<i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics
This paper proposes <i>LTC-Mapping</i>, a method for building object-oriented semantic maps that remain consistent in the long-term operation of mobile robots. Among the different challenges that compromise this aim, <i>LTC-Mapping</i> focuses on two of the more relevant ones...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5308 |
| _version_ | 1797415928785272832 |
|---|---|
| author | Jose-Luis Matez-Bandera David Fernandez-Chaves Jose-Raul Ruiz-Sarmiento Javier Monroy Nicolai Petkov Javier Gonzalez-Jimenez |
| author_facet | Jose-Luis Matez-Bandera David Fernandez-Chaves Jose-Raul Ruiz-Sarmiento Javier Monroy Nicolai Petkov Javier Gonzalez-Jimenez |
| author_sort | Jose-Luis Matez-Bandera |
| collection | DOAJ |
| description | This paper proposes <i>LTC-Mapping</i>, a method for building object-oriented semantic maps that remain consistent in the long-term operation of mobile robots. Among the different challenges that compromise this aim, <i>LTC-Mapping</i> focuses on two of the more relevant ones: preventing duplicate instances of objects (instance duplication) and handling dynamic scenes. The former refers to creating multiple instances of the same physical object in the map, usually as a consequence of partial views or occlusions. The latter deals with the typical assumption made by object-oriented mapping methods that the world is static, resulting in outdated representations when the objects change their positions. To face these issues, we model the detected objects with 3D bounding boxes, and analyze the visibility of their vertices to detect occlusions and partial views. Besides this geometric modeling, the boxes are augmented with semantic information regarding the categories of the objects they represent. Both the geometric entities (bounding boxes) and their semantic content are propagated over time through data association and a fusion technique. In addition, in order to keep the map curated, the non-detection of objects in the areas where they should appear is also considered, proposing a mechanism that removes them from the map once there is evidence that they have been moved (i.e., multiple non-detections occur). To validate our proposal, a number of experiments have been carried out using the Robot@VirtualHome ecosystem, comparing its performance with a state-of-the-art alternative. The results report a superior performance of <i>LTC-Mapping</i> when modeling both geometric and semantic information of objects, and also support its online execution. |
| first_indexed | 2024-03-09T05:56:31Z |
| format | Article |
| id | doaj.art-aa05fe3378d64dfeb9a8b4809b7fc21e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:56:31Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-aa05fe3378d64dfeb9a8b4809b7fc21e2023-12-03T12:13:05ZengMDPI AGSensors1424-82202022-07-012214530810.3390/s22145308<i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in RoboticsJose-Luis Matez-Bandera0David Fernandez-Chaves1Jose-Raul Ruiz-Sarmiento2Javier Monroy3Nicolai Petkov4Javier Gonzalez-Jimenez5Machine Perception and Intelligent Robotics Group (MAPIR-UMA), Malaga Institute for Mechatronics Engineering and Cyber-Physical Systems (IMECH.UMA), University of Malaga, 29016 Malaga, SpainMachine Perception and Intelligent Robotics Group (MAPIR-UMA), Malaga Institute for Mechatronics Engineering and Cyber-Physical Systems (IMECH.UMA), University of Malaga, 29016 Malaga, SpainMachine Perception and Intelligent Robotics Group (MAPIR-UMA), Malaga Institute for Mechatronics Engineering and Cyber-Physical Systems (IMECH.UMA), University of Malaga, 29016 Malaga, SpainMachine Perception and Intelligent Robotics Group (MAPIR-UMA), Malaga Institute for Mechatronics Engineering and Cyber-Physical Systems (IMECH.UMA), University of Malaga, 29016 Malaga, SpainJohann Bernoulli Institute of Mathematics and Computing Science, University of Groningen, 9712 CP Groningen, The NetherlandsMachine Perception and Intelligent Robotics Group (MAPIR-UMA), Malaga Institute for Mechatronics Engineering and Cyber-Physical Systems (IMECH.UMA), University of Malaga, 29016 Malaga, SpainThis paper proposes <i>LTC-Mapping</i>, a method for building object-oriented semantic maps that remain consistent in the long-term operation of mobile robots. Among the different challenges that compromise this aim, <i>LTC-Mapping</i> focuses on two of the more relevant ones: preventing duplicate instances of objects (instance duplication) and handling dynamic scenes. The former refers to creating multiple instances of the same physical object in the map, usually as a consequence of partial views or occlusions. The latter deals with the typical assumption made by object-oriented mapping methods that the world is static, resulting in outdated representations when the objects change their positions. To face these issues, we model the detected objects with 3D bounding boxes, and analyze the visibility of their vertices to detect occlusions and partial views. Besides this geometric modeling, the boxes are augmented with semantic information regarding the categories of the objects they represent. Both the geometric entities (bounding boxes) and their semantic content are propagated over time through data association and a fusion technique. In addition, in order to keep the map curated, the non-detection of objects in the areas where they should appear is also considered, proposing a mechanism that removes them from the map once there is evidence that they have been moved (i.e., multiple non-detections occur). To validate our proposal, a number of experiments have been carried out using the Robot@VirtualHome ecosystem, comparing its performance with a state-of-the-art alternative. The results report a superior performance of <i>LTC-Mapping</i> when modeling both geometric and semantic information of objects, and also support its online execution.https://www.mdpi.com/1424-8220/22/14/5308semantic mapsobject-oriented mapslong-term consistencyinstance duplicationdynamic scenesmobile robots |
| spellingShingle | Jose-Luis Matez-Bandera David Fernandez-Chaves Jose-Raul Ruiz-Sarmiento Javier Monroy Nicolai Petkov Javier Gonzalez-Jimenez <i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics Sensors semantic maps object-oriented maps long-term consistency instance duplication dynamic scenes mobile robots |
| title | <i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics |
| title_full | <i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics |
| title_fullStr | <i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics |
| title_full_unstemmed | <i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics |
| title_short | <i>LTC-Mapping</i>, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics |
| title_sort | i ltc mapping i enhancing long term consistency of object oriented semantic maps in robotics |
| topic | semantic maps object-oriented maps long-term consistency instance duplication dynamic scenes mobile robots |
| url | https://www.mdpi.com/1424-8220/22/14/5308 |
| work_keys_str_mv | AT joseluismatezbandera iltcmappingienhancinglongtermconsistencyofobjectorientedsemanticmapsinrobotics AT davidfernandezchaves iltcmappingienhancinglongtermconsistencyofobjectorientedsemanticmapsinrobotics AT joseraulruizsarmiento iltcmappingienhancinglongtermconsistencyofobjectorientedsemanticmapsinrobotics AT javiermonroy iltcmappingienhancinglongtermconsistencyofobjectorientedsemanticmapsinrobotics AT nicolaipetkov iltcmappingienhancinglongtermconsistencyofobjectorientedsemanticmapsinrobotics AT javiergonzalezjimenez iltcmappingienhancinglongtermconsistencyofobjectorientedsemanticmapsinrobotics |