Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323072992> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4323072992 abstract "High altitude balloons have proved useful for ecological aerial surveys, atmospheric monitoring, and communication relays. However, due to weight and power constraints, there is a need to investigate alternate modes of propulsion to navigate in the stratosphere. Very recently, reinforcement learning has been proposed as a control scheme to maintain the balloon in the region of a fixed location, facilitated through diverse opposing wind-fields at different altitudes. Although air-pump based station keeping has been explored, there is no research on the control problem for venting and ballasting actuated balloons, which is commonly used as a low-cost alternative. We show how reinforcement learning can be used for this type of balloon. Specifically, we use the soft actor-critic algorithm, which on average is able to station-keep within 50;km for 25% of the flight, consistent with state-of-the-art. Furthermore, we show that the proposed controller effectively minimises the consumption of resources, thereby supporting long duration flights. We frame the controller as a continuous control reinforcement learning problem, which allows for a more diverse range of trajectories, as opposed to current state-of-the-art work, which uses discrete action spaces. Furthermore, through continuous control, we can make use of larger ascent rates which are not possible using air-pumps. The desired ascent-rate is decoupled into desired altitude and time-factor to provide a more transparent policy, compared to low-level control commands used in previous works. Finally, by applying the equations of motion, we establish appropriate thresholds for venting and ballasting to prevent the agent from exploiting the environment. More specifically, we ensure actions are physically feasible by enforcing constraints on venting and ballasting." @default.
- W4323072992 created "2023-03-05" @default.
- W4323072992 creator A5011528263 @default.
- W4323072992 creator A5032607052 @default.
- W4323072992 creator A5079000862 @default.
- W4323072992 creator A5090029431 @default.
- W4323072992 creator A5091798976 @default.
- W4323072992 date "2023-03-02" @default.
- W4323072992 modified "2023-09-24" @default.
- W4323072992 title "Resource-Constrained Station-Keeping for Helium Balloons using Reinforcement Learning" @default.
- W4323072992 doi "https://doi.org/10.48550/arxiv.2303.01173" @default.
- W4323072992 hasPublicationYear "2023" @default.
- W4323072992 type Work @default.
- W4323072992 citedByCount "0" @default.
- W4323072992 crossrefType "posted-content" @default.
- W4323072992 hasAuthorship W4323072992A5011528263 @default.
- W4323072992 hasAuthorship W4323072992A5032607052 @default.
- W4323072992 hasAuthorship W4323072992A5079000862 @default.
- W4323072992 hasAuthorship W4323072992A5090029431 @default.
- W4323072992 hasAuthorship W4323072992A5091798976 @default.
- W4323072992 hasBestOaLocation W43230729921 @default.
- W4323072992 hasConcept C126255220 @default.
- W4323072992 hasConcept C127413603 @default.
- W4323072992 hasConcept C146978453 @default.
- W4323072992 hasConcept C154945302 @default.
- W4323072992 hasConcept C203479927 @default.
- W4323072992 hasConcept C204323151 @default.
- W4323072992 hasConcept C2775924081 @default.
- W4323072992 hasConcept C33923547 @default.
- W4323072992 hasConcept C39432304 @default.
- W4323072992 hasConcept C41008148 @default.
- W4323072992 hasConcept C44154836 @default.
- W4323072992 hasConcept C47446073 @default.
- W4323072992 hasConcept C6557445 @default.
- W4323072992 hasConcept C79403827 @default.
- W4323072992 hasConcept C86803240 @default.
- W4323072992 hasConcept C91575142 @default.
- W4323072992 hasConcept C97541855 @default.
- W4323072992 hasConceptScore W4323072992C126255220 @default.
- W4323072992 hasConceptScore W4323072992C127413603 @default.
- W4323072992 hasConceptScore W4323072992C146978453 @default.
- W4323072992 hasConceptScore W4323072992C154945302 @default.
- W4323072992 hasConceptScore W4323072992C203479927 @default.
- W4323072992 hasConceptScore W4323072992C204323151 @default.
- W4323072992 hasConceptScore W4323072992C2775924081 @default.
- W4323072992 hasConceptScore W4323072992C33923547 @default.
- W4323072992 hasConceptScore W4323072992C39432304 @default.
- W4323072992 hasConceptScore W4323072992C41008148 @default.
- W4323072992 hasConceptScore W4323072992C44154836 @default.
- W4323072992 hasConceptScore W4323072992C47446073 @default.
- W4323072992 hasConceptScore W4323072992C6557445 @default.
- W4323072992 hasConceptScore W4323072992C79403827 @default.
- W4323072992 hasConceptScore W4323072992C86803240 @default.
- W4323072992 hasConceptScore W4323072992C91575142 @default.
- W4323072992 hasConceptScore W4323072992C97541855 @default.
- W4323072992 hasLocation W43230729921 @default.
- W4323072992 hasOpenAccess W4323072992 @default.
- W4323072992 hasPrimaryLocation W43230729921 @default.
- W4323072992 hasRelatedWork W2137244709 @default.
- W4323072992 hasRelatedWork W2139943166 @default.
- W4323072992 hasRelatedWork W2146616934 @default.
- W4323072992 hasRelatedWork W2373820626 @default.
- W4323072992 hasRelatedWork W2774865794 @default.
- W4323072992 hasRelatedWork W2899084033 @default.
- W4323072992 hasRelatedWork W2923653485 @default.
- W4323072992 hasRelatedWork W2957776456 @default.
- W4323072992 hasRelatedWork W3214623065 @default.
- W4323072992 hasRelatedWork W4313305131 @default.
- W4323072992 isParatext "false" @default.
- W4323072992 isRetracted "false" @default.
- W4323072992 workType "article" @default.