Drones in wildfire management

An MQ-9 Reaper remotely piloted aircraft assigned to the 163d Attack Wing soars over Southern California skies on a training flight to March Air Reserve Base, California, in this Sept. 15, 2016, file photo. The wing is flying MQ-9s in support of civil authorities battling deadly wildfires in Northern California. (Air National Guard Photo by Tech. Sgt. Neil Ballecer)

This infrared video is from above the North Umpqua Fire by Marcus Tobey, BLM. That southwest Oregon blaze burned about 43,000 acres.

Drones, also known as Unmanned Aerial Systems/Vehicles (UAS/UAV), or  Remotely Piloted Aircraft, are used in wildfire surveillance and suppression. They help in the detection, containment, and extinguishing of fires. They are also used for locating a hot spot, firebreak breaches, and then to deliver water to the affected site. In terms of maneuverability, these are superior to a helicopter or other forms of manned aircraft. They help firefighters determine where a fire will spread through tracking and mapping fire patterns. These empower scientists and incident personnel to make informed decisions. These devices can fly when and where manned aircraft are unable to fly. They are associated with low cost and are flexible devices that offer a high spatiotemporal resolution.

The data gathered through these devices is unique and accurate as they fly low, slow, and for a long period. They can also collect high-resolution imagery and sub-centimeter data in smoke and at night. It provides firefighters access to real-time data without putting the lives of pilots at risk. Managing a 24/7-drone fleet over any huge forestland is challenging. Public drones pose a danger to wildfire and can cost lives. Fire response agencies are forced to ground their aircraft to avoid the potential for a midair collision. Policies in the United States, Canada, and Australia discourage the use of public drones near wildfires.

Description

Thermal-infrared imaging sensors on NASA's Ikhana unmanned research aircraft recorded this image of the Grass Valley/Slide Fire near Lake Arrowhead/Running Springs in the San Bernardino Mountains of Southern California just before noon Oct. 25. The 3-D processed image is a colorized mosaic of images draped over terrain, looking east. Active fire is seen in yellow, while hot, previously burned areas are in shades of dark red and purple. Unburned areas are shown in green hues.

Drones allow firefighters accurate data. By using the real-time data, firefighters can determine where a fire will move next, assisting them in making swift decisions and draw up a strategic plan about movement and evacuation.

Manufacturers equip these devices with infrared cameras that capture wind direction, high-resolution imagery of smoke, and other variables. The capability to operate at a low elevation allows firefighters to use UAVs to identify quick escape routes. These are used in approving flights to monitor massive wildfires in the US Pacific Northwest and in Australia.

The use of UAVs limits exposure and reduces risk to pilots and wildland firefighters. Easily packable and able to fly in remote locations. These can fly as fast as 40 miles an hour. The drone pilots can operate the devices at varying speeds to help people better see what is happening. The transmission from drones or UAVs can be viewed on a laptop computer in a mobile ground station. A drone weighing 15 pounds and a six-foot wingspan, has a range of about eight miles and can stay in the air for an hour without recharging. The aircraft can be programmed to fly on its own, but a safety pilot will monitor operations during the tests. These also serve as tools for starting planned, controlled fires to clear out hard-to-kill underbrush. Drones are a part of fire research and management.

Dragon egg systems

Drones have also been studied as tools for starting planned, controlled fires to clear out hard-to-kill underbrush. It is called the "Dragon Egg System." These are similar to ping-pong balls but are filled with potassium permanganate powder and injected with glycol and dropped to the target site. The balls ignite about 30 seconds after injection to start a controlled fire. A master's student from the University of Idaho was the first person to pilot an "unmanned aerial system plastic sphere dispenser" to deploy fire on a federally managed wildfire near Flagstaff, Arizona.

Integration

Drones are gradually becoming an integral part of the fight against wildfires in the United States, Canada, Australia, Europe, and Thailand.

United States

The United States is experiencing longer wildfire seasons. According to the U.S. Forest Service, the changing climate has led to longer wildfire season and increased expense in fighting fires. In 2018, the President passed an executive order on wildfire management that called for an increased use of drones.

NASA's remotely-piloted Ikhana aircraft, based at the agency's Armstrong Flight Research Center, is flown in preparation for its first mission in public airspace without a safety chase aircraft.

In the year 2008, NASA's Ikhana unmanned aerial vehicle (UAV) was used in the battle against more than 300 wildfires raging in California. Matrice 600 (M600) was used during the Woodbury Fire on June 8, 2019, about 5 miles northwest of Superior, Arizona.

A BQM-167A Subscale Aerial Target is ready to be launched from Tyndall Air Force Base Launch Facility for the 104th Fighter Wing, Massachusetts Air National Guard, on April 13, 2011. Deployed to Tyndall Air Force Base in Florida, the 104th is participating in the Weapons System Evaluation Program (WSEP).

In the year 2013, the National Guard used a drone for the first time in Yosemite National Park to find a crew that lost connection to the commander. The drones helped in finding the crew in five minutes.

Los Angeles Fire Department first used firefighting drones 2017. In the same year, the federal firefighters used UAVs on 340 wildfires in Oregon. The firefighters made use of drones in 12 states, according to the Department of Interior. Drones were used in 2016 fires in California. The drones are being used by Forest Service crews, Bureau of Land Management and the Oregon Department of Forestry.

Wildfire Management Technology Advancement Act

In March 2019, the Wildfire Management Technology Act was signed into law as Section 1114 by President Trump. The goal of the bill is to "develop consistent protocols and plans for the use of wildland fires of unmanned aircraft system technologies, including for the development of real-time maps of the location of wildland fires." The bill was introduced in 2015 after the Carlton Complex Fire.

Call When Needed contract

On May 15, 2018, the U.S. Department of the Interior had awarded a Call When Needed contract to four U.S. companies for small-unmanned aircraft systems services. It was an attempt to combat wildfires. It is a $17 million, one-of-its-kind on-call contract. It allows the agency to obtain fully contractor-operated and maintained small ready-to-be-deployed drones when needed to support wildland fire operations, search and rescue, emergency management in the Contiguous 48 States and Alaska. The companies included in the contract are Bridger Aerospace of Bozeman, Montana, Insitu of Bingen, Washington, Pathways2Solutions of Nashville, Tennessee, and Precision Integrated of Newberg, Oregon.

Canada

The Alberta government-contracted Elevated Robotic Services, which deploys drones for mining companies to assist firefighters in spotting the location of the blaze. In December 2017, researchers at the University of British Columbia used drones to survey the aftermath of the wildfires in British Columbia.

China

A computer engineering researcher at Guangdong College of Business and Technology in Zhaoqing, China, Dr. Songsheng Li is working on an autonomous early warning system for wildfires. It uses small drones that patrol forests, gather environmental data, and analyze the threat of fires. The key components of his system include GPS systems, unmanned aerial vehicles (UAVs), and Intelligent Flight Modes.

Netherlands

The Dutch fire brigade together with the Dutch drone manufacturer, Avy BV are testing a long-range drone to detect & monitor early-stage wildfires for a year since February 2021. The long-range drone is equipped with a stabilized gimbal, including an RGB and a thermal camera. AI is used to recognize the fires automatically.

Types

2016 model DJI Phantom 4 quadcopter with a gimbal stabilised 4K UHD camera, GPS stabilization and automatic obstacle avoidance

Members of the 163d Aircraft Maintenance Squadron,163d Attack Wing, California Air National Guard, conduct a preflight check on the wing's MQ-9 Reaper remotely piloted aircraft before a fire support mission, Aug. 1, 2018, at March Air Reserve Base, California. The wing is supporting state agencies who are battling numerous wildfires in Northern California, including the Carr Fire and Mendocino Complex Fire.

Drones come in various sizes and are equipped with a variety of specialized detectors and equipment. There are fire-starting drones that help in limiting the damage caused by wildfires. The hobbyist drones are those piloted by the public. The use of these drones over wildfires is prohibited by the authorities in the United States and Canada. These drones hinder the firefighting operations and prevent the agencies from using aerial techniques.

According to the National Wildfire Coordinating Group (NWCG), there are four classifications of UAS, based on their capabilities and functions, for wildland fire management purposes. This classification does include specialized aircraft and may not apply to other uses of UAS, such as in military combat. The classifications and their details are as follows:

Type	Configuration	Endurance	Data collection altitude (agl)	Max range (miles)	Typical sensors
1	Fixed-wing	6–14 hours	3,500-8,000	50	EO/Mid wave IR
	Rotorcraft	NA	NA	NA	High quality IR
2	Fixed-wing	1–6 hours	3,500-6,000	25	EO/Long wave IR
	Rotorcraft	NA	NA	NA	Moderate quality IR
3	Fixed-wing	20-60 min.	2,500 and below	5	EO/IR video and stills
	Rotorcraft	20-60 min.	2,000 and below	5	Moderate quality IR
4	Fixed-wing	Up to 30 min.	1,200 and below	<2	EO/IR video and stills
	Rotorcraft	Up to 20 min.	1,200 and below	<2	Moderate quality IR

Operational characteristics

Type 1 and 2

• Usually, operated by contractors to provide situational awareness (SA) and incident mapping;
• Generally, operate above all other incident aircraft;
• Assigned Victor (AM) or air-to-ground (FM) frequencies are used for communication with the UAS ground crew;
• Equipped with Mode C transponders;
• Includes Scan Eagle, Aerosonde, and Penguin among others.

Type 3 and 4

• Usually, operated by the agency (NWCG) to conduct tactical SA or map missions around the fireline;
• None are equipped with Automated Flight Following (AFF) equipment
• Assigned FM frequencies are used for communication with the UAS ground crew;
• Not equipped with transponders
• Includes 3DR Solo (RW) and FireFly6 (FW) among others.

Challenges

Drones assist in wildfire management. Different trees require a unique navigation strategy. Some drones take time to fly through densely covered grounds. Operating drones day and night in harsh weather requires an enormous effort.

A hobbyist drone over a fire puts firefighting risks at a halt and creates a high risk of accidents. Public drones disrupted wildfire operations in several locations. It also forces fire response agencies to ground their aircraft to avoid the potential for a midair collision. There have been more than 100 documented cases of unauthorized drones flying over wildfires. During the Bocco Fire, firefighters had to stop their efforts when an unauthorized civilian drone flew into their airspace. A drone has invaded the airspace above a Minnesota wildfire in each of the last four years since 2016. Interference of public drones create problems for firefighting aircraft, firefighters on the ground, and the public.

Policies

United States

For public

US Department of Agriculture poster warning about the risks of flying drones near wildfires

It is against the law to fly an unauthorized drone near a wildfire, and if caught, the drone could be confiscated by law enforcement, and hefty fines can be imposed in the U.S. Temporary Flight Restrictions (TFRs) are typically put in place during wildfires. It requires aircraft, manned or unmanned, that are not involved in wildfire suppression operations to obtain permission from fire managers to enter specified airspace. It's a federal crime to interfere with firefighting efforts on public lands, and it can lead to 12 months in prison. Congress has authorized the FAA to impose a civil penalty of up to $20,000 against any drone pilot who interferes with wildfire suppression, law enforcement, or emergency response operations. The FAA treats these violations seriously and will immediately consider swift enforcement action for these offenses.

Members of media

As per the law, the media is not allowed to fly drones near wildfires and never interfere with aviation operations or firefighting missions. Media personnel needs to have a special approval, and to qualify for the special approval process, the operations must directly support a response, relief, or recovery activity benefiting a critical public good. They should be a part of the existing Part 107 Remote Pilot and have the support of the on-scene commander on the ground before application submission. After receiving approval, the media personnel must work with the on-site authority, and never interfere with aviation operations or firefighting missions.

Australia

Australia's Civil Aviation Safety Authority (CASA) has issued a warning about the drone. The action was taken after viewing footage taken during the Blue Mountains fires in the year 2013. It was against the regulations laid down in CASA regulations.

Canada

Transport Canada and the British Columbia Wildfire Service banned the use of UAVs or drones near a wildfire.

References

39. The US military has been using drones for surveillance and reconnaissance purposes since the 1960s

Further reading

1. Thomas, Douglas S.; Butry, David T.; Gilbert, Stanley W.; Webb, David H.; Fung, Juan F. (November 2, 2017). The Costs and Losses of Wildfires. National Institute of Standards and Technology (Report). doi:10.6028/NIST.SP.1215.
2. Ladrach, William E. (June 2009). "The effects of fire in agriculture and forest ecosystems". ISTF NEWS. S2CID 51847011.
3. "Forest Service Wildland Fire Suppression Costs Exceed $2 Billion" (Press release). USDA. September 14, 2017.
4. Allison, Robert; Johnston, Joshua; Craig, Gregory; Jennings, Sion (18 August 2016). "Airborne Optical and Thermal Remote Sensing for Wildfire Detection and Monitoring". Sensors. 16 (8): 1310. Bibcode:2016Senso..16.1310A. doi:10.3390/s16081310. PMC 5017475. PMID 27548174.
5. Erdelj, Milan; Natalizio, Enrico; Chowdhury, Kaushik R.; Akyildiz, Ian F. (January 2017). "Help from the Sky: Leveraging UAVs for Disaster Management". IEEE Pervasive Computing. 16 (1): 24–32. doi:10.1109/MPRV.2017.11. S2CID 18047608.
6. Erdelj, Milan; Natalizio, Enrico (2016). "UAV-assisted disaster management: Applications and open issues". 2016 International Conference on Computing, Networking and Communications (ICNC). pp. 1–5. doi:10.1109/ICCNC.2016.7440563. ISBN 978-1-4673-8579-4. S2CID 6921065.
7. "No Drone Zone". National Interangency Fire Center.
8. Jansen, Bart (March 8, 2017). "NYC firefighters use drone to help battle blaze for first time". USA TODAY.
9. Yuan, Chi; Zhang, Youmin; Liu, Zhixiang (July 2015). "A survey on technologies for automatic forest fire monitoring, detection, and fighting using unmanned aerial vehicles and remote sensing techniques". Canadian Journal of Forest Research. 45 (7): 783–792. Bibcode:2015CaJFR..45..783Y. doi:10.1139/cjfr-2014-0347.
10. Martínez-De-Dios, J. R.; Merino, Luis; Ollero, Aníbal; Ribeiro, Luis M.; Viegas, Xavier (2007). "Multi-UAV Experiments: Application to Forest Fires". Multiple Heterogeneous Unmanned Aerial Vehicles. Springer Tracts in Advanced Robotics. Vol. 37. pp. 207–228. doi:10.1007/978-3-540-73958-6_8. ISBN 978-3-540-73957-9.
11. Cruz, Henry; Eckert, Martina; Meneses, Juan; Martínez, José-Fernán (16 June 2016). "Efficient Forest Fire Detection Index for Application in Unmanned Aerial Systems (UASs)". Sensors. 16 (6): 893. Bibcode:2016Senso..16..893C. doi:10.3390/s16060893. PMC 4934319. PMID 27322264.
12. Merino, L.; Caballero, F.; Martinez-De Dios, J.R.; Ollero, A. (2005). "Cooperative Fire Detection using Unmanned Aerial Vehicles". Proceedings of the 2005 IEEE International Conference on Robotics and Automation. pp. 1884–1889. doi:10.1109/ROBOT.2005.1570388. ISBN 0-7803-8914-X. S2CID 7815414.
13. Bekmezci, İlker; Sahingoz, Ozgur Koray; Temel, Şamil (May 2013). "Flying Ad-Hoc Networks (FANETs): A survey". Ad Hoc Networks. 11 (3): 1254–1270. doi:10.1016/j.adhoc.2012.12.004. S2CID 1758514.
14. S. Adams and C. Friedland, "A survey of unmanned aerial vehicle usage for imagery collection in disaster research and management," Jan. 2011.
15. Peng, Han; Razi, Abolfazl; Afghah, Fatemeh; Ashdown, Jonathan (October 2018). "A unified framework for joint mobility prediction and object profiling of drones in UAV networks". Journal of Communications and Networks. 20 (5): 434–442. arXiv:1808.00058. doi:10.1109/JCN.2018.000068. S2CID 51895302.
16. Shamsoshoara, Alireza; Khaledi, Mehrdad; Afghah, Fatemeh; Razi, Abolfazl; Ashdown, Jonathan (2019). "Distributed Cooperative Spectrum Sharing in UAV Networks Using Multi-Agent Reinforcement Learning". 2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC). pp. 1–6. arXiv:1811.05053. doi:10.1109/CCNC.2019.8651796. ISBN 978-1-5386-5553-5. S2CID 53291853.
17. Khaledi, Mehrdad; Rovira-Sugranes, Arnau; Afghah, Fatemeh; Razi, Abolfazl (2018). "On Greedy Routing in Dynamic UAV Networks". 2018 IEEE International Conference on Sensing, Communication and Networking (SECON Workshops). pp. 1–5. arXiv:1806.04587. doi:10.1109/SECONW.2018.8396354. ISBN 978-1-5386-5241-1. S2CID 48359317.
18. Chakareski, Jacob; Naqvi, Syed; Mastronarde, Nicholas; Xu, Jie; Afghah, Fatemeh; Razi, Abolfazl (March 2019). "An Energy Efficient Framework for UAV-Assisted Millimeter Wave 5G Heterogeneous Cellular Networks". IEEE Transactions on Green Communications and Networking. 3 (1): 37–44. doi:10.1109/TGCN.2019.2892141. S2CID 67899363.
19. Naqvi, Syed; Chakareski, Jacob; Mastronarde, Nicholas; Xu, Jie; Afghah, Fatemeh; Razi, Abolfazl (2018). "Energy Efficiency Analysis of UAV-Assisted mm Wave Het Nets". 2018 IEEE International Conference on Communications (ICC). pp. 1–6. doi:10.1109/ICC.2018.8422870. ISBN 978-1-5386-3180-5. S2CID 51874187.
20. Korenda, Ashwija Reddy; Zaeri-Amirani, Mohammad; Afghah, Fatemeh (2017). "A hierarchical Stackelberg-coalition formation game theoretic framework for cooperative spectrum leasing". 2017 51st Annual Conference on Information Sciences and Systems (CISS). pp. 1–6. doi:10.1109/CISS.2017.7926156. ISBN 978-1-5090-4780-2. S2CID 22677262.
21. Razi, Abolfazl; Afghah, Fatemeh; Abedi, Ali (March 2016). "Channel-Adaptive Packetization Policy for Minimal Latency and Maximal Energy Efficiency". IEEE Transactions on Wireless Communications. 15 (3): 2407–2420. arXiv:1511.06344. doi:10.1109/TWC.2015.2503750. S2CID 9910905.
22. Chakareski, Jacob (2017). "Aerial UAV-IoT sensing for ubiquitous immersive communication and virtual human teleportation". 2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). pp. 718–723. arXiv:1703.04192. doi:10.1109/INFCOMW.2017.8116465. ISBN 978-1-5386-2784-6. S2CID 3230377.
23. Chakareski, Jacob (2017). "Drone Networks for Virtual Human Teleportation". Proceedings of the 3rd Workshop on Micro Aerial Vehicle Networks, Systems, and Applications - Dro Net '17. pp. 21–26. doi:10.1145/3086439.3086448. ISBN 978-1-4503-4960-4. S2CID 7664215.
24. Chakareski, Jacob (2017). "VR/AR Immersive Communication". Proceedings of the Workshop on Virtual Reality and Augmented Reality Network - VR/AR Network '17. pp. 36–41. doi:10.1145/3097895.3097902. ISBN 978-1-4503-5055-6. S2CID 24596784.
25. Chakareski, Jacob; Velisavljevic, Vladan; Stankovic, Vladimir (September 2013). "User-Action-Driven View and Rate Scalable Multiview Video Coding". IEEE Transactions on Image Processing. 22 (9): 3473–3484. Bibcode:2013ITIP...22.3473C. doi:10.1109/TIP.2013.2269801. PMID 23797253. S2CID 18735535.
26. Chakareski, Jacob (February 2015). "Uplink Scheduling of Visual Sensors: When View Popularity Matters". IEEE Transactions on Communications. 63 (2): 510–519. doi:10.1109/TCOMM.2014.2380316. S2CID 28272281.
27. Razi, Abolfazl; Afghah, Fatemeh; Chakareski, Jacob (2017). "Optimal measurement policy for predicting UAV network topology". 2017 51st Asilomar Conference on Signals, Systems, and Computers. pp. 1374–1378. arXiv:1710.11185. doi:10.1109/ACSSC.2017.8335579. ISBN 978-1-5386-1823-3. S2CID 4946028.
28. Afghah, Fatemeh; Shamsoshoara, Alireza; Njilla, Laurent; Kamhoua, Charles (2018). "A reputation-based stackelberg game model to enhance secrecy rate in spectrum leasing to selfish IoT devices". IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). pp. 312–317. arXiv:1802.05832. doi:10.1109/INFCOMW.2018.8406970. ISBN 978-1-5386-5979-3. S2CID 3371061.
29. Schneider, Eric; Balas, Ofear; Özgelen, Arif Tuna; Sklar, Elizabeth I; Parsons, Simon D (May 2014). "An empirical evaluation of auction-based task allocation in multi-robot teams". Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. Aamas '14. pp. 1443–1444. ISBN 9781450327381.
30. Korsah, G. Ayorkor; Stentz, Anthony; Dias, M. Bernardine (22 October 2013). "A comprehensive taxonomy for multi-robot task allocation". The International Journal of Robotics Research. 32 (12): 1495–1512. doi:10.1177/0278364913496484. S2CID 12515065.
31. Ghazanfari, Behzad; Afghah, Fatemeh; Taylor, Matthew E. (2018). "Autonomous Extraction of a Hierarchical Structure of Tasks in Reinforcement Learning, A Sequential Associate Rule Mining Approach". arXiv:1811.08275 [cs.AI].
32. Ghazanfari, Behzad; Mozayani, Nasser (2014). "Enhancing Nash Q-learning and Team Q-learning mechanisms by using bottlenecks". Journal of Intelligent & Fuzzy Systems. 26 (6): 2771–2783. doi:10.3233/IFS-130945.
33. Shamsoshoara, Alireza; Darmani, Yousef (2015). "Enhanced multi-route ad hoc on-demand distance vector routing". 2015 23rd Iranian Conference on Electrical Engineering. pp. 578–583. doi:10.1109/IranianCEE.2015.7146282. ISBN 978-1-4799-1972-7. S2CID 25361994.
34. Shamsoshoara, Alireza (9 January 2019). "Overview of Blakley's Secret Sharing Scheme". arXiv:1901.02802 [cs.CR].
35. Mousavi, Seyed Sajad; Schukat, Michael; Howley, Enda (1 September 2017). "Traffic light control using deep policy-gradient and value-function-based reinforcement learning". IET Intelligent Transport Systems. 11 (7): 417–423. arXiv:1704.08883. doi:10.1049/iet-its.2017.0153. S2CID 19934639.
36. Mousavi, Sajad; Schukat, Michael; Howley, Enda; Borji, Ali; Mozayani, Nasser (18 February 2017). "Learning to predict where to look in interactive environments using deep recurrent q-learning". arXiv:1612.05753 [cs.CV].
37. Ghazanfari, Behzad; Mozayani, Nasser (July 2016). "Extracting bottlenecks for reinforcement learning agent by holonic concept clustering and attentional functions". Expert Systems with Applications. 54: 61–77. doi:10.1016/j.eswa.2016.01.030.
38. Shamsoshoara, Alireza (20 January 2019). "Ring Oscillator and its application as Physical Unclonable Function (PUF) for Password Management". arXiv:1901.06733 [cs.CR].
39. Mousavi, Seyed Sajad; Schukat, Michael; Howley, Enda (2018). "Deep Reinforcement Learning: An Overview". Proceedings of SAI Intelligent Systems Conference (Intelli Sys) 2016. Lecture Notes in Networks and Systems. Vol. 16. pp. 426–440. arXiv:1806.08894. doi:10.1007/978-3-319-56991-8_32. ISBN 978-3-319-56990-1. S2CID 49418885.
40. Afghah, Fatemeh; Zaeri-Amirani, Mohammad; Razi, Abolfazl; Chakareski, Jacob; Bentley, Elizabeth (2018). "A Coalition Formation Approach to Coordinated Task Allocation in Heterogeneous UAV Networks". 2018 Annual American Control Conference (ACC). pp. 5968–5975. arXiv:1711.00214. doi:10.23919/ACC.2018.8431278. ISBN 978-1-5386-5428-6. S2CID 21758324.
41. Mousavi, Sajad; Afghah, Fatemeh; Ashdown, Jonathan D.; Turck, Kurt (2018). "Leader-follower based coalition formation in large-scale UAV networks, a quantum evolutionary approach". IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). pp. 882–887. arXiv:1802.07187. doi:10.1109/INFCOMW.2018.8406915. ISBN 978-1-5386-5979-3. S2CID 3434495.
42. Li, Pei; Duan, Haibin (1 September 2017). "A potential game approach to multiple UAV cooperative search and surveillance". Aerospace Science and Technology. 68: 403–415. Bibcode:2017AeST...68..403L. doi:10.1016/j.ast.2017.05.031.
43. Mousavi, Sajad; Afghah, Fatemeh; Ashdown, Jonathan D.; Turck, Kurt (1 May 2019). "Use of a quantum genetic algorithm for coalition formation in large-scale UAV networks". Ad Hoc Networks. 87: 26–36. doi:10.1016/j.adhoc.2018.11.008. S2CID 69839422.
44. Ruan, Lang; Chen, Jin; Guo, Qiuju; Jiang, Han; Zhang, Yuli; Liu, Dianxiong (29 November 2018). "A Coalition Formation Game Approach for Efficient Cooperative Multi-UAV Deployment". Applied Sciences. 8 (12): 2427. doi:10.3390/app8122427.
45. Rahwan, Talal; Jennings, Nick (May 2008). "An improved dynamic programming algorithm for coalition structure generation". Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems. Aamas '08. pp. 1417–1420. ISBN 9780981738123.
46. Cruz-Mencia, Francisco; Cerquides, Jesús; Espinosa, Antonio; Moure, Juan C.; Rodríguez-Aguilar, Juan Antonio (July 2013). Optimizing Performance for Coalition Structure Generation Problems' IDP Algorithm. Csrea. hdl:10261/133773. ISBN 978-1-60132-258-6.
47. Sless, Liat; Hazon, Noam; Kraus, Sarit; Wooldridge, Michael (May 2014). "Forming coalitions and facilitating relationships for completing tasks in social networks". AAMAS '14: Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems. pp. 261–268. ISBN 9781450327381.
48. Bistaffa, Filippo; Farinelli, Alessandro; Cerquides, Jesús; Rodríguez-Aguilar, Juan Antonio; Ramchurn, S. D. (May 2014). "Anytime coalition structure generation on synergy graphs". AAMAS '14: Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems. pp. 13–20. ISBN 9781450327381.