B6, further comprising: determining whether the uncertainty region around the machine intersects a boundary of a region; in response to determining that the uncertainty region around the machine intersects a boundary of a region, stopping autonomous movement of the machine; and locating the machine in response to stopping autonomous movement of the machine.
[0141] Embodiment B8 includes the method of any of the preceding Embodiments B, further comprising updating the location area in response to measuring nighttime ambient lighting in the work area. Embodiment B9 includes the method of Embodiment B8, wherein directing the machine to operate autonomously within the location area includes directing the machine to operate autonomously within a mobile enclosure within the updated location area.
[0142] Embodiment C1 is a method for navigation of an autonomous machine in a work area under various lighting conditions. The method includes: directing the machine to autonomously operate within an enclosed area defined in a navigation map of the work area; determining whether vision-based positioning is available at the location of the machine based on at least an ambient lighting parameter; and in response to determining that vision-based positioning is not available at the location of the machine, stopping autonomous movement of the machine until the machine is able to position itself at the current location.
[0143] Embodiment C2 includes the method according to example C1, further comprising determining one or more buffer areas, wherein at least one buffer area is adjacent to an enclosed area and within the enclosed area, or adjacent to an exclusion area and outside the exclusion area, wherein guiding the machine to operate autonomously includes guiding the machine to avoid the one or more buffer areas during autonomous operation at night.
[0144] Embodiment C3 includes the method according to Example C1 or C2, further comprising: determining an uncertainty region around the machine; comparing the uncertainty region to an uncertainty region threshold; and locating the machine in response to determining that the uncertainty region exceeds the uncertainty region threshold. Embodiment C4 includes the method according to Example C3, further comprising: determining whether the uncertainty region around the machine intersects with a boundary of a region; in response to determining that the uncertainty region around the machine intersects with a boundary of a region, stopping autonomous movement of the machine; and locating the machine in response to stopping autonomous movement of the machine.
[0145] Embodiment D1 comprises an autonomous machine, comprising: a housing coupled to a maintenance tool; a propulsion system comprising a propulsion controller operably coupled to at least one motor; at least one camera adapted to record images under one or more ambient lighting conditions; and a controller operably coupled to the at least one camera and the propulsion controller, the controller adapted to perform a method according to any one of Examples A, B, and C.
[0146] Embodiment E1 includes a method for an autonomous machine to navigate in a work area under various lighting conditions. The method includes: determining a location area in a navigation map of the work area, wherein the location area is defined based on ambient lighting parameters; determining an operating mode based on the ambient lighting parameters, the operating mode defining whether the autonomous machine is allowed to operate outside the location area; and directing the autonomous machine to operate autonomously within the work area based on the operating mode.
[0147] Embodiment E2 includes a method according to embodiment E1, wherein the operating mode includes a night mode, and the method further includes determining one or more buffer areas, wherein at least one buffer area is adjacent to an enclosed area and is within the enclosed area, or is adjacent to an exclusion area and is outside the exclusion area, and wherein guiding the autonomous machine to operate autonomously includes guiding the autonomous machine to avoid the one or more buffer areas during the night mode.
[0148] Embodiment E3 includes the method of embodiment E1 or E2, further comprising: determining whether the autonomous machine can locate at the current location; and in response to determining that the autonomous machine cannot locate at the current location, moving the machine to a second location to reacquire a location. Embodiment E4 includes the method of embodiment E3, wherein moving the machine to the second location includes moving away from a boundary.
[0149] Embodiment E5 includes the method of embodiment E3, wherein moving the machine to the second location includes backtracking. Embodiment E6 includes the method of embodiment E1 or E2, further comprising: determining whether the autonomous machine is able to locate at the current location; and in response to determining that the autonomous machine is unable to locate at the current location, stopping at least one of autonomous ground traversal of the autonomous machine and a moving portion of the autonomous machine until the autonomous machine is able to locate at the current location using a vision-based sensor.
[0150] Embodiment E7 includes the method of embodiment E6, further comprising, in response to locating the current location, directing the autonomous machine to operate autonomously within an area with a known good location. Embodiment E8 includes the method of embodiment E3 or E4, further comprising, in response to determining that the autonomous machine cannot be located at the current location, using the vision-based sensor, using at least one non-vision-based sensor to locate the autonomous machine. Embodiment E9 includes the method of embodiment E8, wherein the at least one non-vision-based sensor includes a GPS sensor, and wherein the ground traversal stop of the autonomous machine allows a period of time for the GPS sensor to obtain a more accurate geolocation reading.
[0151] Embodiment E10 includes the method of embodiment E3 or E4, further comprising, in response to determining that the autonomous machine cannot be positioned at the current location, activating a light source that illuminates a field of view of the vision-based sensor. Embodiment E11 includes the method of embodiment E3 or E4, further comprising, in response to determining that the autonomous machine cannot be positioned at the current location, using a second vision-based sensor to locate the current location.
[0152] Embodiment E12 includes the method according to Embodiment E1, further comprising: determining an uncertainty region around the autonomous machine; comparing the uncertainty region to an uncertainty region threshold; and locating the autonomous machine in response to determining that the uncertainty region exceeds the uncertainty region threshold. Embodiment E13 includes the method according to Embodiment E12, further comprising: determining whether the uncertainty region around the autonomous machine intersects a boundary of a region; in response to determining that the uncertainty region around the autonomous machine intersects a boundary of a region, stopping autonomous movement of the autonomous machine or a moving component of the autonomous machine; and locating the autonomous machine in response to stopping autonomous movement of the autonomous machine.
[0153] Embodiment E14 includes the method of Embodiment E1, further comprising updating the positioning area in response to measuring nighttime ambient lighting in the work area. Embodiment E15 includes the method of Embodiment E14, wherein directing the autonomous machine to operate autonomously within the positioning area comprises directing the autonomous machine to operate autonomously within a mobile enclosure within the updated positioning area.
[0154] Embodiment E16 includes the method according to embodiment E1, and further includes: determining an enclosed area within the navigation map of the working area; determining a feature detection range based on the ambient lighting parameters; determining a feature detection score for each of one or more positions in the enclosed area based on the feature detection range; determining one or more locatable positions in the enclosed area based on the corresponding feature detection scores; and updating the navigation map based on the one or more locatable positions to include the positioning area within the enclosed area and storing data representing the updated navigation map.
[0155] Embodiment F1 relates to an autonomous machine comprising: a housing coupled to a maintenance tool; a propulsion system comprising a propulsion controller operably coupled to at least one motor; at least one vision-based sensor operable to record images under ambient lighting conditions; and a controller operably coupled to the at least one vision-based sensor and the propulsion controller, the controller operable to perform a method according to any one of claims E1 to E16.
[0156] Thus, various embodiments of autonomous machine navigation in various lighting environments are disclosed. Although reference is made herein to the drawings that form a part of the present disclosure, at least one person of ordinary skill in the art will understand that various modifications and variations of the embodiments described herein are within the scope of the present disclosure or do not depart from the scope of the present disclosure. For example, various aspects of the embodiments described herein may be combined with each other in various ways. Therefore, it should be understood that within the scope of the appended claims, the claimed invention may be implemented in a manner other than that explicitly described herein.
[0157] All references and publications cited herein are expressly incorporated by reference into this disclosure for all purposes except to the extent they may directly contradict this disclosure.
[0158] Unless otherwise specified, all scientific and technical terms used herein have the meaning commonly used in the art. The definitions provided herein are for ease of understanding of certain terms frequently used herein and are not intended to limit the scope of the present disclosure.
[0159] The recitation of numerical ranges by endpoints includes all numbers subsumed within that range (eg, 1 to 5 includes 1, 1.5, 2, 2.75, 3, 3.80, 4, and 5) and any range within that range.
[0160] The term "coupled" or "connected" refers to elements being attached to each other directly (directly in contact with each other) or indirectly (having one or more elements between and attaching the two elements). Either term may be modified by "operably" and "operably," which are used interchangeably to describe a connection or connection configuration that allows the components to interact to perform a function.
[0161] As used herein, the term "configured to" may be used interchangeably with the terms "adapted to" or "configured to," unless the context of the present disclosure clearly indicates otherwise.
Claims
1. A method for navigating an autonomous machine in a work area under various lighting conditions, the method include: Determining a location area in a navigation map of the work area, wherein the location area is defined based on ambient lighting parameters; determining an operating mode based on the ambient lighting parameters, the operating mode defining whether the autonomous machine is permitted to operate outside of the positioning area; and The autonomous machine is directed to operate autonomously within the work area based on the operating mode.
2. The method according to claim 1, in, The operating mode includes a night mode, and the method also includes determining one or more buffer areas, wherein at least one buffer area is adjacent to an enclosure area and inside the enclosure area, or adjacent to an exclusion area and outside the exclusion area, wherein directing the autonomous machine to operate autonomously includes directing the autonomous machine to avoid the one or more buffer areas during the night mode.
3. The method according to claim 1 or 2, further comprising: include: determining whether the autonomous machine is capable of being localized at a current location; as well as In response to determining that the autonomous machine cannot locate itself at the current location, the machine is moved to a second location to reacquire a position fix.
4. The method according to claim 3, in, Moving the machine to the second position includes moving away from a boundary.
5. The method according to claim 3, in, Moving the machine to the second position includes backtracking.
6. The method according to claim 1 or 2, further comprising: include: determining whether the autonomous machine is capable of being localized at a current location; as well as In response to determining that the autonomous machine cannot locate at the current location, at least one of autonomous terrain traversal by the autonomous machine and a moving component of the autonomous machine is stopped until the autonomous machine can locate at the current location using the vision-based sensor.
7. The method according to claim 6, further comprising: include: In response to locating the current position, the autonomous machine is directed to operate autonomously within an area having a known good position.
8. The method according to claim 6 or 7, further comprising: include: In response to determining that the autonomous machine cannot be positioned at the current location using the vision-based sensor, the autonomous machine is positioned using at least one non-vision-based sensor.
9. The method according to claim 8, in, The at least one non-vision based sensor includes a GPS sensor, and wherein the ground traversal stop of the autonomous machine allows a period of time for the GPS sensor to obtain a more accurate geolocation reading.
10. The method according to claim 6 or 7, further comprising: include: In response to determining that the autonomous machine cannot be positioned at the current location, a light source is activated that illuminates a field of view of the vision-based sensor.
11. The method according to claim 6 or 7, further comprising: include: In response to determining that the autonomous machine cannot be positioned at the current location, a second vision-based sensor is used to locate the current location.
12. The method according to claim 1, further comprising: include: determining an uncertainty region around the autonomous machine; comparing the uncertainty region to an uncertainty region threshold; as well as The autonomous machine is positioned in response to determining that the uncertainty region exceeds the uncertainty region threshold.
13. The method according to claim 12, further comprising: include: determining whether the uncertainty region around the autonomous machine intersects a boundary of a region; In response to determining that the uncertainty zone around the autonomous machine intersects a boundary of a region, stopping autonomous movement of the autonomous machine or a moving component of the autonomous machine; as well as The autonomous machine is positioned in response to stopping autonomous movement of the autonomous machine.
14. The method of claim 1, further comprising updating the location area in response to measuring nighttime ambient lighting in the work area.
15. The method according to claim 14, in, Directing the autonomous machine to operate autonomously within the positioning area includes directing the autonomous machine to operate autonomously within a moving enclosure within the updated positioning area.
16. The method according to claim 1, further comprising: include: Determining an enclosed area within the navigation map of the working area; determining a feature detection range based on the ambient lighting parameter; determining a feature detection score for each of the one or more locations in the enclosed area based on the feature detection range; determining one or more locatable locations in the enclosed area based on the corresponding feature detection scores; as well as The navigational map is updated based on the one or more locatable locations to include the location area within the enclosed area, and data representing the updated navigational map is stored.
17. An autonomous machine, include: a housing coupled to the maintenance tool; a propulsion system comprising a propulsion controller operably coupled to at least one electric machine; at least one vision-based sensor operable to record images under ambient lighting conditions; as well as a controller operably coupled to the at least one vision-based sensor and the propulsion controller, the controller operable to: determining a location area in a navigation map of a work area, wherein the location area is defined based on the ambient lighting conditions; determining an operating mode based on an ambient lighting parameter, the operating mode defining whether the autonomous machine is permitted to operate outside of the positioning area; and The autonomous machine is directed to operate autonomously within the work area based on the operating mode.
18. The autonomous machine of claim 17, in, The operating modes include a night mode, wherein the controller is further operable to perform determining one or more buffer areas, wherein at least one buffer area is adjacent to an enclosure area and is interior to the enclosure area, or adjacent to an exclusion area and is exterior to the exclusion area, wherein directing the autonomous machine to operate autonomously includes directing the autonomous machine to avoid the one or more buffer areas during the night mode.
19. An autonomous machine according to claim 17 or 18, in, The controller is also operable to: determining whether the autonomous machine can be localized at a current location; and In response to determining that the autonomous machine cannot locate at the current location, autonomous terrain traversal of the autonomous machine or a moving component of the autonomous machine is stopped until the autonomous machine can locate at the current location using the vision-based sensor.
20. The autonomous machine of claim 19, in, The controller is further operable to direct the autonomous machine to operate autonomously within an area having a known good location in response to locating the current position.
21. An autonomous machine according to claim 19 or 20, in, The controller is further operable to perform, in response to determining that the autonomous machine cannot be positioned at the current location using the vision-based sensor, positioning the autonomous machine using at least one non-vision-based sensor.
22. The autonomous machine of claim 21, in, The at least one non-vision based sensor includes a GPS sensor, and wherein the ground traversal stop of the autonomous machine allows a period of time for the GPS sensor to obtain a more accurate geolocation reading.
23. The autonomous machine of claim 19 or 20, further comprising: include: In response to determining that the autonomous machine cannot be positioned at the current location, a light source is activated that illuminates a field of view of the vision-based sensor.
24. The autonomous machine of claim 19 or 20, further comprising: in response to determining that the autonomous machine cannot be positioned at the current position, using a second vision-based sensor to locate the current position.
25. The autonomous machine of claim 17, in, The controller is further operable to: determining an uncertainty region around the autonomous machine; comparing the uncertainty region to an uncertainty region threshold; and The autonomous machine is positioned in response to determining that the uncertainty region exceeds the uncertainty region threshold.
26. The autonomous machine of claim 25, in, The controller is further operable to: determining whether the uncertainty region around the autonomous machine intersects a boundary of a region; responsive to determining that the uncertainty zone around the autonomous machine intersects a boundary of a region, stopping at least one of autonomous movement of the autonomous machine and a moving component of the autonomous machine; as well as The autonomous machine is positioned in response to stopping autonomous movement of the autonomous machine.
27. The autonomous machine of claim 17, in, The controller is further operable to perform updating the location area in response to measuring nighttime ambient lighting in the working area.
28. The autonomous machine of claim 27, in, Directing the autonomous machine to operate autonomously within the positioning area includes directing the autonomous machine to operate autonomously within a moving enclosure within the updated positioning area.
29. The autonomous machine of claim 17, in, The controller is further operable to: Determining an enclosed area within the navigation map of the working area; determining a feature detection range based on the ambient lighting parameter; determining a feature detection score for each of the one or more locations in the enclosed area based on the feature detection range; determining one or more locatable locations in the enclosed area based on the corresponding feature detection scores; as well as The navigational map is updated based on the one or more locatable locations to include the location area within the enclosed area, and data representing the updated navigational map is stored.
