{"id":{"repo_id":"rgu","oai_identifier":"oai:rgu-repository.worktribe.com:2807511"},"canonical_url":"https://search.dev.ndltd.org/etd/rgu/oai:rgu-repository.worktribe.com:2807511","repository":{"repo_id":"rgu","name":"Robert Gordon University","base_url":"https://rgu-repository.worktribe.com/oaiprovider"},"display":{"title":"Developing computational intelligence for helicopter flights control.","abstract":"This aim of this research is to develop computational intelligence for helicopter flights control, a system that learns to fly a helicopter in the way a human pilot would. The work is being carried out because of increased pilots’ workloads and the reward in terms of cost and safety, in a dangerous flight mission. The project draws on the benefits of using inverse simulation and evolutionary algorithms to model systems similar to human process. The aim is to define tasks for the helicopter and have the pilot find control settings that carry out those tasks. The inverse simulation technique for a helicopter generates the control inputs required for a desired set of motion outputs. Most recent researches had relied on the specification of a smooth trajectory, but in piloted tests, pilots are rather given way-points conditions to be met rather than follow precise trajectories. Genetic algorithms (GA) generate feasible solutions to the inverse problem in which the helicopter’s trajectory is defined as a set of way-points. Two genetic encoding methods were implemented in flying a longitudinal acceleration/deceleration manoeuvre. They are: discrete and continuous variables controls. The helicopter pilot was formulated as a multi-optimisation problem with four objectives imposed as penalties. Controls from a tuned experiment using GA were used to test and evaluate the pilot. The study proposes an optimization approach termed maxPenalty, which compared and returned the biggest of the four penalties. Here, the individual objectives’ contribution towards the overall fitness was of paramount interest. The GA attempts to maximise the fitness to 1, while reducing the biggest of the penalties to 0, and minimising the pilot workload. The work shows some aspects of the GA-produced flight that are human-like, and the fact that humans do not move along precise trajectories.","abstract_html":"This aim of this research is to develop computational intelligence for helicopter flights control, a system that learns to fly a helicopter in the way a human pilot would. The work is being carried out because of increased pilots’ workloads and the reward in terms of cost and safety, in a dangerous flight mission. The project draws on the benefits of using inverse simulation and evolutionary algorithms to model systems similar to human process. The aim is to define tasks for the helicopter and have the pilot find control settings that carry out those tasks. The inverse simulation technique for a helicopter generates the control inputs required for a desired set of motion outputs. Most recent researches had relied on the specification of a smooth trajectory, but in piloted tests, pilots are rather given way-points conditions to be met rather than follow precise trajectories. Genetic algorithms (GA) generate feasible solutions to the inverse problem in which the helicopter’s trajectory is defined as a set of way-points. Two genetic encoding methods were implemented in flying a longitudinal acceleration/deceleration manoeuvre. They are: discrete and continuous variables controls. The helicopter pilot was formulated as a multi-optimisation problem with four objectives imposed as penalties. Controls from a tuned experiment using GA were used to test and evaluate the pilot. The study proposes an optimization approach termed maxPenalty, which compared and returned the biggest of the four penalties. Here, the individual objectives’ contribution towards the overall fitness was of paramount interest. The GA attempts to maximise the fitness to 1, while reducing the biggest of the penalties to 0, and minimising the pilot workload. The work shows some aspects of the GA-produced flight that are human-like, and the fact that humans do not move along precise trajectories.","abstract_has_math":false,"creators":["Orike, Sunny"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["J. McCall and G. Brindley"],"committee_chairs":[],"committee_members":[],"year":2008,"date_issued":"2008","date_published":"2008","updated_at":"2026-07-24T04:10:12Z","subjects":["Helicopter flight control","Computational intelligence","Inverse simulation","Genetic algorithms","Pilot modelling","Multi-objective optimisation"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:rgu-repository.worktribe.com:2807511","https://doi.org/10.48526/rgu-wt-2807511"],"render_values":[{"text":"oai:rgu-repository.worktribe.com:2807511","href":null,"code":true},{"text":"https://doi.org/10.48526/rgu-wt-2807511","href":"https://doi.org/10.48526/rgu-wt-2807511","code":true}]}]},"links":{"outbound_url":"https://rgu-repository.worktribe.com/2807511/1/ORIKE%202008%20Developing%20computational%20intelligence","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["J. McCall and G. Brindley"]},{"key":"dc:contributor.sponsor","label":"Sponsor","values":["New Funding Organisation"]},{"key":"dc:creator","label":"Author","values":["Orike, Sunny"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2008-08-31"]},{"key":"dc:date.issued","label":"Date","values":["2008"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://rgu-repository.worktribe.com/output/2807511"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Helicopter flight control","Computational intelligence","Inverse simulation","Genetic algorithms","Pilot modelling","Multi-objective optimisation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:rgu-repository.worktribe.com:2807511","https://doi.org/10.48526/rgu-wt-2807511"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://rgu-repository.worktribe.com/2807511/1/ORIKE%202008%20Developing%20computational%20intelligence"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This aim of this research is to develop computational intelligence for helicopter flights control, a system that learns to fly a helicopter in the way a human pilot would. The work is being carried out because of increased pilots’ workloads and the reward in terms of cost and safety, in a dangerous flight mission. The project draws on the benefits of using inverse simulation and evolutionary algorithms to model systems similar to human process. The aim is to define tasks for the helicopter and have the pilot find control settings that carry out those tasks. The inverse simulation technique for a helicopter generates the control inputs required for a desired set of motion outputs. Most recent researches had relied on the specification of a smooth trajectory, but in piloted tests, pilots are rather given way-points conditions to be met rather than follow precise trajectories. Genetic algorithms (GA) generate feasible solutions to the inverse problem in which the helicopter’s trajectory is defined as a set of way-points. Two genetic encoding methods were implemented in flying a longitudinal acceleration/deceleration manoeuvre. They are: discrete and continuous variables controls. The helicopter pilot was formulated as a multi-optimisation problem with four objectives imposed as penalties. Controls from a tuned experiment using GA were used to test and evaluate the pilot. The study proposes an optimization approach termed maxPenalty, which compared and returned the biggest of the four penalties. Here, the individual objectives’ contribution towards the overall fitness was of paramount interest. The GA attempts to maximise the fitness to 1, while reducing the biggest of the penalties to 0, and minimising the pilot workload. The work shows some aspects of the GA-produced flight that are human-like, and the fact that humans do not move along precise trajectories."]},{"key":"dc:title","label":"Title","values":["Developing computational intelligence for helicopter flights control."]}]}],"canonical_facts":{"dc:contributor.advisor":["J. McCall and G. Brindley"],"dc:contributor.sponsor":["New Funding Organisation"],"dc:creator":["Orike, Sunny"],"dc:date":["2008-08-31"],"dc:date.issued":["2008"],"dc:description.abstract":["This aim of this research is to develop computational intelligence for helicopter flights control, a system that learns to fly a helicopter in the way a human pilot would. The work is being carried out because of increased pilots’ workloads and the reward in terms of cost and safety, in a dangerous flight mission. The project draws on the benefits of using inverse simulation and evolutionary algorithms to model systems similar to human process. The aim is to define tasks for the helicopter and have the pilot find control settings that carry out those tasks. The inverse simulation technique for a helicopter generates the control inputs required for a desired set of motion outputs. Most recent researches had relied on the specification of a smooth trajectory, but in piloted tests, pilots are rather given way-points conditions to be met rather than follow precise trajectories. Genetic algorithms (GA) generate feasible solutions to the inverse problem in which the helicopter’s trajectory is defined as a set of way-points. Two genetic encoding methods were implemented in flying a longitudinal acceleration/deceleration manoeuvre. They are: discrete and continuous variables controls. The helicopter pilot was formulated as a multi-optimisation problem with four objectives imposed as penalties. Controls from a tuned experiment using GA were used to test and evaluate the pilot. The study proposes an optimization approach termed maxPenalty, which compared and returned the biggest of the four penalties. Here, the individual objectives’ contribution towards the overall fitness was of paramount interest. The GA attempts to maximise the fitness to 1, while reducing the biggest of the penalties to 0, and minimising the pilot workload. The work shows some aspects of the GA-produced flight that are human-like, and the fact that humans do not move along precise trajectories."],"dc:identifier":["oai:rgu-repository.worktribe.com:2807511","https://doi.org/10.48526/rgu-wt-2807511"],"dc:identifier.uri":["https://rgu-repository.worktribe.com/2807511/1/ORIKE%202008%20Developing%20computational%20intelligence"],"dc:language":["en"],"dc:relation.isreferencedby":["https://rgu-repository.worktribe.com/output/2807511"],"dc:subject":["Helicopter flight control","Computational intelligence","Inverse simulation","Genetic algorithms","Pilot modelling","Multi-objective optimisation"],"dc:title":["Developing computational intelligence for helicopter flights control."],"dc:type":["Thesis"]},"updated_at":"2026-07-24T04:10:12Z"}