Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments
© 2019 IEEE. Autonomous navigation through unknown environments is a challenging task that entails real-time localization, perception, planning, and control. UAVs with this capability have begun to emerge in the literature with advances in lightweight sensing and computing. Although the planning met...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
IEEE
2021
|
Online Access: | https://hdl.handle.net/1721.1/137805 |
_version_ | 1811080704046399488 |
---|---|
author | Tordesillas, Jesus Lopez, Brett T. Carter, John Ware, John How, Jonathan P. |
author2 | Massachusetts Institute of Technology. Aerospace Controls Laboratory |
author_facet | Massachusetts Institute of Technology. Aerospace Controls Laboratory Tordesillas, Jesus Lopez, Brett T. Carter, John Ware, John How, Jonathan P. |
author_sort | Tordesillas, Jesus |
collection | MIT |
description | © 2019 IEEE. Autonomous navigation through unknown environments is a challenging task that entails real-time localization, perception, planning, and control. UAVs with this capability have begun to emerge in the literature with advances in lightweight sensing and computing. Although the planning methodologies vary from platform to platform, many algorithms adopt a hierarchical planning architecture where a slow, low-fidelity global planner guides a fast, high-fidelity local planner. However, in unknown environments, this approach can lead to erratic or unstable behavior due to the interaction between the global planner, whose solution is changing constantly, and the local planner; a consequence of not capturing higher-order dynamics in the global plan. This work proposes a planning framework in which multi-fidelity models are used to reduce the discrepancy between the local and global planner. Our approach uses high-, medium-, and low-fidelity models to compose a path that captures higher-order dynamics while remaining computationally tractable. In addition, we address the interaction between a fast planner and a slower mapper by considering the sensor data not yet fused into the map during the collision check. This novel mapping and planning framework for agile flights is validated in simulation and hardware experiments, showing replanning times of 5-40 ms in cluttered environments. |
first_indexed | 2024-09-23T11:35:27Z |
format | Article |
id | mit-1721.1/137805 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T11:35:27Z |
publishDate | 2021 |
publisher | IEEE |
record_format | dspace |
spelling | mit-1721.1/1378052023-02-08T19:23:52Z Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments Tordesillas, Jesus Lopez, Brett T. Carter, John Ware, John How, Jonathan P. Massachusetts Institute of Technology. Aerospace Controls Laboratory Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © 2019 IEEE. Autonomous navigation through unknown environments is a challenging task that entails real-time localization, perception, planning, and control. UAVs with this capability have begun to emerge in the literature with advances in lightweight sensing and computing. Although the planning methodologies vary from platform to platform, many algorithms adopt a hierarchical planning architecture where a slow, low-fidelity global planner guides a fast, high-fidelity local planner. However, in unknown environments, this approach can lead to erratic or unstable behavior due to the interaction between the global planner, whose solution is changing constantly, and the local planner; a consequence of not capturing higher-order dynamics in the global plan. This work proposes a planning framework in which multi-fidelity models are used to reduce the discrepancy between the local and global planner. Our approach uses high-, medium-, and low-fidelity models to compose a path that captures higher-order dynamics while remaining computationally tractable. In addition, we address the interaction between a fast planner and a slower mapper by considering the sensor data not yet fused into the map during the collision check. This novel mapping and planning framework for agile flights is validated in simulation and hardware experiments, showing replanning times of 5-40 ms in cluttered environments. 2021-11-08T19:53:25Z 2021-11-08T19:53:25Z 2019-05 2019-10-28T17:38:46Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137805 Tordesillas, Jesus, Lopez, Brett T., Carter, John, Ware, John and How, Jonathan P. 2019. "Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments." en 10.1109/icra.2019.8794248 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IEEE arXiv |
spellingShingle | Tordesillas, Jesus Lopez, Brett T. Carter, John Ware, John How, Jonathan P. Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments |
title | Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments |
title_full | Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments |
title_fullStr | Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments |
title_full_unstemmed | Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments |
title_short | Real-Time Planning with Multi-Fidelity Models for Agile Flights in Unknown Environments |
title_sort | real time planning with multi fidelity models for agile flights in unknown environments |
url | https://hdl.handle.net/1721.1/137805 |
work_keys_str_mv | AT tordesillasjesus realtimeplanningwithmultifidelitymodelsforagileflightsinunknownenvironments AT lopezbrettt realtimeplanningwithmultifidelitymodelsforagileflightsinunknownenvironments AT carterjohn realtimeplanningwithmultifidelitymodelsforagileflightsinunknownenvironments AT warejohn realtimeplanningwithmultifidelitymodelsforagileflightsinunknownenvironments AT howjonathanp realtimeplanningwithmultifidelitymodelsforagileflightsinunknownenvironments |