dc.contributor.author | Dong, S | |
dc.contributor.author | Das, S | |
dc.contributor.author | Townley, S | |
dc.contributor.author | Thornton, A | |
dc.date.accessioned | 2023-10-17T12:20:26Z | |
dc.date.issued | 2023-10-16 | |
dc.date.updated | 2023-10-17T11:11:32Z | |
dc.description.abstract | Flocking, shoaling and swarming in animal groups serve a number of functions, including improving information transmission and reducing predation risks. Individuals in biological populations tend to make limited and simple responses to each other and also to stimuli in the environment. But by acting together they can accomplish collective tasks, which is referred to as swarm intelligence. Insights from natural systems have inspired work in numerous areas, such as meta-heuristic optimization, machine learning and image processing. However, the limitations of information sharing, and transfer make it difficult to solve real-world engineering problems in physical world using the swarm intelligence mechanism. This contrasts with natural systems where, for example, birds use social information to improve sensing of environmental cues and make decisions without lag during flight. Thus, behavioural modelling of animal swarming may provide new insights into this problem. Here, we show comparison of two data-driven deep neural network models for drone flocking. | en_GB |
dc.identifier.citation | 2023 28th International Conference on Automation and Computing (ICAC), 30 August - 1 September 2023 | en_GB |
dc.identifier.doi | https://doi.org/10.1109/icac57885.2023.10275209 | |
dc.identifier.uri | http://hdl.handle.net/10871/134272 | |
dc.identifier | ORCID: 0000-0002-8394-5303 (Das, Saptarshi) | |
dc.identifier | ScopusID: 57193720393 (Das, Saptarshi) | |
dc.identifier | ResearcherID: D-5518-2012 (Das, Saptarshi) | |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_GB |
dc.rights | © 2023 IEEE | en_GB |
dc.subject | collective behaviour | en_GB |
dc.subject | swarm intelligence | en_GB |
dc.subject | artificial intelligence | en_GB |
dc.subject | self-organization model | en_GB |
dc.title | Swarm Intelligence Based Drone Flocking Model | en_GB |
dc.type | Conference paper | en_GB |
dc.date.available | 2023-10-17T12:20:26Z | |
dc.description | This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record | en_GB |
dc.relation.ispartof | 2023 28th International Conference on Automation and Computing (ICAC) | |
dc.rights.uri | http://www.rioxx.net/licenses/all-rights-reserved | en_GB |
dcterms.dateAccepted | 2023 | |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2023-10-16 | |
rioxxterms.type | Conference Paper/Proceeding/Abstract | en_GB |
refterms.dateFCD | 2023-10-17T12:18:34Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2023-10-17T12:20:27Z | |
refterms.panel | B | en_GB |
pubs.name-of-conference | 2023 28th International Conference on Automation and Computing (ICAC) | |