Method and system for simultaneous semantic mapping and investigation of a built environment

{
  "publication_number": "US2024394426A1",
  "country": "US",
  "kind": "A1",
  "title": "Method and system for simultaneous semantic mapping and investigation of a built environment",
  "abstract": "A method and a system for simultaneous semantic mapping and investigation of a built environment are provided herein. The method may include: obtaining distance readings from a moving agent to a built environment; applying the distance readings to a semantic classifier thereby classifying a set of the distance readings into respective semantic built elements selected from a predefined list of two or more types of built elements; repeating the classifying of the distance readings until a connected set of built elements is generated, defining a built volume; detecting at least one opening in the built volume leading to a further built volume; repeating said obtaining, said applying and said classifying, until a connected set of built elements is generated, defining the further built volume; and generating a vectorial map semantically representing the built elements in each of the built volume and the further built volume, and the opening therebetween.",
  "claims": [
    "1. A method of simultaneous semantic mapping and investigation of a built environment, the method comprising: obtaining distance readings from a moving agent to a built environment; applying the distance readings to a semantic classifier to classify a set of the distance readings into respective semantic built elements selected from a closed list of two or more predefined types of built elements; repeating the classifying of the distance readings until a connected set of built elements is generated, defining a built volume; detecting at least one opening in the built volume leading to a further built volume; repeating said obtaining, said applying and said classifying, until a connected set of built elements is generated, defining the further built volume; and generating a vectorial semantical representation of the built elements in each of the built volume and the further built volume, and the opening between the built volume and the further built volume, wherein the vectorial semantical representation is in a form of a directed graph where the built volumes are represented as vertices and wherein the passages between the built volumes are represented as edge. 2. The method according to claim 1, wherein the built volume comprises a room and wherein the built elements comprise at least one of: a wall, a passage, and an object which is neither a wall nor a passage. 3. The method according to claim 1, wherein the built volume comprises a street and wherein the built elements comprise at least one of: a building line, a crossroad, and an object which is neither a building line nor a crossroad. 4. The method according to claim 1, wherein the built elements are semantically represented as plane for the wall or the building line and a directed arrow for the passage or the crossroad. 5. The method according to claim 1, further comprising repeating the method, for further built volumes until the built environment is investigated in its entirety. 6. The method according to claim 1, wherein the distance readings are achieved by receiving reflections of a radiation source from the built environment. 7. The method according to claim 1, wherein the moving agent is a drone or a robot. 8. A mobile agent capable of simultaneous semantic mapping and investigation of a built environment, the mobile agent comprising: at least one sensor configured to obtain distance readings from the moving agent to a built environment; a computer processor; and computer memory comprising a set of instructions that when executed cause the computer processor to: apply the distance readings to a semantic classifier, to classify a set of the distance readings into respective semantic built elements selected from a closed list of two or more predefined types of built elements; repeat the classifying of the distance readings until a connected set of built elements is generated, defining a built volume; detect at least one opening in the built volume leading to a further built volume; repeat said obtaining, said applying and said classifying, until a connected set of built elements is generated, defining the further built volume; and generate a vectorial semantical representation of the built elements in each of the built volume and the further built volume, and the opening between the built volume and the further built volume, wherein the vectorial semantical representation is in a form of a directed graph where the built volumes are represented as vertices and wherein the passages between the built volumes are represented as edge. 9. The mobile agent according to claim 8, wherein the built volume comprises a room and wherein the built elements comprise at least one of: a wall, a passage, and an object which is neither a wall nor a passage. 10. The mobile agent according to claim 8, wherein the built volume comprises a street and wherein the built elements comprise at least one of: a building line, a crossroad, and an object which is neither a building line nor a crossroad. 11. The mobile agent according to claim 9, wherein the built elements are semantically represented as plane for the wall or the building line and a directed arrow for the passage or the crossroad. 12. The mobile agent according to claim 8, wherein the computer processor is further configured to repeat the obtaining, the classifying, and the detecting. for further built volumes until the built environment is investigated in its entirety. 13. The mobile agent according to claim 8, wherein the distance readings are achieved by receiving reflections of a radiation source from the built environment. 14. The mobile agent according to claim 8, wherein the moving agent is a drone or a robot. 15. A non-transitory computer-readable medium for simultaneous semantic mapping and investigation of a built environment, by a mobile agent, the computer-readable medium comprising a set of instructions that when executed cause at least one computer processor to: obtain distance readings from the moving agent to a built environment: apply the distance readings to a semantic classifier, to classify a set of the distance readings into respective semantic built elements selected from a closed list of two or more predefined types of built elements; repeat the classifying of the distance readings until a connected set of built elements is generated, defining a built volume; detect at least one opening in the built volume leading to a further built volume; repeat said obtaining, said applying and said classifying, until a connected set of built elements is generated, defining the further built volume; and generate a vectorial semantical representation of the built elements in each of the built volume and the further built volume, and the opening between the built volume and the further built volume, wherein the vectorial semantical representation is in a form of a directed graph where the built volumes are represented as vertices and wherein the passages between the built volumes are represented as edge. 16. The non-transitory computer-readable medium according to claim 15, wherein the built volume comprises a room and wherein the built elements comprise at least one of: a wall, a passage, and an object which is neither a wall nor a passage. 17. The non-transitory computer-readable medium according to claim 15, wherein the built volume comprises a street and wherein the built elements comprise at least one of: a building line, a crossroad, and an object which is neither a building line nor a crossroad. 18. The non-transitory computer-readable medium according to claim 17, wherein the built elements are semantically represented as plane for the wall or the building line and a directed arrow for the passage or the crossroad."
  ],
  "description_excerpt": "The present invention relates generally to the field of mapping and investigating an environment, and more particularly to simultancous semantic mapping and investigation of a built environment.\n\nMapping and investigating an unknown environment are ongoing challenges in the navigation domain and becomes even more applicable for the use of autonomous agents such as drones and other platforms. Most autonomous agents relay on their perception to make precise and intelligent decisions. Specifically, in exploration, the agent is expected to understand and explore it's surrounding by moving around and expending the surrounding's map. The generated map represents the agent's memory and understanding of its environment. Over the past two decades, occupancy-grid-based maps (OGM) have been used for autonomous avigation and exploration. An OGM represents the probability for obstacle to be in each area of two-dimensional grid. Since OGM suffer from oversimplification, alternative method of study called semantic simultaneous localization and mapping (SLAM) has been introduced. Semantic SLAM main idea is to use labeled data in the form of semantic information, to enrich OGM. Both OGM and semantic SLAM (which rely on OGM) suffer from various disadvantages. For large spaces, OGM requires the tradeoff between computer resources and map resolution and thus suffer from lack of scalability. The localization precision of OGM is bounded by the OGM cell resolution. Sending large OGMs can cause traffic jams in large networks and therefore affects cooperative mapping for multiple autonomous agents.",
  "cpc": [
    "G06F 30/13",
    "B25J 9/1664",
    "G01C 21/20",
    "G01C 21/3826",
    "G01C 21/383",
    "G01C 21/3837",
    "G01C 21/3848",
    "G05D 1/0274",
    "G06V 20/10"
  ],
  "ipc": [
    "G06F 30/13"
  ],
  "assignees": [
    "ELBIT SYSTEMS C4I & CYBER LTD"
  ],
  "inventors": [
    "TZLIL OR",
    "FEINER TAL",
    "KAHN YAIR",
    "NATIV AMIT"
  ],
  "filing_date": "2024-07-31",
  "publication_date": "2024-11-28",
  "priority_date": "2022-03-07",
  "application_number": "US-202418789930-A",
  "family_id": "87936247"
}