Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning
This paper describes and demonstrates an autonomous robotic team that can rapidly learn the characteristics of environments that it has never seen before. The flexible paradigm is easily scalable to multi-robot, multi-sensor autonomous teams, and it is relevant to satellite calibration/validation an...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/6/2240 |
| _version_ | 1797540334310260736 |
|---|---|
| author | David J. Lary David Schaefer John Waczak Adam Aker Aaron Barbosa Lakitha O. H. Wijeratne Shawhin Talebi Bharana Fernando John Sadler Tatiana Lary Matthew D. Lary |
| author_facet | David J. Lary David Schaefer John Waczak Adam Aker Aaron Barbosa Lakitha O. H. Wijeratne Shawhin Talebi Bharana Fernando John Sadler Tatiana Lary Matthew D. Lary |
| author_sort | David J. Lary |
| collection | DOAJ |
| description | This paper describes and demonstrates an autonomous robotic team that can rapidly learn the characteristics of environments that it has never seen before. The flexible paradigm is easily scalable to multi-robot, multi-sensor autonomous teams, and it is relevant to satellite calibration/validation and the creation of new remote sensing data products. A case study is described for the rapid characterisation of the aquatic environment, over a period of just a few minutes we acquired thousands of training data points. This training data allowed for our machine learning algorithms to rapidly learn by example and provide wide area maps of the composition of the environment. Along side these larger autonomous robots two smaller robots that can be deployed by a single individual were also deployed (a walking robot and a robotic hover-board), observing significant small scale spatial variability. |
| first_indexed | 2024-03-10T12:58:38Z |
| format | Article |
| id | doaj.art-058e16eaf51c4a19882447a74d0e59e6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T12:58:38Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-058e16eaf51c4a19882447a74d0e59e62023-11-21T11:38:34ZengMDPI AGSensors1424-82202021-03-01216224010.3390/s21062240Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine LearningDavid J. Lary0David Schaefer1John Waczak2Adam Aker3Aaron Barbosa4Lakitha O. H. Wijeratne5Shawhin Talebi6Bharana Fernando7John Sadler8Tatiana Lary9Matthew D. Lary10Hanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAHanson Center for Space Sciences, University of Texas at Dallas, Richardson, TX 75080, USAThis paper describes and demonstrates an autonomous robotic team that can rapidly learn the characteristics of environments that it has never seen before. The flexible paradigm is easily scalable to multi-robot, multi-sensor autonomous teams, and it is relevant to satellite calibration/validation and the creation of new remote sensing data products. A case study is described for the rapid characterisation of the aquatic environment, over a period of just a few minutes we acquired thousands of training data points. This training data allowed for our machine learning algorithms to rapidly learn by example and provide wide area maps of the composition of the environment. Along side these larger autonomous robots two smaller robots that can be deployed by a single individual were also deployed (a walking robot and a robotic hover-board), observing significant small scale spatial variability.https://www.mdpi.com/1424-8220/21/6/2240machine learninghyper-spectral imagingrobot teamautonomousUAVrobotic boat |
| spellingShingle | David J. Lary David Schaefer John Waczak Adam Aker Aaron Barbosa Lakitha O. H. Wijeratne Shawhin Talebi Bharana Fernando John Sadler Tatiana Lary Matthew D. Lary Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning Sensors machine learning hyper-spectral imaging robot team autonomous UAV robotic boat |
| title | Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning |
| title_full | Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning |
| title_fullStr | Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning |
| title_full_unstemmed | Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning |
| title_short | Autonomous Learning of New Environments with a Robotic Team Employing Hyper-Spectral Remote Sensing, Comprehensive In-Situ Sensing and Machine Learning |
| title_sort | autonomous learning of new environments with a robotic team employing hyper spectral remote sensing comprehensive in situ sensing and machine learning |
| topic | machine learning hyper-spectral imaging robot team autonomous UAV robotic boat |
| url | https://www.mdpi.com/1424-8220/21/6/2240 |
| work_keys_str_mv | AT davidjlary autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT davidschaefer autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT johnwaczak autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT adamaker autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT aaronbarbosa autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT lakithaohwijeratne autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT shawhintalebi autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT bharanafernando autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT johnsadler autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT tatianalary autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning AT matthewdlary autonomouslearningofnewenvironmentswitharoboticteamemployinghyperspectralremotesensingcomprehensiveinsitusensingandmachinelearning |