Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps
This paper develops a decentralized approach to gas distribution mapping (GDM) and information-driven path planning for large-scale distributed sensing systems. Gas mapping is performed using a probabilistic representation known as a Hilbert map, which formulates the mapping problem as a multi-class...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2020
|
| Online Access: | https://hdl.handle.net/1721.1/125301 |
| _version_ | 1826215343467528192 |
|---|---|
| author | Zhu, Pingping Ferrari, Silvia Morelli, Julian Linares, Richard Doerr, Bryce |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Zhu, Pingping Ferrari, Silvia Morelli, Julian Linares, Richard Doerr, Bryce |
| author_sort | Zhu, Pingping |
| collection | MIT |
| description | This paper develops a decentralized approach to gas distribution mapping (GDM) and information-driven path planning for large-scale distributed sensing systems. Gas mapping is performed using a probabilistic representation known as a Hilbert map, which formulates the mapping problem as a multi-class classification task and uses kernel logistic regression to train a discriminative classifier online. A novel Hilbert map information fusion method is presented for rapidly merging the information from individual robot maps using limited data communication. A communication strategy that implements data fusion among many robots is also presented for the decentralized computation of GDMs. New entropy-based information-driven path-planning methods are developed and compared to existing approaches, such as particle swarm optimization (PSO) and random walks (RW). Numerical experiments conducted in simulated indoor and outdoor environments show that the information-driven approaches proposed in this paper far outperform other approaches, and avoid mutual collisions in real time. |
| first_indexed | 2024-09-23T16:24:41Z |
| format | Article |
| id | mit-1721.1/125301 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T16:24:41Z |
| publishDate | 2020 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | mit-1721.1/1253012024-06-24T18:55:04Z Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps Zhu, Pingping Ferrari, Silvia Morelli, Julian Linares, Richard Doerr, Bryce Massachusetts Institute of Technology. Department of Aeronautics and Astronautics This paper develops a decentralized approach to gas distribution mapping (GDM) and information-driven path planning for large-scale distributed sensing systems. Gas mapping is performed using a probabilistic representation known as a Hilbert map, which formulates the mapping problem as a multi-class classification task and uses kernel logistic regression to train a discriminative classifier online. A novel Hilbert map information fusion method is presented for rapidly merging the information from individual robot maps using limited data communication. A communication strategy that implements data fusion among many robots is also presented for the decentralized computation of GDMs. New entropy-based information-driven path-planning methods are developed and compared to existing approaches, such as particle swarm optimization (PSO) and random walks (RW). Numerical experiments conducted in simulated indoor and outdoor environments show that the information-driven approaches proposed in this paper far outperform other approaches, and avoid mutual collisions in real time. 2020-05-18T21:01:08Z 2020-05-18T21:01:08Z 2019-03-28 2019-03-29T19:40:27Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/125301 Sensors 19 (7): 1524 (2019) http://dx.doi.org/10.3390/s19071524 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Multidisciplinary Digital Publishing Institute Multidisciplinary Digital Publishing Institute |
| spellingShingle | Zhu, Pingping Ferrari, Silvia Morelli, Julian Linares, Richard Doerr, Bryce Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps |
| title | Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps |
| title_full | Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps |
| title_fullStr | Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps |
| title_full_unstemmed | Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps |
| title_short | Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps |
| title_sort | scalable gas sensing mapping and path planning via decentralized hilbert maps |
| url | https://hdl.handle.net/1721.1/125301 |
| work_keys_str_mv | AT zhupingping scalablegassensingmappingandpathplanningviadecentralizedhilbertmaps AT ferrarisilvia scalablegassensingmappingandpathplanningviadecentralizedhilbertmaps AT morellijulian scalablegassensingmappingandpathplanningviadecentralizedhilbertmaps AT linaresrichard scalablegassensingmappingandpathplanningviadecentralizedhilbertmaps AT doerrbryce scalablegassensingmappingandpathplanningviadecentralizedhilbertmaps |