Method, system and apparatus for localization-based historical obstacle handling

Abstract

A method of obstacle handling for a mobile automation apparatus includes: obtaining an initial localization of the mobile automation apparatus in a frame of reference; detecting an obstacle by one or more sensors disposed on the mobile automation apparatus; generating and storing an initial location of the obstacle in the frame of reference, based on (i) the initial localization, and (ii) a detected position of the obstacle relative to the mobile automation apparatus; obtaining a correction to the initial localization of the mobile automation apparatus; and applying a positional adjustment, based on the correction, to the initial position of the obstacle to generate and store an updated position of the obstacle.

Description

BACKGROUND

Environments in which objects are managed, such as retail facilities, may be complex and fluid. For example, a retail facility may include objects such as products for purchase, a distribution environment may include objects such as parcels or pallets, a manufacturing environment may include objects such as components or assemblies, a healthcare environment may include objects such as medications or medical devices.

A mobile automation apparatus may be employed to perform tasks within a facility, such as capturing data for use in identifying products that are out of stock, incorrectly located, and the like. The mobile automation apparatus may detect obstacles in the facility, and a navigational path may be generated, based in part on such obstacles, for the mobile automation apparatus to travel within the facility. Corrections to a localization of the mobile automation apparatus may cause navigational errors and reduce system efficiency.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

The accompanying figures, where like reference numerals refer to identical or functionally similar elements throughout the separate views, together with the detailed description below, are incorporated in and form part of the specification, and serve to further illustrate embodiments of concepts that include the claimed invention, and explain various principles and advantages of those embodiments.

FIG. 1 is a schematic of a mobile automation system.

FIG. 2 depicts a mobile automation apparatus in the system of FIG. 1.

FIG. 3 is a block diagram of certain internal hardware components of the mobile automation apparatus in the system of FIG. 1.

FIG. 4 is a flowchart of a method for obstacle handling at the apparatus of FIG. 1.

FIG. 5 is a diagram illustrating an example performance of block 405 of the method of FIG. 4.

FIG. 6 is a diagram illustrating an example performance of blocks 420-425 and 405-415 of the method of FIG. 4.

FIG. 7 is a diagram illustrating a further example performance of blocks 420-425 of the method of FIG. 4.

FIG. 8 is a diagram illustrating an example performance of block 430 of the method of FIG. 4.

FIGS. 9 and 10 are diagrams illustrating another example performance of block 430 of the method of FIG. 4, employing a radius to select obstacle locations for adjustment.

FIGS. 11 and 12 are diagrams illustrating another example performance of block 430 of the method of FIG. 4, varying the radius of FIGS. 9 and 10 based on localization confidence.

FIG. 13 is a diagram illustrating another example performance of block 430 of the method of FIG. 4, varying adjustments to obstacle locations based on distances between the obstacle locations and the apparatus localization.

FIG. 14 is a diagram illustrating another example performance of block 430 of the method of FIG. 4, varying adjustments to obstacle locations based on confidence levels associated with the initial obstacle locations.

Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help to improve understanding of embodiments of the present invention.

The apparatus and method components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

DETAILED DESCRIPTION

Examples disclosed herein are directed to a method of obstacle handling for a mobile automation apparatus including: obtaining an initial localization of the mobile automation apparatus in a frame of reference; detecting an obstacle by one or more sensors disposed on the mobile automation apparatus; generating and storing an initial location of the obstacle in the frame of reference, based on (i) the initial localization, and (ii) a detected position of the obstacle relative to the mobile automation apparatus; obtaining a correction to the initial localization of the mobile automation apparatus; and applying a positional adjustment, based on the correction, to the initial position of the obstacle to generate and store an updated position of the obstacle.

Additional examples disclosed herein are directed to a mobile automation apparatus, comprising: a memory; at least one navigational sensor; and a navigational controller connected to the memory and the at least one navigational sensor, the navigational controller configured to: obtain an initial localization of the mobile automation apparatus in a frame of reference; detect an obstacle via the at least one navigational sensor; generate and store, in the memory, an initial location of the obstacle in the frame of reference, based on (i) the initial localization, and (ii) a detected position of the obstacle relative to the mobile automation apparatus; obtain a correction to the initial localization; and apply a positional adjustment, based on the correction, to the initial position of the obstacle to generate and store an updated position of the obstacle.

Further examples disclosed herein are directed to a non-transitory computer readable medium storing computer readable instructions for execution by a navigational controller to: obtain an initial localization of a mobile automation apparatus in a frame of reference; detect an obstacle via at least one navigational sensor disposed on the mobile automation apparatus; generate and store an initial location of the obstacle in the frame of reference, based on (i) the initial localization, and (ii) a detected position of the obstacle relative to the mobile automation apparatus; obtain a correction to the initial localization; and apply a positional adjustment, based on the correction, to the initial position of the obstacle to generate and store an updated position of the obstacle.

FIG. 1 depicts a mobile automation system 100 in accordance with the teachings of this disclosure. The system 100 is illustrated as being deployed in a retail facility, but in other embodiments can be deployed in a variety of other environments, including warehouse facilities, hospitals, and the like. The system 100 includes a server 101 in communication with at least one mobile automation apparatus 103 (also referred to herein simply as the apparatus 103) and at least one client computing device 105 via communication links 107, illustrated in the present example as including wireless links. In the present example, the links 107 are provided by a wireless local area network (WLAN) deployed within the retail facility by one or more access points (not shown). In other examples, the server 101, the client device 105, or both, are located outside the retail facility, and the links 107 therefore include wide-area networks such as the Internet, mobile networks, and the like. The system 100 also includes a dock 108 for the apparatus 103 in the present example. The dock 108 is in communication with the server 101 via a link 109 that in the present example is a wired link. In other examples, however, the link 109 is a wireless link.

The client computing device 105 is illustrated in FIG. 1 as a mobile computing device, such as a tablet, smart phone or the like. In other examples, the client device 105 is implemented as another type of computing device, such as a desktop computer, a laptop computer, another server, a kiosk, a monitor, and the like. The system 100 can include a plurality of client devices 105 in communication with the server 101 via respective links 107.

The retail facility in which the system 100 is deployed in the illustrated example includes a plurality of support structures such as shelf modules 110-1, 110-2, 110-3 and so on (collectively referred to as shelf modules 110, and generically referred to as a shelf module 110—this nomenclature may also be employed for other elements discussed herein). Each shelf module 110 supports a plurality of products 112. Each shelf module 110 includes a shelf back 116-1, 116-2, 116-3 and a support surface (e.g. support surface 117-3 as illustrated in FIG. 1) extending from the shelf back 116 to a shelf edge 118-1, 118-2, 118-3. Various other support structures can also be included in the retail facility (e.g. peg boards), or in other environments in which the system 100 is deployed.

The shelf modules 110 are typically arranged in a plurality of aisles, each of which includes a plurality of modules 110 aligned end-to-end. In such arrangements, the shelf edges 118 face into the aisles, through which customers in the retail environment as well as the apparatus 103 may travel. As will be apparent from FIG. 1, the term “shelf edge” 118 as employed herein, which may also be referred to as the edge of a support surface (e.g., the support surfaces 117) refers to a surface bounded by adjacent surfaces having different angles of inclination. In the example illustrated in FIG. 1, the shelf edge 118-3 is at an angle of about ninety degrees relative to each of the support surface 117-3 and the underside (not shown) of the support surface 117-3. In other examples, the angles between the shelf edge 118-3 and the adjacent surfaces, such as the support surface 117-3, is more or less than ninety degrees.

The apparatus 103 is deployed within the retail facility, and communicates with the server 101 (e.g. via the link 107) to navigate, autonomously or partially autonomously, along a length 119 of at least a portion of the shelf modules 110. As will be described in greater detail below, the apparatus 103 is configured to navigate among the shelf modules 110 and other fixed (i.e. static) structural features of the facility, such as walls, pillars and the like. The apparatus 103 is also configured to navigate among transient obstacles such as customers, shopping carts and other objects, which may be detected dynamically. Navigational functions can be performed by the apparatus 103 and/or the server 101 with regard to a common frame of reference 102 previously established in the facility.

The apparatus 103 is equipped with a plurality of navigation and data capture sensors 104, such as image sensors (e.g. one or more digital cameras) and depth sensors (e.g. one or more Light Detection and Ranging (LIDAR) sensors, one or more depth cameras employing structured light patterns, such as infrared light, or the like). The apparatus 103 can be configured to employ the sensors 104 for navigational functions, including tracking of the location of the apparatus 103 relative to the frame of reference 102, detection of the above-mentioned transient obstacles, and the like. The apparatus 103 can also employ the sensors to capture shelf data (e.g. images and depth measurements depicting the products 112) during such navigation.

The server 101 includes a special purpose controller, such as a processor 120, specifically designed to control and/or assist the mobile automation apparatus 103 to navigate the environment and to capture data. The processor 120 can be further configured to obtain the captured data via a communications interface 124 for storage in a repository 128 and subsequent processing (e.g. to detect objects such as shelved products 112 in the captured data, and detect status information corresponding to the objects). The server 101 may also be configured to transmit status notifications (e.g. notifications indicating that products are out-of-stock, low stock or misplaced) to the client device 105 responsive to the determination of product status data. The client device 105 includes one or more controllers (e.g. central processing units (CPUs) and/or field-programmable gate arrays (FPGAs) and the like) configured to process (e.g. to display) notifications received from the server 101.

The above-mentioned communications interface 124 of the server 101 is interconnected with the processor 120, and includes suitable hardware (e.g. transmitters, receivers, network interface controllers and the like) allowing the server 101 to communicate with other computing devices—particularly the apparatus 103, the client device 105 and the dock 108—via the links 107 and 109. The links 107 and 109 may be direct links, or links that traverse one or more networks, including both local and wide-area networks. The specific components of the communications interface 124 are selected based on the type of network or other links that the server 101 is required to communicate over. In the present example, as noted earlier, a wireless local-area network is implemented within the retail environment via the deployment of one or more wireless access points. The links 107 therefore include either or both wireless links between the apparatus 103 and the mobile device 105 and the above-mentioned access points, and a wired link (e.g. an Ethernet-based link) between the server 101 and the access point.

The processor 120 is interconnected with a non-transitory computer readable storage medium, such as a memory 132, storing the above-mentioned repository 128 as well as computer readable instructions executable by the processor 120 for performing various functionality. Examples of such functionality include control of the apparatus 103 to capture shelf data, post-processing of the shelf data, and generating and providing certain navigational data to the apparatus 103, such as target locations at which to capture shelf data. The memory 132 includes a combination of volatile (e.g. Random Access Memory or RAM) and non-volatile memory (e.g. read only memory or ROM, Electrically Erasable Programmable Read Only Memory or EEPROM, flash memory). The processor 120 and the memory 132 each comprise one or more integrated circuits. In some embodiments, the processor 120 is implemented as one or more central processing units (CPUs) and/or graphics processing units (GPUs).

The computer readable instructions stored by the memory 132 can include at least one application executable by the processor 120. Execution of the above-mentioned instructions by the processor 120 configures the server 101 to perform various actions discussed herein. The applications stored in the memory 132 in the illustrated example include a control application 136, which may also be implemented as a suite of logically distinct applications. In general, via execution of the application 136 or subcomponents thereof and in conjunction with the other components of the server 101, the processor 120 is configured to implement various functionality related to controlling the apparatus 103 to navigate among the shelf modules 110 and capture data.

Turning now to FIG. 2, the mobile automation apparatus 103 is shown in greater detail. The apparatus 103 includes a chassis 201 containing a locomotive mechanism 203 (e.g. one or more electrical motors driving wheels, tracks or the like). The locomotive mechanism 203 can include one or more odometry sensors (e.g. wheel speed sensors) to generate odometry data when the apparatus 103 is in motion. The apparatus 103 further includes a sensor mast 205 supported on the chassis 201 and, in the present example, extending upwards (e.g., substantially vertically) from the chassis 201. The mast 205 supports the sensors 104 mentioned earlier. In particular, the sensors 104 include at least one imaging sensor 207, such as a digital camera, as well as at least one depth sensor 209, such as a 3D digital camera. The apparatus 103 also includes additional depth sensors, such as LIDAR sensors 211. In other examples, the apparatus 103 includes additional sensors, such as one or more RFID readers, temperature sensors, and the like.

In the present example, the mast 205 supports seven digital cameras 207-1 through 207-7, and two LIDAR sensors 211-1 and 211-2. The mast 205 also supports a plurality of illumination assemblies 213, configured to illuminate the fields of view of the respective cameras 207. That is, the illumination assembly 213-1 illuminates the field of view of the camera 207-1, and so on. The sensors 207 and 211 are oriented on the mast 205 such that the fields of view of each sensor face a shelf module 110 along the length 119 of which the apparatus 103 is travelling. The apparatus 103 is configured to track a location (e.g. a location of the center of the chassis 201) and orientation of the apparatus 103 in the common frame of reference 102, permitting data captured by the mobile automation apparatus 103 to be registered to the common frame of reference 102. The above-mentioned location and orientation of the apparatus 103 within the frame of reference 102, also referred to as a localization, can be employed in the generation of paths for execution by the apparatus 103.

Turning to FIG. 3, certain internal components of the mobile automation apparatus 103 are shown. In particular, apparatus 103 includes a special-purpose navigational controller, such as a processor 220 interconnected with a non-transitory computer readable storage medium, such as a memory 222. The memory 222 includes a combination of volatile (e.g. Random Access Memory or RAM) and non-volatile memory (e.g. read only memory or ROM, Electrically Erasable Programmable Read Only Memory or EEPROM, flash memory). The processor 220 and the memory 222 each comprise one or more integrated circuits. The memory 222 stores computer readable instructions for execution by the processor 220. In particular, the memory 222 stores a navigation application 228 which, when executed by the processor 220, configures the processor 220 to perform various functions discussed below in greater detail and related to the navigation of the apparatus 103 (e.g. by controlling the locomotive mechanism 203). The application 228 may also be implemented as a suite of distinct applications in other examples.

The processor 220, when so configured by the execution of the application 228, may also be referred to as a navigational controller 220. Those skilled in the art will appreciate that the functionality implemented by the processor 220 via the execution of the application 228 may also be implemented by one or more specially designed hardware and firmware components, such as FPGAs, Application-Specific Integrated Circuits (ASICs) and the like in other embodiments.

The memory 222 may also store a repository 232 containing, for example, one or more maps of the environment in which the apparatus 103 operates, for use during the execution of the application 228. The repository 232, in the examples discussed below, contains a facility map, which may also be referred to as a permanent map. The facility map represents the positions of fixed structural features of the facility such as walls, shelf modules 110 and the like, according to the frame of reference 102. The apparatus 103 may communicate with the server 101, for example to receive instructions to navigate to specified locations and initiate data capture operations, via a communications interface 224 over the link 107 shown in FIG. 1. The communications interface 224 also enables the apparatus 103 to communicate with the server 101 via the dock 108 and the link 109.

In the present example, the apparatus 103 is configured (via the execution of the application 228 by the processor 220) to generate navigational paths to travel through the environment, for example to reach goal locations provided by the server 101. The apparatus 103 is also configured to control the locomotive mechanism 203 to travel along the above-mentioned paths. To that end, the apparatus 103 is also configured, as will be discussed below in greater detail, to detect obstacles in the surroundings of the apparatus 103. Such obstacles, referred to earlier as transient obstacles, are distinguished from fixed structural features of the facility in which the apparatus 103 is deployed. The positions of obstacles relative to the frame of reference 102 are stored in the memory 222, e.g. in an obstacle map separate from the facility map, or as transient additions to the facility map itself. As will be discussed in greater detail below, the apparatus 103 is also configured to dynamically update the positions of at least some previously detected obstacles in response to certain changes in localization.

As will be apparent in the discussion below, other examples, some or all of the processing performed by the apparatus 103 may be performed by the server 101, and some or all of the processing performed by the server 101 may be performed by the apparatus 103. That is, although in the illustrated example the application 228 resides in the mobile automation apparatus 103, in other embodiments the actions performed by the apparatus 103 via execution of the application 228 may be performed by the processor 120 of the server 101, either in conjunction with or independently from the processor 220 of the mobile automation apparatus 103. As those of skill in the art will realize, distribution of navigational computations between the server 101 and the mobile automation apparatus 103 may depend upon respective processing speeds of the processors 120 and 220, the quality and bandwidth of the link 107, as well as criticality level of the underlying instruction(s).

The functionality of the application 228 will now be described in greater detail. In particular, the detection and updating of obstacle positions based on localization tracking of the apparatus 103 will be described as performed by the apparatus 103. FIG. 4 illustrates a method 400 of localization-based historical obstacle handling. The method 300 will be described in conjunction with its performance by the apparatus 103.

The apparatus 103 is configured to periodically update its localization according to the frame of reference 102 during navigation within the facility. Localization is updated based on sensor data, e.g. from any one or more of the image, depth and odometry sensors mentioned earlier. In other words, the apparatus 103 detects its location and orientation within the facility by comparing sensor data to the map stored in the repository 232. As will be apparent to those skilled in the art, the accuracy of localization of the apparatus 103 may vary over time. Certain updated localizations may therefore reflect not only physical movement of the apparatus 103, but also corrected localization accuracy.

Obstacles are also detected via the above-mentioned image and depth sensors (e.g. 207, 209, 211), and positions of the obstacles in the frame of reference 102 are stored, e.g. in the memory 222. When an obstacle is in the field of view of such sensors, corrections to the localization of the apparatus 103 are implicitly applied to the obstacle (i.e. the stored position of the obstacle is updated along with the localization of the apparatus 103). However, when a previously detected obstacle is not currently within the field of view of the above sensor, such implicit updates to stored obstacle positions may no longer occur. As a result, the localization of the apparatus 103 may sometimes be corrected to overlap with the stored position of an obstacle that is not currently visible to the apparatus 103. Although no actual collision has occurred, such an event may generate an error condition, interrupt operation of the apparatus or the like. The method 400 to be discussed below mitigates or avoids the above virtual collisions resulting from corrections to the localization of the apparatus 103.

At block 305, the apparatus 103 is configured to initiate navigation and localization tracking. For example, the apparatus 103 can receive an instruction from the server 101 to travel to at least one location in the facility and/or perform tasks such as data capture at such locations. In response to the instruction, the apparatus 103 can generate a navigational path based on the facility map stored in the repository 232. The apparatus 103 can then initiate execution of the path by controlling the locomotive mechanism 203. The apparatus 103 also begins tracking localization, generating an updated localization estimate at any suitable frequency (e.g. 10 Hz, although a wide variety of other localization frequencies can also be employed both above and below 10 Hz).

The apparatus 103 can also be configured, for each localization, to generate a confidence level. The confidence level, which may also be referred to as localization certainty level, indicates the probable accuracy of the localization, as assessed by the apparatus 103. Various mechanisms for generating localizations and associated confidence levels will occur to those skilled in the art, including mechanisms based on any one or more of odometry data (e.g. received at the processor 220 from a wheel sensor or the like included in the locomotive mechanism 203), inertial sensor data (e.g. from an inertial measurement unit (IMU)), lidar data, or the like. The localization confidence level is typically generated simultaneously with the localization itself, and may be expressed in a variety of formats, including as a fraction between zero and one, as a percentage, or the like.

Before proceeding to block 410, the apparatus 103 is assumed to have computed at least one localization (that is, a current localization is assumed to be available). At block 410, the apparatus 103 determines whether any obstacles have been detected via the above-mentioned sensors at the current localization. A variety of object detection and/or recognition mechanisms can be employed by the apparatus 103 to process sensor data and determine whether the sensor data represents an obstacle distinct from the features of the facility map.

Turning to FIG. 5, a map 500 is shown that contains indications, according to the frame of reference 102, of structural features of the facility such as shelf module boundaries 504-1 and 504-2. The map 500 also illustrates a navigational path 508 along which the apparatus 103 has begun to travel. Further, the map 500 illustrates a current localization 512 of the apparatus 104 as well as a confidence level associated with the localization 512. The confidence level is shown as 0.7 (e.g. within a range between zero and one, with one representing complete certainty). Also shown in the map 500 is a field of view 516 of the sensors 104 of the apparatus 103.

The map 500 need not be maintained in the memory 222 as a single file. Rather, the information shown in FIG. 5 can be maintained in multiple files in some embodiments. For example, the above-mentioned facility map can contain the boundaries 504, and the apparatus 103 can maintain a separate file defining the path 508 and localization 512. In addition, some information, such as the extent of the field of view 516, can simply be omitted (i.e. not stored explicitly in the memory 222).

As shown in FIG. 5, no obstacles are within the field of view 516, and the determination at block 410 is therefore negative. Returning to FIG. 4, the apparatus 103 therefore bypasses block 415 (to be discussed further below) and proceeds to block 420. At block 420 the apparatus 103 obtains an updated localization. As noted above, a variety of localization mechanisms can be employed by the apparatus 103, and the localization of the apparatus 103 can be updated at a variety of frequencies. For example, the apparatus 103 can capture respective sets of image and/or depth measurements, as well as odometry measurements, at a suitable frequency. Each set of measurements can be employed as inputs to a localization filter (e.g. a Kalman filter), which produces a localization estimate.

At block 425, having obtained an updated localization, the apparatus 103 is configured to determine whether the updated localization obtained at block 420 represents a correction to a preceding localization (i.e. from block 405, or from the preceding performance of block 420 if applicable). Referring to FIG. 6, an updated localization 600 is shown, with a confidence level of 0.8. Relative to the localization 512 shown in FIG. 5, the localization 600 shows that the apparatus 103 perceives having traveled a certain distance along the path 508.

The determination at block 425 includes determining a difference between the updated localization from block 420 and a combination of the preceding localization and odometry data. In other words, when the preceding localization, modified by odometry data representing movement of the apparatus 103, is equal to the updated localization, no correction has occurred. However, when the preceding localization modified by odometry data representing movement of the apparatus 103 is not equal to the updated localization, a correction has occurred. In the example illustrated in FIG. 6, odometry data is indicated as a vector 604. In the illustrated example, the localization 512, modified by the vector 604, is equal to the localization 600. Therefore, the entirety of the difference between the localization 512 and the localization 600 is explained by the odometry data 604, and the determination at block 425 is negative. Performance of the method 400 therefore returns to block 410.

At a subsequent performance of block 410, still referring to FIG. 6, the determination at block 410 is affirmative. Specifically, an obstacle 608 is detected within the field of view 516 of the apparatus 103. The apparatus 103, in response to detecting the obstacle 608, proceeds to block 415. At block 415, the apparatus 103 stores an initial location of the obstacle 608 according to the frame of reference, based on the current localization 600 and the position of the obstacle 608 relative to the apparatus 103. The location of the obstacle 608 shown in FIG. 6 reflects the initial location of the obstacle 608 as stored in the memory 222. As will be apparent to those skilled in the art, the location of the obstacle 608 illustrated in FIG. 6 may not coincide exactly with the true physical location of the obstacle 608, due to error in the localization 600 of the apparatus 103.

In some examples, as illustrated in FIG. 6, the confidence level associated with the current localization 600 is also stored in association with the detected obstacle. Therefore, the location of the obstacle 608 is stored in conjunction with the confidence level “0.8”.

Having stored the obstacle location at block 415, the apparatus 103 proceeds to block 420 to obtain a further updated localization (e.g. in response to further travel along the path 508). In the present example, the apparatus 103 may also be configured to alter the path 508 to avoid a collision with the obstacle 608. Turning to FIG. 7, a further localization 700 (that is, obtained via another performance of block 420) is illustrated, with a confidence level of 0.7. As also shown in FIG. 7, the path 508 has been updated to a path 704, routing the apparatus 103 away from a collision course with the obstacle 608. It is assumed, for the current performance of block 425 (after the localization 700 is obtained), that the determination at block 425 is again negative. That is, the difference between the localization 700 and the localization 600 is assumed to correspond entirely to odometry data defining the motion of the apparatus along the path 704. Therefore, the apparatus returns to block 410.

At another performance of block 410, the determination is negative because, as seen in FIG. 7, no obstacles are within the field of view of the apparatus 103. The location of the obstacle 608 is retained, but the obstacle 608 is not currently visible to the apparatus 103 and may therefore be referred to as a historical obstacle that is stored in the memory 222.

The apparatus 103 therefore proceeds again to block 420 to obtain an updated localization, as illustrated in FIG. 8. In particular, FIG. 8 illustrates an updated localization 800, as well as the previous localization 700. It is assumed that the apparatus 103 has not moved between the acquisition of the localization 700 and the acquisition of the localization 800. In other words, the difference between the localizations 700 and 800 is not explained by odometry data, and therefore the determination at block 425 is affirmative. That is, the difference between the localizations 700 and 800 represents a correction to the localization of the apparatus 103.

The location of the obstacle 608 is also shown in FIG. 8 (in dashed lines). As will be apparent from the illustration, the obstacle 608 remains outside of the field of view 516, and the apparatus 103 is therefore unable to obtain updated information concerning the position of the obstacle 608 relative to the apparatus 103. Further, the stored location of the obstacle 608 overlaps with the updated localization 800. In the absence of any changes to the stored location of the obstacle 608, the apparatus 103 may perceive that a collision has occurred (when a collision has not, in fact, occurred), and may enter an error condition that prevents continued operation.

Referring again to FIG. 4, following an affirmative determination at block 425, the apparatus 103 proceeds to block 430. At block 430, to mitigate the occurrence of the above-mentioned virtual collision, the apparatus 103 applies an adjustment to the stored position of the obstacle 608. More generally, at block 430 the apparatus 103 applies an adjustment to a subset of stored obstacle positions. Which subset of stored obstacle locations is adjusted, and what adjustments are applied to the obstacle locations in that subset, may depend on a variety of factors as discussed below.

Returning to FIG. 8, in the illustrated example the apparatus 103 is configured to apply an adjustment to the location of the obstacle 608 that is equal to the correction applied to the localization (i.e. the difference between the localizations 700 and 800). That is, the stored location of the obstacle 608 is shifted, as shown by the stored position 608a, by the same distance and in the same direction as the localization 800 relative to the localization 700. The initial stored location of the obstacle 608 is discarded, and the confidence level associated with the updated obstacle location 608a may be retained.

In some examples, all stored historical obstacle locations can be updated as described above. That is, an adjustment equal to the localization correction can be applied to every historical obstacle location stored in the memory 222. Adjustments are not applied to obstacles that are within the field of view of the apparatus 103, because the stored locations of such visible obstacles are already based on the current localization, and they are not considered historical obstacles.

Turning to FIG. 9, another map 900 is illustrated showing an apparatus localization 902, as well as three historical obstacle positions 904, 908 and 912. A preceding localization 916 is also shown, to which the localization 902 represents a correction. In the illustrated example, the apparatus 103 is configured to apply the adjustment at block 430 only to stored obstacle positions within a predefined radius 920 from the current localization 902. Therefore, as shown in FIG. 10, following the performance of block 430, the obstacle location 904 has been updated to an obstacle location 904a, but the stored locations of the obstacles 908 and 912 are unchanged. That is, the adjustment applied at block 430 may be null for some obstacles.

Turning to FIGS. 11 and 12, in other examples the radius 920 can vary depending on the confidence level associated with the current localization. In FIG. 11, a current localization 1000 has an associated confidence level of 0.9, compared to the confidence level of 0.7 shown in FIGS. 9 and 10. The apparatus 103 is configured to employ a smaller radius 1020 to select obstacles for adjustment. FIG. 12, in contrast, shows a localization 1100 with a confidence level of 0.5. The apparatus 103 therefore selects a larger radius 1120 to select obstacles for adjustment. The radius employed at block 430 can vary, for example, between a predefined minimum and a predefined maximum, with the variation being inversely proportional to the confidence level. For example, a confidence level of 1.0 (i.e. absolute certainty of localization) may lead to use of the minimum predefined radius, while a confidence level of zero may lead to use of the maximum predefined radius.

In other examples, rather than minimum and maximum radii, the apparatus 103 can store a default radius, which is incremented or decremented based on the confidence level associated with the current localization. More specifically, the radius may be decreased for each of a set of predefined steps above a confidence level of 0.5, or increased for each of a set of predefined steps below a confidence level of 0.5. Various other mechanisms for scaling the radius based on localization confidence level may also be employed.

In further examples, as illustrated in FIGS. 13 and 14, the adjustment applied to each selected obstacle location is not equal to the localization correction, but varies with one or both of distance between the current localization and the stored obstacle location. In FIG. 13, adjustments are shown to the obstacle locations 904 and 908, resulting in updated obstacle locations 904a and 908a. The adjustments applied to the obstacle locations 904 and 908, however, are portions of the localization correction that are inversely proportional to the distance between the localization 1100 and the respective obstacle locations. The obstacle location 904, therefore, being closer to the localization 1100, is adjusted by a greater portion of the difference between the localizations 1100 and 916, whereas the obstacle location 908, being further from the localization 1100, is adjusted by a smaller portion of the above difference. The specific portions employed can be determined in various ways. For example, the entire localization correction can be employed for obstacles at zero distance from the apparatus 103, and a null adjustment (i.e. 0% of the localization correction) can be applied to obstacles at the radius 1120.

In FIG. 14, obstacle locations are adjusted based on confidence levels associated with the localizations at which the obstacles were detected. More specifically, obstacle locations are adjusted by portions of the localization correction that are inversely proportional to the confidence levels associated with the obstacle locations. Therefore, the obstacle location 908, with an associated confidence level of 0.9, may be adjusted by ten percent of the localization correction. The obstacle location 904, with an associated confidence level of 0.6, may be adjusted by forty percent of the localization correction.

Variations to the above systems and methods are contemplated. For example, in some embodiments the adjustments applied to obstacle locations can be portions of the localization correction based on the age of the stored obstacle locations. For example, at block 415 each detected obstacle location can be stored with a time of detection, and at block 430, obstacles with greater ages (i.e. earlier times of detection) may be adjusted by smaller portions of the localization correction.

In the foregoing specification, specific embodiments have been described. However, one of ordinary skill in the art appreciates that various modifications and changes can be made without departing from the scope of the invention as set forth in the claims below. Accordingly, the specification and figures are to be regarded in an illustrative rather than a restrictive sense, and all such modifications are intended to be included within the scope of present teachings.

The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential features or elements of any or all the claims. The invention is defined solely by the appended claims including any amendments made during the pendency of this application and all equivalents of those claims as issued.

Moreover in this document, relational terms such as first and second, top and bottom, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms “comprises,” “comprising,” “has”, “having,” “includes”, “including,” “contains”, “containing” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, has, includes, contains a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by “comprises . . . a”, “has . . . a”, “includes . . . a”, “contains . . . a” does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises, has, includes, contains the element. The terms “a” and “an” are defined as one or more unless explicitly stated otherwise herein. The terms “substantially”, “essentially”, “approximately”, “about” or any other version thereof, are defined as being close to as understood by one of ordinary skill in the art, and in one non-limiting embodiment the term is defined to be within 10%, in another embodiment within 5%, in another embodiment within 1% and in another embodiment within 0.5%. The term “coupled” as used herein is defined as connected, although not necessarily directly and not necessarily mechanically. A device or structure that is “configured” in a certain way is configured in at least that way, but may also be configured in ways that are not listed.

It will be appreciated that some embodiments may be comprised of one or more specialized processors (or “processing devices”) such as microprocessors, digital signal processors, customized processors and field programmable gate arrays (FPGAs) and unique stored program instructions (including both software and firmware) that control the one or more processors to implement, in conjunction with certain non-processor circuits, some, most, or all of the functions of the method and/or apparatus described herein. Alternatively, some or all functions could be implemented by a state machine that has no stored program instructions, or in one or more application specific integrated circuits (ASICs), in which each function or some combinations of certain of the functions are implemented as custom logic. Of course, a combination of the two approaches could be used.

Moreover, an embodiment can be implemented as a computer-readable storage medium having computer readable code stored thereon for programming a computer (e.g., comprising a processor) to perform a method as described and claimed herein. Examples of such computer-readable storage mediums include, but are not limited to, a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a ROM (Read Only Memory), a PROM (Programmable Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory) and a Flash memory. Further, it is expected that one of ordinary skill, notwithstanding possibly significant effort and many design choices motivated by, for example, available time, current technology, and economic considerations, when guided by the concepts and principles disclosed herein will be readily capable of generating such software instructions and programs and ICs with minimal experimentation.

The Abstract of the Disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be seen that various features are grouped together in various embodiments for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separately claimed subject matter.

Claims

1. A method of obstacle handling for a mobile automation apparatus, the method comprising: obtaining an initial localization of the mobile automation apparatus in a frame of reference;detecting an obstacle by one or more sensors disposed on the mobile automation apparatus;generating an initial location of the obstacle in the frame of reference, based on (i) the initial localization, and (ii) a detected position of the obstacle relative to the mobile automation apparatus;storing, in association with the initial location of the obstacle, a confidence level associated with the initial localization;obtaining a correction to the initial localization of the mobile automation apparatus;determining a positional adjustment to the initial position of the obstacle as a portion of the localization correction based on the confidence level, wherein the portion is inversely proportional to the confidence level; andapplying the positional adjustment to generate an updated position of the obstacle.

2. The method of claim 1, wherein obtaining the correction to the initial localization includes: obtaining an updated localization of the mobile automation apparatus and odometry data; anddetermining a difference between (i) the updated localization and (ii) the initial localization modified by the odometry data.

3. The method of claim 2, further comprising: obtaining an adjustment radius; anddetermining a distance between the updated localization and the initial location of the obstacle;wherein the positional adjustment is null when the distance exceeds the adjustment radius.

4. The method of claim 3, further comprising: when the distance does not exceed the adjustment radius, generating the positional adjustment as a portion of the correction to the initial localization, the portion being inversely proportional to the distance.

5. The method of claim 3, further comprising: when the distance does not exceed the adjustment radius, generating the positional adjustment as equal to the correction to the initial localization.

6. The method of claim 3, wherein obtaining the adjustment radius includes: obtaining a confidence level associated with the updated localization; andincreasing or decreasing a default adjustment radius according to the confidence level.

7. A mobile automation apparatus, comprising: a memory;at least one navigational sensor; anda navigational controller connected to the memory and the at least one navigational sensor, the navigational controller configured to: obtain an initial localization of the mobile automation apparatus in a frame of reference;detect an obstacle via the at least one navigational sensor;generate an initial location of the obstacle in the frame of reference, based on (i) the initial localization, and (ii) a detected position of the obstacle relative to the mobile automation apparatus;store, in association with the initial location of the obstacle, a confidence level associated with the initial localization;obtain a correction to the initial localization;determine a positional adjustment as a portion of the localization correction based on the confidence level, wherein the portion is inversely proportional to the confidence level; andapply the positional adjustment to generate an updated position of the obstacle.

8. The mobile automation apparatus of claim 7, wherein the navigational controller is configured, in order to obtain the correction to the initial localization, to: obtain an updated localization of the mobile automation apparatus and odometry data; anddetermine a difference between (i) the updated localization and (ii) the initial localization modified by the odometry data.

9. The mobile automation apparatus of claim 8, wherein the navigational controller is further configured to: obtain an adjustment radius; anddetermine a distance between the updated localization and the initial location of the obstacle;wherein the positional adjustment is null when the distance exceeds the adjustment radius.

10. The mobile automation apparatus of claim 9, wherein the navigational controller is further configured to: when the distance does not exceed the adjustment radius, generate the positional adjustment as a portion of the correction to the initial localization, the portion being inversely proportional to the distance.

11. The mobile automation apparatus of claim 9, wherein the navigational controller is further configured to: when the distance does not exceed the adjustment radius, generate the positional adjustment as equal to the correction to the initial localization.

12. The mobile automation apparatus of claim 9, wherein the navigational controller is further configured, in order to obtain the adjustment radius, to: obtain a confidence level associated with the updated localization; andincrease or decrease a default adjustment radius according to the confidence level.

13. A non-transitory computer readable medium storing computer readable instructions for execution by a navigational controller, the instructions comprising: obtaining an initial localization of a mobile automation apparatus in a frame of reference;detecting an obstacle via at least one navigational sensor disposed on the mobile automation apparatus;generating an initial location of the obstacle in the frame of reference, based on (i) the initial localization, and (ii) a detected position of the obstacle relative to the mobile automation apparatus;storing, in association with the initial location of the obstacle, a confidence level associated with the initial localization;obtaining a correction to the initial localization;determining a positional adjustment to the initial position of the obstacle as a portion of the localization correction based on the confidence level, wherein the portion is inversely proportional to the confidence level; andapplying the positional adjustment to generate an updated position of the obstacle.

14. The non-transitory computer readable medium of claim 13, wherein the instructions further comprise: obtaining an updated localization of the mobile automation apparatus and odometry data; anddetermining a difference between (i) the updated localization and (ii) the initial localization modified by the odometry data.

15. The non-transitory computer readable medium of claim 14, wherein the instructions further comprise obtaining an adjustment radius and determining a distance between the updated localization and the initial location of the obstacle, wherein the positional adjustment is null when the distance exceeds the adjustment radius.

16. The non-transitory computer readable medium of claim 15, wherein the instructions further comprise: when the distance does not exceed the adjustment radius, generating the positional adjustment as a portion of the correction to the initial localization, the portion being inversely proportional to the distance.