Position estimation system and method for material

Abstract

Systems and methods of tracking a material handling vehicle include estimating a position of the material handling vehicle based on modeled position data from a first sensor configured to model an odometer of the vehicle; measuring a position of the material handling vehicle based on measured position data from a second sensor configured to measure relative movement of the vehicle; determining an amount of noise in both the modeled position data from the first sensor and the measured position data from the second sensor; and updating an estimated position of the material handling vehicle based on position data from the first sensor, the second sensor, and the amount of noise.

Description

Cross Reference to Related Applications

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 649,812, filed May 20, 2024, which is incorporated by reference in its entirety. BACKGROUND

[0002] To facilitate integration with warehouse management systems, it can be beneficial to track (e.g., estimate) a current or predicted position of a materials handling vehicle in a warehouse or other work environment. SUMMARY

[0003] According to one aspect of the disclosure, a method of tracking a materials handling vehicle can include estimating a position of the materials handling vehicle based on modeled position data from a first sensor, the first sensor configured to model an odometer of the vehicle. The method can include measuring a position of the materials handling vehicle based on measured position data from a second sensor, the second sensor configured to measure a relative motion of the vehicle. The method can include determining a noise quantity of both the modeled position data from the first sensor and the measured position data from the second sensor. The method can include updating the estimated position of the materials handling vehicle based on the position data from the first sensor, the second sensor, and the noise quantity.

[0004] In some examples, the modeled position information can be based on odometer data of the materials handling vehicle.

[0005] In some examples, the measured position information can be based on inertial measurement unit data of the materials handling vehicle.

[0006] In some examples, updating the estimated position of the materials handling vehicle can include combining the modeled position data from the first sensor and the measured position data from the second sensor within a Kalman filter.

[0007] In some examples, the method can include using the updated estimated position of the materials handling vehicle to track a position of an object outside a field of view of a vision sensor of the materials handling vehicle.

[0008] In some examples, the method can include creating a buffer zone around a tracked object to prevent the materials handling vehicle from coming into contact with the tracked object.

[0009] In some embodiments, the method can include adjusting at least one operational parameter of the materials handling vehicle based on the estimated position of the materials handling vehicle.

[0010] In some examples, the operational parameter can include at least one of a maximum speed, a maximum lift height, or a maximum acceleration.

[0011] According to another aspect of the disclosure, a guidance, navigation, and control system for a materials handling vehicle can include a first sensor to measure odometry data. The system can include a second sensor to measure inertial measurement unit data. The system can include a processor to predict a position of the materials handling vehicle based on the odometry data from the first sensor; measure the position of the materials handling vehicle based on the inertial measurement unit data from the second sensor; and combine the odometry data from the first sensor and the inertial measurement unit data from the second sensor within a Kalman filter to generate an updated position estimate of the materials handling vehicle.

[0012] In some examples, the processor can calculate an amount of noise in both the measured odometry data and the measured inertial measurement unit data.

[0013] In some examples, the updated position estimate of the materials handling vehicle can be based on the odometry data from the first sensor, the inertial measurement unit data from the second sensor, and the noise in both the measured odometry data and the measured inertial measurement unit data.

[0014] In some examples, the system can include a feature tracking system configured to track a position of an object outside of a sensor field of view based on the updated position estimate of the materials handling vehicle.

[0015] In some examples, the feature tracking system can be configured to create a buffer around the tracked object to account for potential drift in the updated position estimate.

[0016] In some examples, the system can include an absolute position measurement system configured to determine an absolute position of the materials handling vehicle within a warehouse based on the updated position estimate.

[0017] In some examples, the processor can be further configured to adjust an operational parameter of the materials handling vehicle based on the updated position estimate, wherein the operational parameter includes at least one of a maximum speed, a lift height, or a turning radius.

[0018] In some examples, the processor can be further configured to communicate the updated position estimate to a warehouse management system to facilitate tracking of the materials handling vehicle throughout the warehouse.

[0019] According to yet another aspect of the disclosure, a method of tracking an object using a guidance, navigation, and control system of a materials handling vehicle can include estimating a position of the materials handling vehicle using a Kalman filter to combine measured position data from a first sensor and modeled position data from a second sensor. The method can include detecting an object within a field of view of a third sensor on the materials handling vehicle. The method can include recording a position of the detected object relative to the estimated position of the materials handling vehicle. The method can include updating the estimated position of the detected object based on subsequent estimated positions of the materials handling vehicle even when the object is no longer within the field of view of the sensor.

[0020] In some examples, the method can include communicating the estimated position of the detected object to a warehouse management system to facilitate tracking of obstacles within a warehouse environment.

[0021] In some examples, the method can include creating a buffer zone around the estimated position of the object and preventing the materials handling vehicle from entering the buffer zone.

[0022] In some examples, the size of the buffer zone can increase over time to account for potential drift in the estimated position of the materials handling vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which are incorporated in and form a part of the specification, illustrate embodiments of the present application and, together with the description, serve to explain the principles of the embodiments of the application:

[0024] Figure 1 is a diagrammatic view of a materials handling vehicle in accordance with aspects of the present disclosure.

[0025] Figure 2 is a diagrammatic view of a Figure 1 guidance, navigation, and control system of a materials handling vehicle in accordance with aspects of the present disclosure.

[0026] Figure 3 is a diagrammatic view of a Figure 2 position estimation method of a guidance, navigation, and control system in accordance with aspects of the present disclosure.

[0027] Figure 4 is a diagrammatic view of a Figure 1 another example of a guidance, navigation, and control system of a materials handling vehicle in accordance with aspects of the present disclosure.

[0028] Figure 5 is a diagrammatic view of a Figure 1 example feature tracking system of a materials handling vehicle in accordance with aspects of the present disclosure. DETAILED DESCRIPTION

[0029] The following discussion presents embodiments of the application to enable a person skilled in the art to make and use the application. Various modifications to the illustrated embodiments will be readily apparent to those skilled in the art, and the principles described herein can be applied to other embodiments and applications without departing from the scope of the embodiments of the application. Thus, the embodiments of the application are not intended to be limited to the described embodiments, but are to be accorded the widest scope consistent with the principles and features disclosed herein.

[0030] The following detailed description is read with reference to the accompanying drawings in which like elements in different drawings have like reference numerals. The drawings depict only selected embodiments and are not intended to limit the scope of the embodiments of the application. The skilled artisan will recognize the example provided herein have a number of useful alternatives and fall within the scope of the embodiments of the application.

[0031] Before any embodiments of the application are explained in detail, it is to be understood that the application is not limited in its application to the details of construction and the arrangement of components set forth in the following description or illustrated in the accompanying drawings. The application is capable of other embodiments and of being practiced or being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and not limitation. As used herein, the terms "including," "comprising," or "having" and variations thereof are meant to encompass the items listed thereafter and equivalents thereof as well as additional items. Unless specified or limited otherwise, the terms "mounted," "connected," "supported," and "coupled," and variations thereof are used broadly and encompass both direct and indirect mountings, connections, supports, and couplings. Further, "connected" and "coupled" are not restricted to physical or mechanical connections or couplings.

[0032] It should also be appreciated that material handling vehicles are designed in various classes and configurations to perform various tasks. It will be apparent to those skilled in the art that the present disclosure is not limited to any particular material handling vehicle, and various other types of material handling vehicle classes and configurations can also be provided, including, for example, lift trucks, fork trucks, reach trucks, SWING (Registered Trademark) vehicles, turret trucks, side loaders, counterbalance trucks, pallet stacker trucks, order pickers, transfer trucks, tractors, and man-up trucks, and can be commonly found in warehouses, factories, shipyards, and anywhere that pallets, bulk packages, or large quantities of goods can need to be transported from one place to another. The various systems and methods disclosed herein are applicable to any of the following: operator-controlled material handling vehicles, pedestrian-controlled material handling vehicles, remotely-controlled material handling vehicles, and autonomously-controlled material handling vehicles. Further, the present disclosure is not limited to application with material handling vehicles. Rather, the present disclosure can be provided for other types of vehicles, such as automobiles, buses, trains, tractor trailers, agricultural vehicles, factory vehicles, etc.

[0033] It should be noted that the various material handling vehicles listed above can perform various load handling functions. For example, a material handling vehicle and / or a load handling portion of a material handling vehicle (e.g., forks, a mast, and / or a fork carriage, etc.) can be operated to move forks up and down, tilt, extend (e.g., move in and out of the forks), rotate, travel (e.g., move the material handling vehicle), and / or any combination thereof, to complete a load handling function.

[0034] It should be noted that for certain types of vehicles, there are various government agency, legal, regulatory, and code-mandated training requirements. For example, OSHA mandates that employers have a duty to train and supervise operators of various types of material handling vehicles. Re-certification is also required every three years. In certain instances, refresher training on relevant topics should be provided to operators as needed. In all instances, the operator maintains control of the material handling vehicle during performance of any action. Further, a warehouse manager maintains control of a fleet of material handling vehicles within a warehouse environment. Operator training and supervision provided by a warehouse manager requires proper operating practices, among other things, including the operator maintaining control of the material handling vehicle, paying attention to the operating environment, and always looking in the direction of travel, among other things.

[0035] In one example, a guidance, navigation, and control system for a materials handling vehicle can be configured to receive data from one or more sensors (e.g., one or more sensors located on the materials handling vehicle) and output an estimate of a position of the materials handling vehicle (e.g., a predicted future position, a current position, etc.). For example, the sensors can include sensors for monitoring odometry data of the materials handling vehicle, such as rotary encoders, traction encoders, steering encoders, etc. Alternatively or additionally, the sensors can include sensors for monitoring inertial measurement unit (IMU) data of the materials handling vehicle, such as accelerometers, gyroscopes, magnetometers, compasses, etc. Further, in some examples, the sensors can include sensors for monitoring visual data (e.g., images, etc.). For example, the materials handling vehicle can include one or more cameras, LiDAR, etc.

[0036] In one example, the guidance, navigation, and control system can receive both odometry data and inertial measurement unit data from the sensors and process the data through a filter, such as a Kalman filter, to determine an updated position estimate of the materials handling vehicle. In some examples, the system (e.g., a controller within the system) can further determine an amount of noise in each data set and utilize each of the odometry data, the inertial measurement unit data, and the noise to determine the updated position estimate of the materials handling vehicle.

[0037] In another example, the position of the materials handling vehicle can be estimated by processing the odometry data and the inertial measurement unit data through a first filter (e.g., a Kalman filter) to generate an intermediate position estimate. The intermediate position estimate can then be combined and processed through a second filter (e.g., a Kalman filter) to generate a more precise position estimate of the materials handling vehicle. In yet another example, the position of the materials handling vehicle can be estimated using visual data (e.g., images, video, etc. of an area surrounding the materials handling vehicle) using a visual sensor (e.g., a camera, LiDAR, etc.).

[0038] Figure 1An example of a warehouse 100 is shown, which can include one or more material handling vehicles 105. In one example, to facilitate organization of the warehouse 100, it can be desirable to track the location (e.g., physical location) of the material handling vehicles 105 within the warehouse 100. For example, tracking the location of the material handling vehicles 105 can allow for delegation from a warehouse management system (WMS) to the material handling vehicle that is closest to a pick / put down location, which can increase overall efficiency in the warehouse 100. Further, in another example, tracking the location of the material handling vehicles 105 can set values for the maximum speed, lift height, etc. of the vehicle. For example, the maximum speed of the vehicle can be reduced in areas with high foot traffic, or the maximum lift height of the vehicle can be reduced in areas with insufficient vertical clearance. In yet another example, tracking the location of the material handling vehicles can increase operator awareness of nearby vehicles within the warehouse.

[0039] In one particular example, the location of a material handling vehicle can be referred to as a pose, which can include an X-coordinate and a Y-coordinate of the material handling vehicle and a heading angle of the material handling vehicle. In other examples, it can be difficult to track the location (e.g., pose) of the material handling vehicles 105 due to sensor noise, processor requirements, oversize of the solution space, etc. However, the location of the material handling vehicle can be estimated based on the speed, acceleration, direction, or other variables (e.g., kinematic properties) of the material handling vehicle 105. For example, using dead reckoning, a past known location of the material handling vehicle 105 can be used to calculate an estimated current location of the material handling vehicle 105 based on a known speed of movement, acceleration, and direction.

[0040] In some examples, the material handling vehicles 105 can include a guidance, navigation, and control system 110 to track the location (e.g., position, orientation, speed, acceleration, etc.) of the material handling vehicles 105. In some examples, the guidance, navigation, and control system 110 can further allow the material handling vehicles 105 to operate autonomously (or partially autonomously). In further examples, the guidance, navigation, and control system 110 of the material handling vehicles 105 can be integrated with or exchange information with a telematics system (e.g., a remote information processing system) of the warehouse 100 to provide location and tracking data of the material handling vehicles 105. The guidance, navigation, and control system 110 can include a controller 120 (e.g., including a processor and a memory) that can be in communication (e.g., wired or wireless communication) with one or more first sensors 115 of the material handling vehicle 105. For example, the first sensors 115 can include an inertial measurement unit, a gyroscope, an accelerometer, a speedometer, an encoder, a magnetometer, a camera, a LiDAR, or any other known sensor.

[0041] ​The materials handling vehicle 105 can further include a drive system including one or more wheels 125, which can each include one or more second sensors 130. For example, the second sensors 130 can be in the form of a rotary encoder, an inertial measurement unit, a gyroscope, an accelerometer, a speedometer, a magnetometer, a camera, a LiDAR, or any other known sensor. Moreover, the second sensors 130 can be in communication with the guidance, navigation, and control system 110 (e.g., via the controller 120).

[0042] In one particular example, the guidance, navigation, and control system 110 can utilize data from the first sensors 115 and the second sensors 130 to estimate a position of the materials handling vehicle 105 within the warehouse 100. For example, the guidance, navigation, and control system 110 can utilize a current (e.g., known) position 135 of the materials handling vehicle 105 in combination with data from the sensors 115, 130 to calculate an estimated position 140 of the materials handling vehicle 105. Thus, as the materials handling vehicle 105 moves (as indicated by arrow 145), the guidance, navigation, and control system 110 can continuously (or intermittently) calculate a next (e.g., anticipated) position of the materials handling vehicle 105. Moreover, this information can be provided to a telematics system of the warehouse 100 to facilitate tracking of the materials handling vehicle 105 throughout the warehouse 100.

[0043] Figure 2 An example of the guidance, navigation, and control system 110 is shown, which can utilize a Kalman filter 205 (or other filter) to combine data from the sensors 115, 130 in order to provide a position estimate of the materials handling vehicle 105. For example, the Kalman filter 205 of the guidance, navigation, and control system 110 can receive a first type of data from the first sensors 115 and a second type of data from the second sensors 130, and then the filter 205 can combine the first type of data from the first sensors 115 and the second type of data from the second sensors 130 along with noise in the data to provide a position estimate of the materials handling vehicle 105.

[0044] In one particular example, the Kalman filter 205 can receive measured position data 210, which can correspond to inertial measurement unit data from the first sensor 115. Due to various environmental factors, the measured position data 210 from the first sensor 115 can include noise 215, which can affect the accuracy of the measurements. In addition to the measured position data 210, the Kalman filter 205 can also receive modeled position data 220, which can correspond to odometry data from the second sensor 130. Due to various environmental factors, the modeled position data 220 from the second sensor 130 can include noise 225, which can affect the accuracy of the measurements. Based on the modeled position data 220 and the measured position data 210 (of the position of the materials handling vehicle 105) combined with the respective noise 215, 225, the Kalman filter 205 can generate an updated position estimate of the materials handling vehicle 105 that accounts for the noise 215, 225 within the measured position data 210 and the modeled position data 220.

[0045] Accordingly, to account for the noise 215, 225 within the measured position data 210 and the modeled position data 220, the Kalman filter 205 can be used to reduce the impact of the noise 215, 225 on the data 210, 220. Furthermore, by combining the measured position data 210 from the first sensor 115 and the modeled position data 220 from the second sensor 130, the system 110 can have built-in redundancy. For example, if the first sensor 115 or the second sensor 130 loses communication with the system 110, the system 110 can still be able to estimate the position of the materials handling vehicle 105 (e.g., by using the other sensor of the first sensor 115 or the second sensor 130 that remains in communication with the system 110).

[0046] In some other examples, the measured position data 210 can correspond to odometry data from the second sensor 130, while the modeled position data 220 can correspond to inertial measurement unit data from the first sensor 115. For example, the input variables into the filter 205 can include angular velocity, linear velocity, acceleration, heading angle, or any other known variable that can be measured by the sensors 115, 130.

[0047] Figure 3A method 300 for estimating a location of a materials handling vehicle 105 based on measured location data 210 and modeled location data 220 is shown in accordance with some aspects of the present disclosure. The method 300 can be used with measured location data 210 (e.g., from a first sensor 115) and modeled location data 220 (e.g., from a second sensor 130) to calculate estimated location data 230 of the materials handling vehicle 105 within the warehouse 100, and can be particularly useful in providing a robust location estimate for the materials handling vehicle 105 within the warehouse 100 relative to previously used methods. While the method 300 is described with reference to the guidance, navigation, and control system 110 of the materials handling vehicle 105 discussed above, the method can also be used with other types of guidance, navigation, and control systems for various uses. Additionally, the operations of the method 300 need not be performed in the particular order discussed below, and in some cases, can be implemented with other control devices and systems not explicitly described herein.

[0048] With continued reference to Figure 3 At stage 305, the guidance, navigation, and control system 110 can use the modeled location data 220 (e.g., using a state extrapolation equation, which can be a mathematical model used in dynamic systems to predict future states of a system based on a current state of the system) to predict a location of the materials handling vehicle 105. For example, data from the second sensor 130 can be used to predict a location of the materials handling vehicle 105 based on an acceleration, a velocity, an angular velocity, or past / current location(s) of the materials handling vehicle 105. In one particular example, the modeled location data 220 can use velocity and steering (e.g., directional) odometry data from one or more sensors to predict a location and heading angle of the materials handling vehicle 105. However, in other examples, the first sensor 115 can be used alone (e.g., without using the second sensor 120) to predict a location of the materials handling vehicle 105.

[0049] At stage 310, the guidance, navigation, and control system 110 can estimate an amount of noise 225 in the modeled location data 220 (e.g., within data from the sensor 115, the sensor 130), which can be used at stage 315 to calculate an amount of uncertainty (e.g., a statistical solution space for a location) in the location data predicted using the modeled location data 220. In some examples, this stage can include calculating a process noise covariance matrix (e.g., a mathematical representation of uncertainty or randomness in a system state transition model), and then calculating a state covariance extrapolation equation. At this point, the guidance, navigation, and control system 110 can determine a first calculated value of a predicted location of the materials handling vehicle 105 based on the modeled location data 220.

[0050] At stage 320, the guidance, navigation, and control system 110 can measure a position of the materials handling vehicle 105, which can correspond to the measured position data 210. For example, data from the first sensor 115 can be used to measure a position of the materials handling vehicle 105. In one particular example, the sensor can be a six-axis inertial measurement unit that provides accelerometer and gyroscope data for measuring acceleration and angular velocity of the materials handling vehicle 105. However, in other examples, the second sensor 130 can be used to measure the position of the materials handling vehicle. Accordingly, at stage 325, the guidance, navigation, and control system 110 can estimate the amount of noise 215 in the measured position data 210 (e.g., by calculating a measured noise covariance matrix, which can represent the uncertainty or noise associated with the measurements used in the system). At this point, the guidance, navigation, and control system 110 can determine a second calculated value of the position of the materials handling vehicle 105 based on the measured position data 210, which can be independent of the first calculated value based on the modeled position data 220.

[0051] At stage 330, the guidance, navigation, and control system 110 can solve (e.g., calculate) a Kalman gain, which can be used to determine how to weight the first calculated value or the second calculated value of the position of the materials handling vehicle 105. At stage 335, the guidance, navigation, and control system 110 can estimate the position of the materials handling vehicle based on the position data 230 of the materials handling vehicle 105 by combining the measured position data 210 and the modeled position data 220 within the Kalman filter 205 (e.g., via fusion of the measured position data and the modeled position data). In some examples, the data, after being modified by the Kalman gain, provides a position estimate based on both the measured position data 210 and the modeled position data 220, and accounts for the noise 215, 225 in both the measured position data 210 and the modeled position data 220. Further, at stage 340, the guidance, navigation, and control system 110 can calculate the amount of noise (e.g., noise in the data from the sensors 115, 130) within the guidance, navigation, and control system 110 by combining the covariance matrices of the measurement noise and the model noise.

[0052] It should be appreciated that the above-described method 300 can be an iterative process that is continuously performed throughout the operation (e.g., manual or autonomous operation) of the materials handling vehicle 105 to provide position tracking of the materials handling vehicle 105.

[0053] Reference is now made to Figure 4In some examples, the guidance, navigation, and control system 110 can further include one or more downstream systems 400 that utilize the estimated position data 230 to perform higher-level localization and tracking functions, such as an absolute position measurement system 405, an environmental feature tracking 410, and the like. For example, as previously described, one or more first sensors 115 (e.g., relative position-type sensors, including accelerometers, compasses, gyroscopes, magnetometers, and the like) can output data into the Kalman filter 205. Correspondingly, one or more second sensors 130 (e.g., modeled position-type sensors, including encoders, steering angle sensors, and the like) can output data into the Kalman filter 205. As previously described, the Kalman filter 205 can combine data from the sensors 115, 130 and output a refined relative position estimate (e.g., the estimated position data 230).

[0054] In some examples, this more refined data (e.g., the estimated position data 230) can then be used by one or more downstream systems 400. For example, the absolute position measurement system 405 can use the Kalman-filtered estimated position data 230 to help determine the absolute position of the materials handling vehicle 105 within a global frame of reference (e.g., a warehouse or similar facility). In another example, the feature (e.g., object) tracking system 410 can use the Kalman-filtered estimated position data 230 to help determine the position of external objects (e.g., obstacles) even after the objects leave the field of view of the sensors on the materials handling vehicle 105 (e.g., object permanence).

[0055] In some examples, the use of the estimated position data 230 (e.g., the combination of data from the sensors 115, 130) can help reduce the number of possible solutions for the position of the materials handling vehicle 105. For example, in situations where there can be multiple options for the position of the materials handling vehicle (e.g., due to a sparse feature environment, sensor noise, unknown initial position, and the like), the use of the estimated position data 230 can reduce the number of possible positions for the materials handling vehicle. In some examples, this can further help reduce the computational time (and corresponding required computational power) of the system.

[0056] In other words, while the estimated position data 230 can reflect movement of the materials handling vehicle 105 from a previously known position, the data 230 itself can not indicate the position of the materials handling vehicle 105 within the larger environment (e.g., warehouse). Thus, to address this issue, the absolute position measurement system 405 can include a global localization module configured to update the absolute position of the materials handling vehicle 105. For example, the global localization module (e.g., within the absolute position measurement system 405) can update the absolute position of the materials handling vehicle by receiving and processing the measured position data 210 (e.g., corresponding to data from the first sensor 115) and the modeled position data 220 (e.g., corresponding to data from the second sensor 130) using a filter (e.g., Kalman filter 205). In one particular example, combining the measured position data 210 and the modeled position data 220 can narrow the solution space (e.g., possible positions of the materials handling vehicle 105) of the absolute position measurement system 405, where multiple possible solutions are available (e.g., there can be multiple candidate positions initially). In other words, incorrect options can be eliminated, which can help speed up the computation time of the absolute position measurement system 405. Moreover, in some examples, as the absolute position measurement system 405 operates iteratively, the refined solution space can reduce the number of iterations required and improve computational efficiency.

[0057] Figure 5 An example of a feature tracking system 410 (e.g., object permanence system) is shown, which can be configured to detect and remember the position of objects within a warehouse (e.g., even when the objects are outside the field of view of a sensor). In some examples, the materials handling vehicle 105 can include a sensor 505 (e.g., a third sensor, such as a camera, etc.) having a predetermined field of view 515. In some examples, as the materials handling vehicle 105 travels throughout the warehouse 100, objects (e.g., object 510) can enter and exit the field of view 515 of the sensor 505. However, in some examples, with existing systems, objects outside the field of view 515 of the sensor 505 can not be recognized by the materials handling vehicle 105, which can be undesirable.

[0058] However, with the feature tracking system 410, the materials handling vehicle 105 can be able to track and remember the location of the object 510 outside of the field of view 515 of the sensor 505 (allowing the object 510 to have previously been within the field of view 515 of the sensor 505). In some examples, the object 510 can be initially detected within the field of view 515 of the sensor 505 as the materials handling vehicle 105 moves in the direction indicated by arrow 520. However, as the materials handling vehicle 105 continues to travel, the object 510 can move outside of the field of view 515 of the sensor 505. However, the feature tracking system 410 can record the previously detected object 510 (e.g., an obstacle, an environmental feature, etc.), the positioning (e.g., location) relative to the materials handling vehicle 105’s location at which the external object 415 was initially detected.

[0059] Accordingly, as the materials handling vehicle 105 continues to proceed in the direction indicated by arrow 520, a location estimate for the object 510 can be generated based on the known movements of the materials handling vehicle 105 (e.g., from the measured location data 210 and the modeled location data 220). In use, even though the object 510 is no longer within the field of view 515 of the sensor 505, the feature tracking system 410 can continue to update the estimated location of the previously detected object 510 with the estimated location data 230. In some examples, the feature tracking system 410 can artificially increase the size of the object 510 around the object 510 (e.g., create a buffer zone 525) to account for the accumulated location uncertainty as the object 510 is not directly detected by the sensor.

[0060] In some implementations, the devices or systems disclosed herein can be utilized, manufactured, or installed using methods embodying aspects of the present application. Correspondingly, any description herein of particular features, capabilities, or intended purposes of a device or system is generally intended to include disclosure of methods of using such devices for the intended purposes, methods of otherwise implementing such capabilities, methods of manufacturing the relevant components of such devices or systems (or the devices or systems as a whole), and methods of installing the disclosed (or otherwise known) components to support such purposes or capabilities. Similarly, unless otherwise indicated or limited, any discussion herein of methods for manufacturing or using (including installing) a particular device or system is intended to inherently include disclosure of the used features and implemented capabilities of such devices or systems as embodiments of the present application.

[0061] Further Examples

[0062] Example 1. A method of tracking a materials handling vehicle, the method comprising: estimating a position of the materials handling vehicle based on modeled position data from a first sensor, the first sensor configured to model an odometry of the vehicle; measuring a position of the materials handling vehicle based on measured position data from a second sensor, the second sensor configured to measure a relative motion of the vehicle; determining an amount of noise in both the modeled position data from the first sensor and the measured position data from the second sensor; and updating the estimated position of the materials handling vehicle based on the position data from the first sensor, the second sensor, and the amount of noise.

[0063] Example 2. The method of example 1, wherein the modeled position data is based on odometry data of the materials handling vehicle.

[0064] Example 3. The method of example 1 or example 2, wherein the measured position data is based on inertial measurement unit data of the materials handling vehicle.

[0065] Example 4. The method of any of examples 1-3, wherein updating the estimated position of the materials handling vehicle comprises combining the modeled position data from the first sensor and the measured position data from the second sensor within a Kalman filter.

[0066] Example 5. The method of any of examples 1-4, further comprising: using the updated estimated position of the materials handling vehicle to track a position of an object that is outside a field of view of a vision sensor of the materials handling vehicle.

[0067] Example 6. The method of example 5, further comprising: creating a buffer zone around the tracked object to prevent the materials handling vehicle from coming into contact with the tracked object.

[0068] Example 7. The method of any of examples 1-6, further comprising: adjusting at least one operational parameter of the materials handling vehicle based on the estimated position of the materials handling vehicle.

[0069] Example 8. The method of example 7, wherein the operational parameter comprises at least one of a maximum speed, a maximum lift height, or a maximum acceleration.

[0070] Example 9. A guidance, navigation, and control system for a materials handling vehicle, the system comprising: a first sensor to measure odometry data; a second sensor to measure inertial measurement unit data; and a processor to: predict a position of the materials handling vehicle based on the odometry data from the first sensor; measure the position of the materials handling vehicle based on the inertial measurement unit data from the second sensor; and combine the odometry data from the first sensor and the inertial measurement unit data from the second sensor within a Kalman filter to generate an updated position estimate of the materials handling vehicle.

[0071] Example 10. The system of example 9, wherein the processor computes an amount of noise in both the measured odometry data and the measured inertial measurement unit data.

[0072] Example 11. The system of example 10, wherein the updated position estimate of the materials handling vehicle is based on the odometry data from the first sensor, the inertial measurement unit data from the second sensor, and the noise in both the measured odometry data and the measured inertial measurement unit data.

[0073] Example 12. The system of any of examples 9-11, further comprising: a feature tracking system configured to track a position of an object outside a sensor field of view based on the updated position estimate of the materials handling vehicle.

[0074] Example 13. The system of example 12, wherein the feature tracking system is configured to create a buffer around the tracked object to account for potential drift in the updated position estimate.

[0075] Example 14. The system of any of examples 9-13, further comprising: an absolute position measurement system configured to determine an absolute position of the materials handling vehicle within a warehouse based on the updated position estimate.

[0076] Example 15. The system of any of examples 9-14, wherein the processor is further configured to adjust an operational parameter of the materials handling vehicle based on the updated position estimate, wherein the operational parameter comprises at least one of a maximum speed, a lift height, or a turning radius.

[0077] Example 16. The system of any of examples 9-15, wherein the processor is further configured to communicate the updated position estimate to a warehouse management system to facilitate tracking of the materials handling vehicle throughout the warehouse.

[0078] Example 17. A method of tracking an object using a guidance, navigation, and control system of a materials handling vehicle, the method comprising: combining measured position data from a first sensor and modeled position data from a second sensor using a Kalman filter to estimate a position of the materials handling vehicle; detecting an object within a field of view of a third sensor on the materials handling vehicle; recording a position of the detected object relative to the estimated position of the materials handling vehicle; and updating the estimated position of the detected object based on subsequent estimated positions of the materials handling vehicle even when the object is no longer within the object field of view of the sensor.

[0079] Example 18. The method of example 17, further comprising: communicating the estimated position of the detected object to a warehouse management system to facilitate tracking of obstacles within a warehouse environment.

[0080] Example 19. The method of example 17, further comprising: creating a buffer zone around the estimated position of the object; and preventing the materials handling vehicle from entering the buffer zone.

[0081] Example 20. The method of example 19, wherein the size of the buffer zone increases over time to account for potential drift in the estimated position of the materials handling vehicle.

[0082] Also, as used herein, unless otherwise indicated, the term "or" indicates a non-exclusive list of alternatives, such that, for example, A, B, or C means A; B; C; A and B; A and C; B and C; and A, B, and C. Accordingly, as used herein, the term "or" only indicates an exclusive alternative when preceded by the exclusive term "either," "one of," "only one of," or "exactly one of." For example, the phrase "one of A, B, or C" indicates the following options: A, but not B and C; B, but not A and C; and C, but not A and B. A list of items following "one or more of" (and variants thereof) and including "or" to separate listed items indicates an option of one or more of any of the listed items. For example, the phrases "one or more of A, B, or C" and "at least one of A, B, or C" indicate the following options: one or more A; one or more B; one or more C; one or more A and one or more B; one or more B and one or more C; one or more A and one or more C; and one or more of A, one or more of B, and one or more of C. Similarly, a list of items following "a plurality of" (and variants thereof) and including "or" to separate listed items indicates an option of multiple instances of any of the listed items. For example, the phrases "a plurality of A, B, or C" and "two or more of A, B, or C" indicate the following options: A and B; B and C; A and C; and A, B, and C.

[0083] In some examples, aspects of the disclosed technology, including computerized implementations of methods in accordance with the disclosed technology, can be implemented using standard programming or engineering techniques to produce software, firmware, hardware, or any combination thereof, to control a processor device (e.g., serial or parallel general or special purpose processor chips, single or multi-core chips, microprocessors, field programmable gate arrays, control units, arithmetic logic units, and any various combinations thereof, etc.), a computer (e.g., a processor device operatively coupled to a memory), or another electronically operated controller to implement aspects detailed herein. Accordingly, for example, aspects of the disclosed technology can be implemented as a set of instructions tangibly embodied on a non-transitory computer- readable medium, such that the processor device can implement the instructions based on reading the instructions from the computer-readable medium. Some examples of the disclosed technology can include (or utilize) a control device, such as an automated device, a special or general purpose computer including various computer hardware, software, firmware, etc., consistent with the discussion below. As a specific example, a control device can include a processor, microcontroller, field programmable gate array, programmable logic controller, logic gates, etc., as well as other typical components known in the art for implementing appropriate functionality (e.g., memory, communication systems, power sources, user interfaces, and other inputs, etc.). In some examples, a control device can include a centralized hub controller that receives, processes, and (re)transmits control signals and other data to and from other distributed control devices (e.g., engine controllers, implement controllers, drive controllers, etc.), including as part of a central hub-and-spoke architecture or otherwise.

[0084] As used herein, the term "article of manufacture" is intended to encompass a computer program accessible from any computer-readable device, carrier, or media (e.g., non-transitory signal media). For example, computer-readable media can include but are not limited to magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips, etc.), optical disks (e.g., compact disk (CD), digital versatile disk (DVD), etc.), smart cards, and flash memory devices (e.g., card, stick, etc.). Additionally, it should be appreciated that a carrier wave can be employed to carry computer-readable electronic data such as those used in transmitting and receiving electronic mail or in accessing a network such as the Internet or a local area network (LAN). Those skilled in the art will recognize many modifications can be made to this configuration without departing from the scope and spirit of the claimed subject matter.

[0085] Certain operations of methods according to the disclosed technology or certain operations of systems performing those methods can be represented schematically in the drawings or otherwise discussed herein. Unless otherwise specified or limited, representation of particular operations in a particular spatial order in the drawings does not necessarily require that the operations be performed in that particular order corresponding to the particular spatial order. Accordingly, certain operations represented in the drawings or otherwise disclosed herein can be performed in a different order than the order explicitly stated or described, in a manner appropriate for a particular example of the disclosed technology. Further, in some examples, certain operations can be performed in parallel, including by dedicated parallel processing devices, or by separate computing devices configured to interoperate as part of a larger system.

[0086] As used herein in the context of computer-implemented, unless otherwise specified or limited, the terms "component," "system," "module," "block," "device," and the like are intended to encompass part or all of a computer-related system including hardware, software, a combination of hardware and software, or software in execution. For example, a component can be, but is not limited to, a processor device, a process executed by a processor device, an object, an executable, a thread of execution, a computer program, or a computer. By way of illustration, both an application running on a computer and the computer itself can be a component. One or more components (or systems, modules, etc.) can reside within a process or thread of execution, can be located on one computer, can be distributed between two or more computers or other processor devices, or can be included within another component (or system, module, etc.).

[0087] As used herein, unless otherwise defined or limited, directional terms are used for ease of reference to discuss particular drawings or examples. For example, references to downward (or other) directions or top (or other) positions can be used to discuss aspects of particular examples or drawings, but similar orientations or geometries are not necessarily required in all installations or configurations.

[0088] Additionally, unless otherwise indicated or implied, the terms "about" and "approximately" as used herein with reference to a reference value means a variation of plus or minus 15% or less of the reference value, including the endpoints of the range. Similarly, the term "substantially equal" as used herein with reference to a reference value means a variation of less than plus or minus 30% of the reference value, including the endpoints. In particular instances, "substantially" can specifically indicate a variation in one numerical direction relative to a reference value. For example, "substantially less" than a reference value (equal) indicates a value that is 30% or more less than the reference value, while "substantially more" than a reference value (equal) indicates a value that is 30% or more greater than the reference value.

[0089] The foregoing description of the disclosed embodiments is provided as an enabling teaching of the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art in view of the foregoing description, and the principles as defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Accordingly, the application is not intended to be limited to the embodiments shown herein and is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for tracking a material handling vehicle, the method comprising: The position of the material handling vehicle is estimated based on modeling location data from a first sensor configured to model the vehicle's odometer. The position of the material handling vehicle is measured based on position data from a second sensor configured to measure the relative motion of the vehicle. Determine the amount of noise in both the modeling location data from the first sensor and the measurement location data from the second sensor; as well as The estimated position of the material handling vehicle is updated based on position data from the first sensor, the second sensor, and the noise level.

2. The method as described in claim 1, characterized in that, The modeling location data is based on the odometer data of the material handling vehicle.

3. The method as described in claim 1, characterized in that, The measured location data is based on the inertial measurement unit data of the material handling vehicle.

4. The method as described in claim 1, characterized in that, Updating the estimated location of the material handling vehicle includes: The modeling location data from the first sensor and the measurement location data from the second sensor are combined within a Kalman filter.

5. The method of claim 1, further comprising: The updated estimated position of the material handling vehicle is used to track the position of objects outside the field of view of the vehicle's vision sensors.

6. The method of claim 5, further comprising: A buffer zone is created around the tracked object to prevent the material handling vehicle from colliding with it.

7. The method of claim 1, further comprising: At least one operating parameter of the material handling vehicle is adjusted based on the estimated position of the material handling vehicle.

8. The method as described in claim 7, characterized in that, The operating parameters include at least one of maximum speed, maximum lifting height, or maximum acceleration.

9. A guidance, navigation, and control system for a material handling vehicle, the system comprising: A first sensor, used to measure odometer data; The second sensor is used to measure data from the inertial measurement unit. as well as Processor, the processor being used for: The location of the material handling vehicle is predicted based on the odometer data from the first sensor; The position of the material handling vehicle is measured based on the inertial measurement unit data from the second sensor; as well as The odometer data from the first sensor and the inertial measurement unit data from the second sensor are combined within a Kalman filter to generate an updated position estimate of the material handling vehicle.

10. The system as described in claim 9, characterized in that, The processor calculates the amount of noise in both the measured odometer data and the measured inertial measurement unit data.

11. The system as claimed in claim 10, characterized in that, The updated position estimate of the material handling vehicle is based on the odometer data from the first sensor, the inertial measurement unit data from the second sensor, and the noise in both the measured odometer data and the measured inertial measurement unit data.

12. The system of claim 9, further comprising: A feature tracking system configured to track the position of objects outside the sensor's field of view based on the updated position estimate of the material handling vehicle.

13. The system as described in claim 12, characterized in that, The feature tracking system is configured to create a buffer around the tracked object to account for potential offsets in the updated location estimate.

14. The system of claim 9, further comprising: An absolute position measurement system is configured to determine the absolute position of the material handling vehicle within the warehouse based on the updated position estimate.

15. The system as described in claim 9, characterized in that, The processor is further configured to adjust the operating parameters of the material handling vehicle based on the updated position estimate, wherein the operating parameters include at least one of maximum speed, lifting height, or turning radius.

16. The system as described in claim 9, characterized in that, The processor is further configured to transmit the updated location estimate to the warehouse management system to facilitate tracking of the material handling vehicles throughout the warehouse.

17. A method for tracking objects using a guidance, navigation, and control system for a material handling vehicle, the method comprising: The position of the material handling vehicle is estimated by combining the measured position data from the first sensor and the modeled position data from the second sensor using a Kalman filter. Detecting objects within the field of view of the third sensor on the material handling vehicle; Record the position of the detected object relative to the estimated position of the material handling vehicle; as well as Even when the object is no longer within the field of view of the sensor, the estimated position of the detected object is still updated based on the subsequent estimated position of the material handling vehicle.

18. The method of claim 17, further comprising: The estimated location of the detected object is transmitted to the warehouse management system to facilitate obstacle tracking within the warehouse environment.

19. The method of claim 17, further comprising: Create a buffer around the estimated location of the object; as well as To prevent the material handling vehicles from entering the buffer zone.

20. The method described in claim 19, characterized in that, The size of the buffer increases over time to account for potential offsets in the estimated position of the material handling vehicle.

Images