System and method for determining the instantaneous absolute position and orientation of an entity in a navigation space

Abstract

A method and system for determining a precise absolute position and a precise absolute orientation of an entity in a navigation space is provided, the system including: a plurality of sensors; a coarse absolute position and orientation estimation unit that determines a coarse absolute position and / or a coarse absolute orientation of the entity based on position data captured by the sensors at a predefined frequency / interval; a relative position and orientation estimation unit that determines a relative position and / or a relative orientation of the entity based on data sets captured from the sensors; a navigation guidance unit that provides and updates specific attributes of the navigation space; and an analysis unit that determines the precise absolute position or the precise absolute orientation of the entity by using a navigation map to fine-tune the coarse absolute position based on the relative positions and the coarse absolute orientation based on the relative orientation.

Description

Technical Field

[0001] (Related Application) This application claims the priority of Indian Provisional Patent Application (PPA) Serial No. 202041052367, filed on December 1, 2020, with the title "SYSTEM AND METHOD FOR DETERMINING AN INSTANTANEOUS ABSOLUTE POSITION AND ORIENTATION OF AN ENTITY IN A NAVIGATION SPACE". The content of the above PPA is hereby incorporated by reference in its entirety.

Background Art

[0002] Generally, embodiments of the present invention relate to position sensing and navigation systems. In particular, embodiments of the present invention relate to position sensing and navigation systems for moving objects. More specifically, embodiments of the present invention relate to methods and systems for determining the instantaneous absolute position and orientation of an entity such as a robot (BOT) in a navigation space, hereinafter referred to as refined absolute position and refined absolute orientation, respectively, in this document.

[0003] (Description of Related Art) According to an exemplary scenario, determining the position and rotational orientation of an object within a defined space is a practical problem that has led to many solutions, each of which is specialized to solve the specific requirements of an application. Some existing techniques for determining the position or orientation of an object (stationary or moving) within a given space include, for example, optical, ultrasonic, or wireless-based techniques. However, most of the existing techniques do not provide angular orientation information, and the existing techniques that enable angular orientation measurement lack position determination. For example, some existing techniques employ the Global Positioning System (GPS) for position determination but lack the ability to determine the orientation of stationary objects, and the operability of GPS is also troubled by signal attenuation and reflection indoors and is thus not a good choice for indoor applications. Magnetometers provide absolute orientation but are very susceptible to dynamically changing magnetic fields near the sensor. They can function well in controlled scenarios, but for baggage handling applications, the magnetism of the baggage can make the measured values unreliable. Ultrasonic methods work well indoors but lack orientation determination. Furthermore, existing techniques such as laser-based technology (Lidar) provide both position and orientation but do so at a huge cost. Additionally, existing techniques that use position data associated with objects loosely fixed on the floor, such as furniture, machinery, etc., as reference points are very vulnerable to dynamically changing scenarios on the floor.

[0004] Furthermore, while navigating through a narrow passage, it is important to keep the entity near a predefined path (e.g., the centerline of the passage) to avoid any collisions or misinterpretations with fixed structures such as walls as obstacles. To keep the entity along the predefined path, accurate information about the position of the entity (e.g., within an error of a few centimeters) is absolutely essential. To keep the entity on the ideal path, the current position of the entity and the deviation from the ideal path need to be accurately grasped with a desired error, for example, less than 10 centimeters.

[0005] Therefore, there is a need for a cost-effective alternative method and system for determining the absolute position and orientation of an entity while providing good accuracy, along with the elimination of any dependencies on dynamically changing scenarios in the navigation space, except for planned changes such as changing the navigation route or modifying the layout to break through walls. Further, there is a need for a system and method for finding the absolute position of a stationary or moving entity (hereinafter referred to as BOT) in a 2D coordinate system (e.g., orthogonal), with the assistance of a guiding entity (e.g., a proprietary map) that dynamically provides the required guidance regarding the use of diverse datasets to accurately arrive at the required absolute position for a given navigation segment.

[0006] The above-mentioned drawbacks, disadvantages, and problems are addressed herein and will be understood by reading and studying the following specification.

[0007] (Objectives of Embodiments) A primary object of the present invention is to provide a system and method for determining the precise absolute position and precise absolute orientation of an entity in a navigation space in a cost-effective manner with good accuracy while eliminating any dependencies on dynamically changing scenarios or unplanned changes in the navigation space. Without reference to historical data, the quality of the absolute position remains the same and does not degrade over any time interval due to dependencies on the recency of old data.

[0008] Another object of the embodiments herein is to provide a system and method for determining the precise absolute position and precise absolute orientation of an entity in a navigation space based on the extraction of diverse features in the navigation space using diverse sensors used to seamlessly assist in improving the accuracy of absolute position and orientation, including on-the-fly switchovers.

[0009] Yet another object of embodiments of this specification is to realize an accurate absolute position by using a rough absolute position and a unique combination of relative positions extracted from various sensors using specific features in a navigation space, and to provide a system and method for determining a precise absolute position and a precise absolute orientation of an entity in the navigation space.

[0010] Yet another object of embodiments of this specification is to provide a system and method for determining a precise absolute position and a precise absolute orientation of an entity in a navigation space by using a seamless switchover between sensors during navigation based on a context supported by a unique navigation map.

[0011] These and other objects and advantages of the embodiments of this specification will become readily apparent from the following detailed description when used in conjunction with the accompanying drawings.

Summary of the Invention

[0012] The following details present a simplified summary of the invention of the embodiments of this specification and provide a basic understanding of some aspects of the embodiments of this specification. The summary of the invention is not an extensive overview of the embodiments of this specification. It is not intended to identify the main / important elements of the embodiments of this specification or to define the scope of the embodiments of this specification. Its sole purpose is to present the concepts of the embodiments of this specification in a simplified form as a prelude to the more detailed description presented later.

[0013] Other objects and advantages of the embodiments of this specification will become readily apparent from the following description when used in conjunction with the accompanying drawings. However, it should be understood that the following description, while showing preferred embodiments and numerous specific details thereof, is given by way of illustration and not by way of limitation. Many changes and modifications may be made within the scope of the embodiments of this specification without departing from the spirit thereof, and the embodiments of this specification include all such modifications.

[0014] The summary of the present invention is provided to introduce, in a simplified form, a selection of concepts that are further described below in the detailed description. The summary of the present invention is not intended to identify the key or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0015] Various embodiments of the present specification provide a system that determines the absolute position and absolute orientation of entities in a navigation space in a cost-effective manner with good accuracy while eliminating any dependency on dynamically changing scenarios or unplanned changes in the navigation space. Without reference to historical data, the quality of the absolute position remains the same and does not degrade over any time interval due to dependency on licensees of old data.

[0016] According to one embodiment of the present specification, a system for determining the precise absolute position and precise absolute orientation of an entity in a navigation space is disclosed. According to one embodiment of the present invention, the system includes a plurality of sensors including a first set of sensors disposed at a first plurality of positions on the entity, and the first set of sensors is part of a Cartesian coordinate system provided by a local positioning system formed using technologies such as, but not limited to, UWB, Bluetooth®, Zig-bee®, ultrasonic, and others. According to an embodiment of the present invention, the system includes a second diverse set of sensors disposed at a second plurality of positions on the entity. The system is also configured to determine at least one of the rough absolute position and rough absolute orientation of the entity based on the position data captured by the first set of sensors in a two-dimensional orthogonal plane of the Cartesian coordinate system at a predetermined frequency / interval, and includes a rough absolute position estimation unit. Further, the system includes a relative position and orientation estimation unit configured to determine at least one of a plurality of relative positions and relative orientations of the entity with respect to a predetermined path based on a dataset captured from the second diverse set of sensors, and the captured data represents one of the relative deviation and relative tilt of the entity with respect to a preset known fixed physical feature in the navigation space. Further, the system includes a navigation guidance unit configured to provide unique attributes based on a desired navigable layout identified in an indoor navigation space and to dynamically update one or more attributes of a navigation map as learning / feedback based on historical navigation data. Further, the system includes an analysis unit configured to determine at least one of the precise absolute position and precise absolute orientation of the entity by fine-tuning the rough absolute position and rough absolute orientation based on one or more of a plurality of inputs provided by the relative position and orientation estimation unit, the rough absolute position of the entity, and the navigation map.

[0017] According to one embodiment of the present specification, the analysis unit aligns a predetermined path to be parallel to the X-axis or Y-axis in a two-dimensional orthogonal plane, and rotates the navigation plane associated with the predetermined path by a rotation angle to generate a transformed navigation plane, thereby transforming the predetermined path. The rough absolute position is also rotated through the same rotation angle to obtain the transformed rough absolute position of the entity. By correcting / calibrating the transformed rough absolute position of the entity, based on one or more of a plurality of inputs from the relative position and orientation estimation unit, the transformed precise absolute position of the entity is obtained. The transformed rough absolute position of the entity is corrected / calibrated by replacing either the X value or the Y value of the transformed rough absolute position coordinates of the entity with a combination of the transformed ideal coordinate value of the object and one or more of a plurality of inputs from the relative position and orientation estimation unit, depending on the rotation applied during the transformation of the plane. The transformed ideal coordinate value of the object is equal to the transformed ideal starting point coordinate value selected based on the applied transformation, and the ideal starting point coordinates are the coordinates of the starting node of the line segment obtained from the navigation map. The precise absolute position of the entity is obtained by rotating the navigation plane back in the opposite direction through the same rotation angle to the original orientation of the navigation plane. The transformed precise absolute position is rotated by the same angle to provide the precise absolute position of the entity.

[0018] According to one embodiment of the present specification, the precise absolute orientation of an entity is derived based on 1) the relative orientation of the entity obtained from the relative position and orientation estimation unit and 2) the rough absolute orientation obtained from the rough absolute position and orientation estimation unit. In the transformed navigation plane, the relative position and orientation estimation unit provides the relative orientation of the entity with respect to a transformed path that is parallel to either the X-axis or the Y-axis based on the applied transformation. Since the transformed absolute orientation of the entity in the transformed navigation plane has the same absolute orientation as either the X-axis or the Y-axis for the transformed path, the relative orientation of the entity, along with its sign, is added to the absolute orientation of the transformed path to derive the transformed absolute orientation angle. By rotating the transformed navigation plane in the reverse direction by the same amount as the rotation angle, the transformed absolute orientation angle undergoes a similar rotation, providing an intermediate representation of the absolute orientation of the entity. The precise absolute orientation of the entity is obtained as a weighted combination of the rough absolute orientation and the intermediate representation of the absolute orientation of the entity.

[0019] According to one embodiment of the present specification, the analysis unit is configured to select and use one or more of the relative position and relative orientation from the relative position and orientation estimation unit among a plurality of inputs. Such a plurality of inputs to the analysis unit are derived by the relative position and orientation estimation unit using various sensor sets among a second set of sensors. The selection of the specific input to be used is guided by the unique attributes provided by the navigation guidance unit based on the rough absolute position.

[0020] According to one embodiment of the present specification, while navigating through different sections of a navigation layout including either a plurality of line segments or a single line segment having changing physical attributes, the analysis unit is configured to seamlessly select and use one or more of the relative positions and relative orientations from the relative position and orientation estimation unit from among a plurality of inputs, and the selection is guided by a navigation guidance unit based on the rough absolute position of the entity, and the navigation guidance unit provides physical attributes associated with each such line segment, such as, for example, but not limited to, walls adjacent to the navigation path and their sides, the presence of lane markings, etc.

[0021] According to one embodiment of the present specification, the first plurality of positions on the entity includes the front end portion and the rear end portion of the entity, and the second plurality of positions includes at least one of the left side portion of the entity, the right side portion of the entity, the front end portion of the entity, and the rear end portion of the entity.

[0022] According to an embodiment of the present specification, a method for navigating an entity along a predetermined path in a navigation space is disclosed. The method includes: 1) starting the navigation of the entity along a predetermined path in the navigation space; 2) determining at least one of the rough absolute position and the rough orientation of the entity based on position data captured at a predefined frequency / interval by a first set of sensors from among a plurality of sensors disposed at a first plurality of positions on the entity; 3) determining at least one of the relative position and the relative orientation of the entity with respect to the predetermined path based on a dataset captured from a second diverse set of sensors from among a plurality of sensors disposed at a second plurality of positions on the entity; 4) selecting at least one of the relative position and the relative orientation of the entity with respect to the predetermined path from among a plurality of relative positions and relative orientations based on the rough absolute position and the navigation map, wherein the navigation map is generated and updated based on map data and a machine learning model based on historical navigation data; 5) determining the precise absolute position and the precise absolute orientation of the entity by fine-tuning the rough absolute position based on the relative position and the rough absolute orientation based on the relative orientation using the navigation map; and 6) continuing steps 2-5 until the destination is reached.

[0023] These and other aspects of the embodiments of the present specification will be better recognized and understood when considered in conjunction with the following description and the accompanying drawings. However, it should be understood that the following description, while showing preferred embodiments and numerous specific details thereof, is given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments of the present specification without departing from its spirit, and the embodiments of the present specification include all such modifications.

Brief Description of the Drawings

[0024] Embodiments of the present invention will be better understood from the following detailed description with reference to the drawings.

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 3C

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

[0025] However, specific features of the embodiments of the present specification are shown in some drawings and not in others. This is done for convenience only, as each feature may be combined with any or all of the other features according to the embodiments of the present specification.

DETAILED DESCRIPTION OF THE INVENTION

[0026] In the following detailed description, reference is made to the accompanying drawings which form a part hereof, and in which are shown by way of illustration specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the embodiments, and it is to be understood that other changes may be made without departing from the scope of the embodiments. Accordingly, the following detailed description is not to be taken in a limiting sense.

[0027] Embodiments of the present specification and their various features and advantageous details are more fully described with reference to the non-limiting embodiments shown in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as not to unnecessarily obscure the embodiments of the present specification. The examples used herein are merely intended to facilitate the understanding of the manner in which the embodiments of the invention may be practiced and to further enable those skilled in the art to practice the embodiments of the invention. Accordingly, the examples are not to be construed as limiting the scope of the embodiments of the present specification.

[0028] The various embodiments of the present specification provide a system and method for determining the precise absolute position and precise absolute orientation of entities in a navigation space in a cost-effective manner with good accuracy while eliminating dependencies on any dynamically changing scenarios or unplanned changes in the navigation space. Without reference to historical data, the quality of the absolute position and orientation remains the same and does not degrade over any time interval due to dependencies on licensees of old data.

[0029] According to one embodiment of the present specification, a system for determining the precise absolute position and precise absolute orientation of an entity in a navigation space is disclosed. According to one embodiment of the present invention, a plurality of sensors including a first set of sensors arranged at a first plurality of positions on the entity are included, and the first set of sensors is part of a rectangular coordinate system provided by a local positioning system formed using technologies such as, but not limited to, UWB, Bluetooth, Zig-bee, ultrasonic, and others. According to another embodiment of the present invention, a second set of sensors is arranged at a second plurality of positions on the entity. The system is also configured to determine at least one of the rough absolute position and rough absolute orientation of the entity based on the position data captured in the two-dimensional orthogonal plane of the rectangular coordinate system at a predetermined frequency / interval by the first set of sensors, and includes a rough absolute position and orientation estimation unit. Further, the system is configured to determine at least one of the plurality of relative positions and relative orientations of the entity with respect to a predetermined path based on the data set captured at a predetermined frequency / interval from the second diverse set of sensors, and includes a relative position and orientation estimation unit. Further, the system is configured to provide unique attributes based on a desired navigable layout identified in an indoor navigation space, and to dynamically update one or more attributes of a navigation map as learning / feedback based on historical navigation data, and includes a navigation guidance unit. Further, the system is configured to determine at least one of the precise absolute position and precise absolute orientation of the entity at a predetermined frequency / interval by fine-tuning the rough absolute position and rough absolute orientation based on 1) one or more of the plurality of inputs provided by the relative position and orientation estimation unit (108), 2) the rough absolute position of the entity, and 3) the unique attributes provided by the navigation guidance unit, and includes an analysis unit.

[0030] According to one embodiment of the present specification, the analysis unit aligns a predetermined path so as to be parallel to the X-axis or the Y-axis in a two-dimensional orthogonal plane, and rotates the navigation plane associated with the predetermined path by a rotation angle in order to generate a transformed navigation plane, thereby transforming the predetermined path. The rough absolute position is also rotated through the same rotation angle to obtain the transformed rough absolute position of the entity. By correcting / calibrating the transformed rough absolute position of the entity, based on one or more of a plurality of inputs from the relative position and orientation estimation unit, the transformed precise absolute position of the entity is obtained. The transformed rough absolute position of the entity is corrected / calibrated by replacing either the X value or the Y value of the transformed rough absolute position coordinates of the entity with a combination of the transformed ideal coordinate value of the object and one or more of a plurality of inputs from the relative position and orientation estimation unit, depending on the rotation applied during the transformation of the plane. The transformed ideal coordinate value of the object is equal to the transformed ideal starting point coordinate value selected based on the applied transformation, and the ideal starting point coordinates are the coordinates of the starting node of the line segment obtained from the navigation map. The precise absolute position of the entity is obtained by rotating the navigation plane back to its original orientation in the reverse direction through the same rotation angle. The transformed precise absolute position is rotated by the same angle to provide the precise absolute position of the entity.

[0031] According to one embodiment of the present specification, the precise absolute orientation of an entity is derived based on 1) the relative orientation of the entity obtained from a relative position and orientation estimation unit and 2) the rough absolute orientation obtained from a rough absolute position and orientation estimation unit. In the transformed navigation plane, the relative position and orientation estimation unit provides the relative orientation of the entity with respect to a transformed path that is parallel to either the X-axis or the Y-axis based on the applied transformation. Since the absolute orientation of the transformed path is the same as one of the X-axis or the Y-axis, the transformed absolute orientation of the entity in the transformed navigation plane is derived by adding the relative orientation of the entity, along with its sign, to the absolute orientation of the transformed path. By rotating the transformed navigation plane in the reverse direction by the same amount as the rotation angle, the transformed absolute orientation angle undergoes a similar rotation, providing an intermediate representation of the absolute orientation of the entity. The precise absolute orientation of the entity is obtained as a weighted combination of the rough absolute orientation and the intermediate representation of the absolute orientation of the entity.

[0032] According to one embodiment of the present specification, the analysis unit is configured to select and use one or more of the relative position and relative orientation from the relative position and orientation estimation unit from among a plurality of inputs. Such a plurality of inputs to the analysis unit are derived by the relative position and orientation estimation unit using various sensor sets among a second set of sensors. The selection of the specific input to be used is guided by the navigation map based on the rough absolute position.

[0033] According to one embodiment of the present specification, while navigating through different sections of a navigation layout including either a plurality of line segments or a single line segment having changing physical attributes, the analysis unit is configured to seamlessly select and use one or more of the relative position and relative orientation from the relative position and orientation estimation unit from among a plurality of inputs, and the selection is guided by a navigation map based on a rough absolute position of the entity, and the navigation map provides physical attributes associated with each such line segment, such as, for example, but not limited to, walls adjacent to the navigation path and their sides, the presence of lane markings, etc.

[0034] According to one embodiment of the present specification, the first plurality of positions on the entity includes a front end portion and a rear end portion of the entity, and the second plurality of positions includes at least one of a left side portion of the entity, a right side portion of the entity, a front end portion of the entity, and a rear end portion of the entity.

[0035] According to one embodiment of the present specification, a method for navigating an entity along a predetermined path in a navigation space is disclosed. The method includes: 1) starting the navigation of the entity along a predetermined path in the navigation space; 2) determining at least one of a rough absolute position and a rough orientation of the entity based on position data captured at a predefined frequency / interval by a first set of sensors from among a plurality of sensors disposed at a first plurality of positions on the entity; 3) determining at least one of a relative position and a relative orientation of the entity with respect to the predetermined path based on a dataset captured from a second diverse set of sensors from among a plurality of sensors disposed at a second plurality of positions on the entity; 4) selecting at least one of a relative position and a relative orientation of the entity with respect to the predetermined path from among a plurality of relative positions and relative orientations based on the rough absolute position and a navigation map; 5) determining a precise absolute position and a precise absolute orientation of the entity by fine-tuning a rough absolute position based on the relative position and a rough absolute orientation based on the relative orientation using the navigation map, wherein the navigation map is generated based on map data and a machine learning model based on historical navigation data; and 6) continuing steps 2-5 until the destination is reached.

[0036] The various embodiments disclosed herein provide methods and systems for determining the precise absolute position and orientation of entities in a navigation space. The systems and methods disclosed herein use various sensors that are used to seamlessly assist in improving the accuracy of absolute position, including on-the-fly switchovers, to determine the precise absolute position and precise absolute orientation of an entity in a navigation space based on the extraction of various features in the navigation space. Further, the systems and methods disclosed herein use a rough absolute position and a unique combination of relative positions extracted from various sensors using specific features in the navigation space to achieve an accurate absolute position. The entity can include a stationary object or a moving object.

[0037] FIG. 1 shows a block diagram of a system for determining the position and orientation of an entity in a navigation space according to an embodiment of the present specification. As depicted in FIG. 1, system 102 includes a plurality of sensors 104, a rough absolute position and orientation estimation unit 106, a relative position and orientation estimation unit 108, a navigation guidance unit 110, and an analysis unit 112. For example, the entity may include a stationary object or a moving object (such as mobile factory equipment or a vehicle, etc.). The navigation space includes, for example, an enclosed space or an open space having a predefined boundary, such as the space inside a factory unit. According to an embodiment of the present specification, the plurality of sensors includes a first set of sensors disposed at a first plurality of positions on the entity and a second set of sensors disposed at a second plurality of positions on the entity. For example, the second plurality of sensors may include, but are not limited to, proximity sensing devices, image capture devices, and the like.

[0038] According to one embodiment of the present specification, the rough absolute position and orientation estimation unit 106 is configured to determine at least one of the rough absolute position and the rough absolute orientation of an entity based on position data captured at a predetermined frequency / interval by a first sensor set (further described with FIGS. 2A-2B). The predetermined path includes an ideal navigation path of an entity within the navigation space. According to one embodiment of the present specification, the relative position and orientation estimation unit 108 is configured to determine at least one of the relative position and the relative orientation of an entity with respect to a predetermined path based on a set of data captured at a predetermined frequency / interval from a second diverse sensor set (further described with FIGS. 3A-3C).

[0039] According to one embodiment of the present specification, the navigation guidance unit 110 is configured to provide unique attributes based on a desired navigable layout identified in an indoor navigation space and to dynamically update one or more attributes as learning / feedback based on historical navigation data. According to one embodiment of the present specification, the navigation guidance unit 110 includes a centralized / local system or device that includes unique pre-defined attributes for each line segment of a virtual map created for a navigation space (e.g., a factory floor). The unique pre-defined attributes include, but are not limited to, nodes, destinations, absolute coordinates of nodes and other attributes, valid paths connecting each node to any other node, optimal paths between nodes, associated costs and intermediate transition angles, reinforcement for each line segment such as the ideal path of the segment, the presence / availability of walls on either side of a passage having sub-section accuracy to capture possible gaps when there are no walls, the presence of lane lines on either side of a line segment, lane width, maximum speed of movement based on lane width and any other considerations, azimuth angle offsets at each node, etc.

[0040] According to one embodiment of the present specification, the navigation guidance unit 110 generates an initial map using an initial input data set such as, for example, node coordinates, valid routes, route widths, etc. The initial input data set is processed in a proprietary way to reach a robust map and, for the most part, has all the attributes necessary to perform successful navigation from its very first execution without the need for special training for the entity 200. This is with respect to the subsequent refinement / dynamic update of attributes such as the azimuth angle offset of the nodes, the presence of walls or fixed structures along the route, the reliability of the lane markings on the floor for a given segment, etc. The navigation guidance unit 110 collects / gathers various data from the entity during navigation and applies machine learning (ML) techniques for further inference. According to one embodiment of the present invention, the dynamic map generation unit 110 uses ML-based inferred data collected based on the experiences of various entities, and further applies artificial intelligence techniques to improve the attributes and update the initial map. Subsequently, the updated map is made available for all entities in the navigation space from just the next navigation.

[0041] According to one embodiment of the present specification, the analysis unit 112 fine-tunes the rough absolute position and the rough absolute orientation based on 1) one or more of a plurality of inputs provided by the relative position and orientation estimation unit (108), 2) the rough absolute position of the entity, and 3) the unique attributes provided by the navigation guidance unit (110), so as to determine at least one of the precise absolute position and the precise absolute orientation of the entity at a predetermined frequency / interval. According to one embodiment of the present specification, the analysis unit 112 is configured to rotate the navigation plane 402 associated with the predetermined path by a rotation angle so that the predetermined path 304 is aligned parallel to one of the X-axis or the Y-axis of the two-dimensional orthogonal plane and generate a transformed navigation plane 404. The rough absolute position similarly undergoes the same rotation and becomes the transformed rough absolute position of the entity. According to one embodiment of the present specification, the analysis unit 112 is configured to apply refinement to the transformed absolute position based on one or more of a plurality of inputs from the relative position and orientation estimation unit and obtain the transformed precise absolute position of the entity on the transformed navigation. The refinement is a single substitution of either the X value or the Y value of the transformed rough absolute position coordinates of the entity with a combination of the transformed ideal coordinate value of the object and one or more of a plurality of deviations from the predetermined path selected from among a plurality of inputs from the relative position and orientation estimation unit, depending on the rotation applied during the transformation of the plane. The transformed ideal coordinate value of the object is the same as one of the transformed ideal starting point coordinate values selected based on the applied transformation, and the ideal starting point is the theoretical coordinates of the starting node of the line segment obtained from the navigation map. According to one embodiment of the present specification, the analysis unit 112 is configured to obtain the precise absolute position of the entity by rotating the navigation plane in the reverse direction by the same amount as the rotation angle to return to the original orientation of the navigation plane 402. The transformed precise absolute position rotates by the same angle to provide the precise absolute position of the entity (further described in conjunction with FIGS. 4A-4B).

[0042] According to one embodiment of the present specification, the analysis unit 112 derives the precise absolute orientation of the entity based on 1) the relative orientation of the entity obtained from the relative position and orientation estimation unit 108 and 2) the rough absolute orientation obtained from the rough absolute position and orientation estimation unit 106. In the transformed navigation plane, the relative position and orientation estimation unit 108 provides the relative orientation of the entity with respect to a transformed path that is parallel to either the X-axis or the Y-axis based on the applied transformation. Since the absolute orientation of the transformed path is the same as one of the X-axis or the Y-axis, the transformed absolute orientation of the entity in the transformed navigation plane is derived by adding the relative orientation of the entity, along with its sign, to the absolute orientation of the transformed path. By rotating the transformed navigation plane 404 in the reverse direction by the same amount as the rotation angle, the transformed absolute orientation angle undergoes a similar rotation, providing an intermediate representation of the absolute orientation of the entity. The precise absolute orientation of the entity is obtained as a weighted combination of the rough absolute orientation and the intermediate representation of the absolute orientation of the entity (further described in conjunction with FIGS. 3C, 4A - 4B, and 8). According to an embodiment of the present invention, the analysis unit 112 is configured to select and use one or more of the relative position and relative orientation from the relative position and orientation estimation unit 108 from among a plurality of inputs. Such a plurality of inputs to the analysis unit 112 are derived by the relative position and orientation estimation unit 108 using diverse sensor sets among a second set of sensors. The selection of the specific input to be used is guided by the navigation map based on the rough absolute position.According to one embodiment of the present specification, while navigating different sections of a navigation layout including either a plurality of line segments or a single line segment having changing physical attributes, the analysis unit 112 is configured to seamlessly select and use one or more of relative position and relative orientation from among a plurality of inputs, and the selection is guided by a navigation map based on the rough absolute position of the entity, and the navigation map provides physical attributes associated with each such line segment, such as, for example, but not limited to, walls adjacent to the navigation path and their sides, the presence of lane markings, etc. (further described with FIG. 6).

[0043] Figures 2A-2B illustratively show the positioning of a first set of sensors at a first plurality of positions on an exemplary entity according to one embodiment of the present specification. As depicted in FIG. 2A, the exemplary entity 200 includes a front end portion 206 and a rear end portion 204. The first set of sensors 202A-H includes a rear sensor set 202E-H disposed at the rear end portion 204 and a front sensor set 202A-D disposed at the front end portion 206 of the exemplary entity 200. FIG. 2B depicts a representation of the positioning of the first set of sensors 202A-H on the exemplary entity 200 in the X-Y plane 208. As depicted in FIG. 2B, points B1-B4 and points F1-F4 represent the positioning of sensors 202E-H and 202A-D, respectively. The first set of sensors 202A-H is positioned to achieve three-dimensional spatial diversity. The first set of sensors 202A-H captures the absolute position of the exemplary entity, and the absolute position provided by each sensor is used to calculate a redundant set of absolute orientation representations, and the average of the absolute orientation representations is used to determine the absolute orientation of the entity in the XY plane 208.

[0044] According to one embodiment of the present specification, the position of an entity (such as the exemplary entity 200) captured by the first plurality of sensors (such as the first plurality of sensors 202A-H) is used to determine at least one of a rough absolute position and / or a rough absolute orientation. According to one embodiment of the present specification, as depicted in FIG. 2B, the rough absolute position and orientation estimation unit 106 determines the lines B1F1 212 and B4F4 214. The lines B1F1 212 and B4F4 214 from the rear to the front provide an indication of the angle at which the entity is oriented with respect to a given instance on a predetermined path. The rough absolute position and orientation estimation unit 106 determines the angles of the lines B1B4 216 and F1F4 218. The lines B1B4 216 and F1F4 218 provide an angle that is 90 degrees greater than the angle of the entity. The absolute position unit 106 combines the angles to obtain Quad_Sensor_Angle. Quad_Sensor_Angle is given by Equation 1. [Equation 1] Quad_Sensor_Angle = ((∠B1F1 + ∠B4F4 + (∠B1B4 - 90) + (∠F1F4 - 90)) / 4 2 (1)

[0045] According to one embodiment of the present specification, the rough absolute position and orientation estimation unit 106 uses the points B1B2B3B4 to determine a first center point (BC). BC is given by Equation 2. [Equation 2] BC= (B1+B2+B3+B4) / 4 (2)

[0046] According to one embodiment of the present specification, the rough absolute position and orientation estimation unit 106 uses the points B1B2B3B4 to determine a second center point (FC). FC is given by Equation 3. [Equation 3] FC = (F1+F2+F3+F4) / 4 (3)

[0047] The rough absolute position and orientation estimation unit 106 determines the angle (Centre_Of_Sensors_Angle) representing the line BCFC given by Equation 4. [Equation 4] Centre_Of_Sensors_Angle = ∠BCFC (4)

[0048] According to an embodiment of the present specification, the rough absolute position and orientation estimation unit 106 determines the angle representing the line B1F4 and the angle representing the line B4F1. Although the lines B1F4 and B4F1 have an offset with respect to the orientation of the entity, since the first sensor set 202A-H is located in a rectangle, the offset becomes invalid. For example, as depicted in FIG. 2B, the actual orientation of the entity is 270 degrees. Assuming that B1F4 is at an angle of 300 degrees, B4F1 can be 240 degrees. Therefore, the sum of the angle of B1F4 and the angle of B4F1 gives an expression of the instantaneous orientation (Big_Diagonal_Angle) of the entity given by Equation 5. [Equation 5] Big_Diagonal_Angle = (∠B1F4 + ∠B4F1) / 2 (5)

[0049] According to an embodiment of the present specification, the rough absolute position and orientation estimation unit 106 determines and uses the points BC and FC specified at Centre_Of_Sensors_Angle. The rough absolute position and orientation estimation unit 106 determines the angles representing BCF1 and BCF4 and the average of the angles to obtain the angle SD_Angle_1. The rough absolute position and orientation estimation unit 106 determines the angles representing B1FC and B4FC and the average of the angles to obtain the angle SD_Angle_2. The rough absolute position and orientation estimation unit 106 determines Small_Diagonal_Angle by averaging SD_Angle_1 and SD_Angle_2 given by Equation 6. [Equation 6] Small_Diagonal_Angle = ((∠BCF1 + ∠BCF4) / 2 + (∠B1FC + ∠B4FC) / 2) / 2 (6)

[0050] According to one embodiment of the present specification, the rough absolute position and orientation estimation unit 106 determines the rough absolute orientation of the entity given by Equation 7. [Equation 7] Rough absolute orientation = (K1*Quad_Sensor_Angle + K2*Centre_Of_Sensors_Angle + K3*Big_Diagonal_Angle + K4*Small_Diagonal_Angle) / (K1+K2+K3+K4) (7) Here, K1, K2, K3, and K4 are multiplication constants generated based on the reliability of each angle representation.

[0051] Figures 3A-3B illustratively show the positioning of a second set of sensors at a second plurality of positions on an exemplary entity according to one embodiment of the present specification. As depicted in Figure 3A, the second set of sensors 302A-C are positioned along the left surface 304 of the exemplary entity 200. The second set of sensors 302A-C may also be positioned along the right surface of the exemplary entity 200 (not shown). The second set of sensors 302A-C provides measurements of the distance (d) of the entity from a fixed structure located on the side of the sidewall or path.

[0052] As further described with reference to Figure 3B, the relative position and orientation estimation unit 108 determines the deviation from a predetermined path (ideal navigation path) based on the distance (d). Figure 3B shows a process for determining the deviation of an entity from a predetermined path during navigation in a navigation space according to one embodiment. As depicted in Figure 3B, the width of the entity 200 is represented by "b" 306, and the distance of the entity 200 from the left wall 310 is represented by "d" 308. The relative position and orientation estimation unit 108 determines the deviation (Δw) 312 given by Equation 8. [Equation 8] Δw = w / 2 - (d + b / 2) (8) Here, w / 2 represents the distance between the left wall 310 and the predetermined path 304, and the distance between the predetermined path and the assembly line 1 314 or the assembly line 2 316 in the navigation space.

[0053] According to an embodiment of the present specification, the relative position and orientation estimation unit 108 determines the relative position of the entity 200 in a marked passage such as a lane as depicted in FIG. 3C, and based on one sensor (for example, an image capture device) from among a second set of sensors disposed at the front portion, rear portion, and / or central portion of the entity 200, determines the relative position and / or relative orientation of the entity 200. As shown in FIG. 3A, sensors 306A and 306B disposed at the front side portion 206 and the rear side portion 204 respectively represent one such embodiment.

[0054] FIG. 3C illustratively shows determining the relative position and relative orientation of the entity 200 according to an embodiment of the present specification. More specifically, FIG. 3C depicts a front perspective view of the entity 200 having a sensor (image capture device) 320 located at the front side portion of the entity 200. The entity navigates along a predetermined path 304. The sensor 320 captures the relative distance of the entity 200 with respect to a pair of lane lines 322 and 324. The relative position and orientation estimation unit 108 determines the deviation Δw of the entity 200 from the predetermined path (or ideal path) 304 based on the distance from the center of the entity (where the sensor or image capture device is disposed). The deviation Δw of the entity 200 is determined based on Equation 8. Also, the difference in the angles of the lane lines sensed by the sensor 320 enables the relative position and orientation estimation unit 108 to determine the relative orientation of the entity with respect to the lane lines.

[0055] According to one embodiment of the present specification, the relative position and orientation estimation unit 108 determines the relative position and relative orientation of the entity 200 using a system that provides depth information of a predetermined path 304. Using the depth information, the relative position and orientation estimation unit 108 depicts a virtual lane, and then, as described with FIGS. 3B-3C, the deviation from the predetermined path 304 is identified.

[0056] FIGS. 4A-4B depict the transformation of the navigation plane 402 that always aligns a predetermined path with the Y-axis, as shown in the transformed navigation plane 404 according to one embodiment of the present specification, and the rough absolute position is transformed so as to be the transformed rough absolute position of the entity. A floor alignment similar to that in FIG. 3B requires a simple step of increasing the deviation of the entity 200 from the predetermined path by improving only the Y value among the XY coordinates determined based on the transformed rough absolute position. Regarding a general solution to eliminate the constraints of the factory floor alignment with the XY axes, the analysis unit 112 transforms the predetermined path (line segment) by plane rotation so as to always align with one of the axes, such as the Y-axis. As depicted in FIG. 4A, if (x, y) is the absolute coordinate set of the entity 200 provided by the rough absolute position and orientation estimation unit 106, the analysis unit 112 rotates the initial plane 402 by θ (the angle between the direction of the entity and the Y-axis) to obtain a transformed plane 404 parallel to the Y-axis, and the transformed coordinates of the entity 200 in the transformed plane 404 are (x t ,y t ), where x t is given by equation 9. [Equation 9] JPEG0007693808000001.jpg12153

[0057] Since the deviation from the predetermined (ideal) path in the transformed plane 404 is a single refinement to only x t , the analysis unit 112 applies the refinement based on the instantaneous relative position of the entity 200 received from the relative position and orientation estimation unit 108, and the coordinates (x’t , y t ), to obtain. The starting coordinates in the predetermined path are (x i , y i ) are given, and the converted x i value x i t is given by the number 10. [Number 10] JPEG0007693808000002.jpg7153

[0058] After conversion, the predetermined (ideal) path becomes parallel to the Y-axis, and all values of the predetermined path can have the same value x i t . The analysis unit 112 applies refinement to x t based on the instantaneous relative position of the entity 200 received from the relative position and orientation estimation unit 108, and obtains x' t given by the number 11. [Number 11] x' t = x i t - Δw(11) If the wall is on the right side of the navigation direction of the entity 200, x' t is given by the number 12. [Number 12] x' t = x i t + Δw(12) If the wall is on the left side of the navigation direction of the entity 200, Δw is the deviation of the entity with respect to the predetermined path 304 derived by the number 8 (further described using FIG. 3B), x i t is the converted "x" value of the starting coordinates in the ideal path, w is the width of the path, d is the relative distance reported from the side of the entity 200 to the wall by a plurality of sensors, and b is the width of the entity 200.

[0059] According to an embodiment of the present specification, as depicted in FIG. 4B, the analysis unit 112 is (x' t , y t) To obtain , after rotation and translation, the plane is rotated back to its original orientation in the navigation plane 402. The analysis unit 112 obtains the precise absolute position (x’, y’) of the entity 200 in the navigation plane 402 given by the number 13.

[0060] [Number 13] JPEG0007693808000003.jpg10153

[0061] The precise absolute coordinates (x’, y’) provide the exact absolute position of the entity 200 with respect to the predetermined path 304, for example, with a maximum error of 10 cm.

[0062] According to one embodiment of the present specification, the analysis unit 112 derives the absolute orientation of the entity using the relative orientation of the entity provided by the relative position and orientation estimation unit 108. Since the transformed path in 404 is parallel to the Y-axis, the orientation of the transformed path is 90 degrees. The relative orientation of the entity is used to improve the absolute orientation of the transformed path shown in 404, and then, by rotating the plane back to the original orientation of the navigation plane 402, the absolute orientation of the entity in the navigation plane 402 is obtained. The weighted combination of this absolute orientation and the rough absolute orientation provided by the rough absolute position and orientation estimation unit (106) provides the final precise absolute orientation of the entity derived by the analysis unit (112). The weighting is determined based on the accuracy provided by specific relative inputs from the relative position and orientation estimation unit 108 and the rough absolute position and orientation estimation unit (106).

[0063] FIG. 5 is a flowchart showing a process for finding the precise absolute position and precise absolute orientation of an entity at a predetermined frequency / interval and facilitating the navigation of entity 200 along a predetermined path in a navigation space using the system 102 of FIG. 1 according to an embodiment of the present specification. In step 502, the navigation of the entity is initiated along a predetermined path in the navigation space. In step 504, at least one of the rough absolute position and rough absolute orientation of the entity is determined based on position data captured by a first set of sensors from among a plurality of sensors disposed at a first plurality of positions on the entity. In step 506, at least one of the plurality of relative positions and relative orientations of the entity is determined with respect to the predetermined path based on a data set captured from a second diverse set of sensors from among a plurality of sensors disposed at a second plurality of positions on the entity. In step 508, at least one of the relative position and relative orientation of the entity with respect to the predetermined path is selected from among the plurality of relative positions and relative orientations based on the rough absolute position and the navigation map. In step 510, the precise absolute position and precise absolute orientation of the entity are determined by fine-tuning the rough absolute position based on the relative position and the rough absolute orientation based on the relative orientation using the navigation map, and the navigation map is generated based on map data and a machine learning model based on historical navigation data. In step 512, it is verified whether the destination has been reached. If the destination has been reached, in step 514, the navigation is stopped. If the destination has not been reached, steps 504 to 512 are repeated.

[0064] FIG. 6 represents a typical navigation scenario according to an embodiment of the present specification. When an entity traverses from point A to point D, the entity moves across various sections of the navigation space. During the navigation process, for each section, the relative position of the entity is obtained based on the context and attributes provided by each section of the layout and by the navigation map. For example, when the entity navigates through section AB, the relative position is obtained with respect to the adjacent wall (602) on the left. Between point B and point C, the lane markings (604) provide an indication of the relative position of the entity with respect to the lane lines. Further, to navigate through section CD, the adjacent wall (606) on the right is used to find the relative position of the entity. Based on the context of a given navigation section, seamless switchover between sensors during navigation is supported by the navigation map.

[0065] FIG. 7 shows the improvement provided by the present invention with precise representation of the absolute position and orientation of an entity, enhancing the ability of the entity to navigate surely and reach the target successfully. For a given navigation, comparison of the trajectories between the precise absolute position (704) and the coarse absolute position (702) clearly shows the consistency of the trajectories provided by the present invention.

[0066] FIG. 8 shows an embodiment of finding the relative orientation of an entity using a proximity sensing device forming part of a second diverse sensor set according to an embodiment of the present specification. According to an embodiment further described with FIGS. 4A-4B, the navigation plane 402 is rotated to align a predetermined path parallel to the Y-axis. In this transformed plane 404, using the distance measurements provided by the proximity sensors 802a-c, the slope of the straight line connecting 802a-c can be obtained in the transformed plane 404. By rotating the entity back to the navigation plane 402, the slope of the straight line undergoes a similar rotation. This modified slope of the line gives a measure of an intermediate representation of the absolute orientation of the entity in the navigation plane 402, and the precise absolute orientation of the entity (200) is obtained as a weighted combination of the coarse absolute orientation and the intermediate representation of the absolute orientation of the entity.

[0067] Various embodiments of a system and process for navigating an entity along a predetermined path in a navigation space disclosed herein use a combination of an absolute positioning system, one such embodiment of a wireless technology (a local positioning system), and embodiments of relative sensor data to facilitate an instantaneous and accurate representation of an absolute position. The technology does not require reference to either short-term or long-term history data to determine position and does not require a training phase to generate any templates for future comparison. Further, in the technology, data from multiple sensors are captured simultaneously without reference to history data to reach an instantaneous absolute position representation, so the quality of the absolute position remains the same and does not degrade over any time interval due to dependence on a licensee of old data, and the absolute position also does not depend on fixed references on the floor. Thus, the vulnerability associated with dynamic changes in the position of fixed references is completely avoided. Planned changes such as the introduction of new navigation paths, the demolition of existing walls, and the construction of new walls can be updated anyway to the inherent floor map maintained with respect to position. Further, the technology eliminates dependence on any dynamically changing scenario on the floor, such as changes to the navigation path, modifying the layout to break a wall, etc., unless there are planned changes, and provides a cost-effective system and process that provides good accuracy.

[0068] Further, the technology enables determination of a precise absolute position and a precise absolute orientation of an entity in a navigation space by using a coarse absolute position and a unique combination of relative positions extracted from various sensors using specific features in the navigation space. The technology also enables seamless switching between sensors during navigation based on a context supported by an inherent navigation map that provides better accuracy compared to existing technologies. The technology uses the precise absolute position and the precise absolute orientation to reliably enable navigation of the entity, thus minimizing deviation from the ideal path and accurately reaching the target.

[0069] The foregoing description of specific embodiments can sufficiently clarify the general nature of the embodiments herein, so that others, by applying current knowledge, can easily modify and / or adapt various uses such as specific embodiments without departing from the upper concept. Therefore, such adaptations and modifications should be understood and intended to be within the meaning and equivalent scope of the disclosed embodiments. It should be understood that the language or terms adopted herein are for the purpose of description and not for the purpose of limitation. Therefore, the embodiments herein are described from the perspective of preferred embodiments, and those skilled in the art will recognize that the embodiments herein can be implemented with modifications within the spirit and scope of the appended claims.

[0070] Although the embodiments herein are described in various specific embodiments, it will be apparent to those skilled in the art that the embodiments herein can be implemented with modifications.

Claims

1. A system (102) for determining the instantaneous absolute position and absolute orientation of an entity in a navigation space, comprising: A plurality of sensors (104) including a first set of sensors arranged at a first plurality of positions on the entity (200), which are within a Cartesian coordinate system provided by a local positioning system formed using wireless technology, and a second set of sensors is arranged at a second plurality of positions on the entity (200), the plurality of sensors (104); A rough absolute position and orientation estimation unit (106) configured to determine at least one of the rough absolute position and rough absolute orientation of the entity (200) based on position data captured in a two-dimensional orthogonal plane of the Cartesian coordinate system at a predetermined frequency / interval by the first set of sensors (304); A relative position and orientation estimation unit (108) configured to determine at least one of the relative position and relative orientation of the entity (200) with respect to a navigation path (304) of the entity predetermined in the navigation space based on a data set captured at a predetermined frequency / interval from the second set of sensors, wherein the entity is rectangular when viewed from above and moves parallel to a straight line portion of one of the predetermined physical features in the navigation space, has a side parallel to the straight line portion, the navigation path is parallel to the straight line portion, the relative position represents a relative deviation Δw = w / 2 - (d + b / 2) of the entity with respect to the navigation path, where w / 2 represents the distance between one of the predetermined physical features and the navigation path, b represents the width in a direction orthogonal to the moving direction of the entity, and d represents the distance of the entity from one of the predetermined physical features, the relative position and orientation estimation unit (108); Based on a desired navigable layout identified in the navigation space, generating a navigation map that provides unique attributes, and dynamically updating one or more of the attributes of the navigation map based on historical navigation data. The navigation guidance unit (110) is configured to perform the above operations. The navigation guidance unit (110) is disposed inside or outside the entity (200). The navigation guidance unit (110) and 1) One or more of the relative position and relative orientation provided by the relative position and orientation estimation unit (108), 2) The approximate absolute position of the entity, and 3) Based on the unique attributes provided by the navigation guidance unit (110), by finely adjusting the approximate absolute position and the approximate absolute orientation, at a predetermined frequency / interval, at least one of the precise absolute position and the precise absolute orientation of the entity (200) is determined. An analysis unit (112) configured to perform the above operations Including The entity (200) includes a stationary object or a moving object. System (102).

2. The analysis unit (112) Align the navigation path (304) parallel to one of the X-axis or Y-axis of the two-dimensional orthogonal plane, and rotate the navigation plane associated with the navigation path (304) by a rotation angle to generate a transformed navigation plane (404). By transforming the navigation path (304), the approximate absolute position undergoes the same rotation and becomes the transformed approximate absolute position of the entity. The above transformation To obtain the transformed precise absolute position of the entity (200) on the transformed navigation plane (404), based on one or more of the relative position and the relative orientation from the relative position and orientation estimation unit, applying refinement to the transformed rough absolute position, wherein the refinement depends on the rotation applied during the transformation of the plane, and is a single substitution of either the X value or the Y value of the transformed rough absolute position coordinates of the entity (200) for a combination of the transformed ideal coordinate value of the object and one or more of the relative position and the relative orientation with respect to the navigation path obtained from one or more of the relative position and the relative orientation from the relative position and orientation estimation unit (108), the transformed ideal coordinate value of the object is equal to one of the transformed ideal starting point coordinate values selected based on the applied transformation, the transformed ideal coordinate value of the object is equal to the X coordinate value of the transformed navigation path aligned parallel to the Y axis of the orthogonal plane, or equal to the Y coordinate value of the transformed navigation path aligned parallel to the X axis of the orthogonal plane, the ideal starting point is the coordinate value of the starting node of the line segment obtained from the navigation map, the applying, Obtaining the precise absolute position of the entity (200) by rotating the transformed navigation plane (404) in the reverse direction by the same amount equal to the rotation angle to return to the original orientation of the navigation plane (402), wherein the transformed precise absolute position is rotated by the same angle to provide the precise absolute position of the entity (200), the obtaining The system (102) according to claim 1, configured to perform.

3. The analysis unit (112) is, 1) Based on the relative orientation of the entity obtained from the relative position and orientation estimation unit (108), and 2) the rough absolute orientation obtained from the rough absolute position and orientation estimation unit (104), it is configured to derive the precise absolute orientation of the entity. Together with the sign of the positive or negative of the relative orientation, the relative orientation of the entity with respect to the navigation path (304) provided by the relative position and orientation estimation unit (108) is added to the orientation of the navigation path in the transformed navigation plane (404), and the transformed absolute orientation of the entity in the transformed navigation plane (404) is obtained. The orientation of the navigation path in the transformed navigation plane (404) is the same as either the X-axis or the Y-axis based on the applied transformation. By rotating the transformed navigation plane (404) in the reverse direction by the same amount as the rotation angle to the original orientation of the navigation plane 402, the transformed absolute orientation angle undergoes a similar rotation to provide an intermediate representation of the absolute orientation of the entity (200). The precise absolute orientation of the entity (200) is obtained as a weighted combination of the rough absolute orientation and the intermediate representation of the absolute orientation of the entity, according to the system (102) of claim 2.

4. The analysis unit (112) is configured to select and use one or more of the relative position and the relative orientation from the relative position and orientation estimation unit, and one or more of the relative position and the relative orientation to the analysis unit are derived and used by the relative position and orientation estimation unit using the second sensor set. The selection of one or more of the relative position and the relative orientation used is guided by the navigation map based on the rough absolute position of the entity (200), and is configured to perform the selection and use. The system (102) according to claim 1.

5. While navigating through a plurality of mutually different sections of a navigation layout including either a plurality of line segments having mutually different physical attributes or a single line segment, the analysis unit (112) selects the relative position and the relative orientation from among one or more of the relative position and the relative orientation from the relative position and orientation estimation unit, the selection being guided by the navigation map based on the rough absolute position of the entity (200), the navigation map providing the physical attribute associated with each such line segment, the physical attribute being the presence of a wall adjacent to the navigation path or a lane marking, the system (102) according to claim 1, configured to perform the selection.

6. The first plurality of positions on the entity (200) includes a front end portion and a rear end portion of the entity (200), and the second plurality of positions is selected from a group including a left side portion of the entity (200), a right side portion of the entity (200), a front end portion of the entity (200), and a rear end portion of the entity (200), the system (102) according to claim 1.

7. The second sensor set includes a proximity sensing device and an image capture device. When using the second sensor set, the relative position and orientation estimation unit (108) provides the analysis unit (112) with the relative position and relative orientation of the entity (200) with respect to the navigation path (304), which are derived based on a data set captured from the second sensor set at a predetermined frequency / interval. The entity is rectangular when viewed from above, moves parallel to a straight portion of a fixed structure in the navigation space, has sides parallel to the straight portion, the navigation path is parallel to the straight portion, the relative position represents a relative deviation Δw = w / 2 - (d + b / 2) of the entity with respect to the navigation path, where w / 2 represents the distance between the straight portion of the fixed structure and the navigation path, b represents the width in a direction orthogonal to the moving direction of the entity, d represents the distance of the entity from the straight portion of the fixed structure, and the relative position and orientation estimation unit (108) derives a plurality of such relative positions and relative orientations based on the data set captured from the second sensor set. The system (102) according to claim 1.

Images