Digitala Vetenskapliga Arkivet

Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Exploring feasibility of reinforcement learning flight route planning
Linköpings universitet, Institutionen för datavetenskap. Linköpings universitet, Filosofiska fakulteten.
2021 (Engelska)Självständigt arbete på grundnivå (kandidatexamen), 12 poäng / 18 hpStudentuppsats (Examensarbete)Alternativ titel
Undersökning av använding av förstärkningsinlärning för flyruttsplannering (Svenska)
Abstract [en]

This thesis explores and compares traditional and reinforcement learning (RL) methods of performing 2D flight path planning in 3D space. A wide overview of natural, classic, and learning approaches to planning s done in conjunction with a review of some general recurring problems and tradeoffs that appear within planning. This general background then serves as a basis for motivating different possible solutions for this specific problem. These solutions are implemented, together with a testbed inform of a parallelizable simulation environment. This environment makes use of random world generation and physics combined with an aerodynamical model. An A* planner, a local RL planner, and a global RL planner are developed and compared against each other in terms of performance, speed, and general behavior. An autopilot model is also trained and used both to measure flight feasibility and to constrain the planners to followable paths. All planners were partially successful, with the global planner exhibiting the highest overall performance. The RL planners were also found to be more reliable in terms of both speed and followability because of their ability to leave difficult decisions to the autopilot. From this it is concluded that machine learning in general, and reinforcement learning in particular, is a promising future avenue for solving the problem of flight route planning in dangerous environments.

Ort, förlag, år, upplaga, sidor
2021. , s. 36
Nyckelord [en]
SAAB, flight route planning, autorouting, auto-routing, auto routing, AI, machine learning, fighter jet, convolution, PPO, DQN, Astar, A*, C++, Python, LibTorch, PyTorch, multi threading, multi-threading, simulation, aerodynamics, world generation, Perlin noise, investigation, reward
Nyckelord [sv]
Flygplanering, flygruttsplannering, maskininlärning, AI, SAAB, faltning, faltningslager, belöning
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Identifikatorer
URN: urn:nbn:se:liu:diva-178314ISRN: LIU-IDA/KOGVET-G–21/031—SEOAI: oai:DiVA.org:liu-178314DiVA, id: diva2:1585642
Externt samarbete
Dynorobotics AB
Ämne / kurs
Kognitionsvetenskap
Handledare
Examinatorer
Tillgänglig från: 2021-09-01 Skapad: 2021-08-17 Senast uppdaterad: 2021-09-01Bibliografiskt granskad

Open Access i DiVA

fulltext(9076 kB)1012 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 9076 kBChecksumma SHA-512
90ce138bb1176555b7d2bba9237d0e95feef4ac48b5bdd689c8d640a5d282949cae15d7a8f31e9ed06fbe18e8f06112767881c3982d8add07013f201b4e142d7
Typ fulltextMimetyp application/pdf

Övriga länkar

Alternativ nerladdning
Av organisationen
Institutionen för datavetenskapFilosofiska fakulteten
Datorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 1012 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 675 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf