Deep reinforcement learning for time-critical wilderness search and rescue using drones
Traditional search and rescue methods in wilderness areas can be time-consuming and have limited coverage. Drones offer a faster and more flexible solution, but optimizing their search paths is crucial for effective operations. This paper proposes a novel algorithm using deep reinforcement learning...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2024.1527095/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832544893146234880 |
|---|---|
| author | Jan-Hendrik Ewers David Anderson Douglas Thomson |
| author_facet | Jan-Hendrik Ewers David Anderson Douglas Thomson |
| author_sort | Jan-Hendrik Ewers |
| collection | DOAJ |
| description | Traditional search and rescue methods in wilderness areas can be time-consuming and have limited coverage. Drones offer a faster and more flexible solution, but optimizing their search paths is crucial for effective operations. This paper proposes a novel algorithm using deep reinforcement learning to create efficient search paths for drones in wilderness environments. Our approach leverages a priori data about the search area and the missing person in the form of a probability distribution map. This allows the policy to learn optimal flight paths that maximize the probability of finding the missing person quickly. Experimental results show that our method achieves a significant improvement in search times compared to traditional coverage planning and search planning algorithms by over 160%, a difference that can mean life or death in real-world search operations Additionally, unlike previous work, our approach incorporates a continuous action space enabled by cubature, allowing for more nuanced flight patterns. |
| format | Article |
| id | doaj-art-6f081fba3cd847e89448bcaa30b05697 |
| institution | Kabale University |
| issn | 2296-9144 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj-art-6f081fba3cd847e89448bcaa30b056972025-02-03T09:03:01ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442025-02-011110.3389/frobt.2024.15270951527095Deep reinforcement learning for time-critical wilderness search and rescue using dronesJan-Hendrik EwersDavid AndersonDouglas ThomsonTraditional search and rescue methods in wilderness areas can be time-consuming and have limited coverage. Drones offer a faster and more flexible solution, but optimizing their search paths is crucial for effective operations. This paper proposes a novel algorithm using deep reinforcement learning to create efficient search paths for drones in wilderness environments. Our approach leverages a priori data about the search area and the missing person in the form of a probability distribution map. This allows the policy to learn optimal flight paths that maximize the probability of finding the missing person quickly. Experimental results show that our method achieves a significant improvement in search times compared to traditional coverage planning and search planning algorithms by over 160%, a difference that can mean life or death in real-world search operations Additionally, unlike previous work, our approach incorporates a continuous action space enabled by cubature, allowing for more nuanced flight patterns.https://www.frontiersin.org/articles/10.3389/frobt.2024.1527095/fullreinforcement learningsearch planningmission planningautonomous systemswilderness search and rescueunmanned aerial vehicle |
| spellingShingle | Jan-Hendrik Ewers David Anderson Douglas Thomson Deep reinforcement learning for time-critical wilderness search and rescue using drones Frontiers in Robotics and AI reinforcement learning search planning mission planning autonomous systems wilderness search and rescue unmanned aerial vehicle |
| title | Deep reinforcement learning for time-critical wilderness search and rescue using drones |
| title_full | Deep reinforcement learning for time-critical wilderness search and rescue using drones |
| title_fullStr | Deep reinforcement learning for time-critical wilderness search and rescue using drones |
| title_full_unstemmed | Deep reinforcement learning for time-critical wilderness search and rescue using drones |
| title_short | Deep reinforcement learning for time-critical wilderness search and rescue using drones |
| title_sort | deep reinforcement learning for time critical wilderness search and rescue using drones |
| topic | reinforcement learning search planning mission planning autonomous systems wilderness search and rescue unmanned aerial vehicle |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2024.1527095/full |
| work_keys_str_mv | AT janhendrikewers deepreinforcementlearningfortimecriticalwildernesssearchandrescueusingdrones AT davidanderson deepreinforcementlearningfortimecriticalwildernesssearchandrescueusingdrones AT douglasthomson deepreinforcementlearningfortimecriticalwildernesssearchandrescueusingdrones |