Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963669306> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2963669306 abstract "Multi-robot transfer learning allows a robot to use data generated by a second, similar robot to improve its own behavior. The potential advantages are reducing the time of training and the unavoidable risks that exist during the training phase. Transfer learning algorithms aim to find an optimal transfer map between different robots. In this paper, we investigate, through a theoretical study of single-input single-output (SISO) systems, the properties of such optimal transfer maps. We first show that the optimal transfer learning map is, in general, a dynamic system. The main contribution of the paper is to provide an algorithm for determining the properties of this optimal dynamic map including its order and regressors (i.e., the variables it depends on). The proposed algorithm does not require detailed knowledge of the robots' dynamics, but relies on basic system properties easily obtainable through simple experimental tests. We validate the proposed algorithm experimentally through an example of transfer learning between two different quadrotor platforms. Experimental results show that an optimal dynamic map, with correct properties obtained from our proposed algorithm, achieves 60–70% reduction of transfer learning error compared to the cases when the data is directly transferred or transferred using an optimal static map." @default.
- W2963669306 created "2019-07-30" @default.
- W2963669306 creator A5052147335 @default.
- W2963669306 creator A5090475114 @default.
- W2963669306 date "2017-09-01" @default.
- W2963669306 modified "2023-09-23" @default.
- W2963669306 title "Multi-robot transfer learning: A dynamical system perspective" @default.
- W2963669306 cites W1457482454 @default.
- W2963669306 cites W1518858799 @default.
- W2963669306 cites W1997543377 @default.
- W2963669306 cites W2037346085 @default.
- W2963669306 cites W2066239357 @default.
- W2963669306 cites W2085757577 @default.
- W2963669306 cites W2091714857 @default.
- W2963669306 cites W2098514000 @default.
- W2963669306 cites W2123261262 @default.
- W2963669306 cites W2126909264 @default.
- W2963669306 cites W2134949557 @default.
- W2963669306 cites W2143346970 @default.
- W2963669306 cites W2184965786 @default.
- W2963669306 cites W2396317032 @default.
- W2963669306 cites W2592857946 @default.
- W2963669306 cites W2964050632 @default.
- W2963669306 cites W2964254257 @default.
- W2963669306 cites W2964262254 @default.
- W2963669306 cites W4292872153 @default.
- W2963669306 cites W2207114418 @default.
- W2963669306 doi "https://doi.org/10.1109/iros.2017.8206342" @default.
- W2963669306 hasPublicationYear "2017" @default.
- W2963669306 type Work @default.
- W2963669306 sameAs 2963669306 @default.
- W2963669306 citedByCount "23" @default.
- W2963669306 countsByYear W29636693062018 @default.
- W2963669306 countsByYear W29636693062019 @default.
- W2963669306 countsByYear W29636693062020 @default.
- W2963669306 countsByYear W29636693062021 @default.
- W2963669306 countsByYear W29636693062022 @default.
- W2963669306 crossrefType "proceedings-article" @default.
- W2963669306 hasAuthorship W2963669306A5052147335 @default.
- W2963669306 hasAuthorship W2963669306A5090475114 @default.
- W2963669306 hasBestOaLocation W29636693062 @default.
- W2963669306 hasConcept C111335779 @default.
- W2963669306 hasConcept C11413529 @default.
- W2963669306 hasConcept C12713177 @default.
- W2963669306 hasConcept C150899416 @default.
- W2963669306 hasConcept C154945302 @default.
- W2963669306 hasConcept C2524010 @default.
- W2963669306 hasConcept C2775924081 @default.
- W2963669306 hasConcept C33923547 @default.
- W2963669306 hasConcept C41008148 @default.
- W2963669306 hasConcept C47446073 @default.
- W2963669306 hasConcept C90509273 @default.
- W2963669306 hasConceptScore W2963669306C111335779 @default.
- W2963669306 hasConceptScore W2963669306C11413529 @default.
- W2963669306 hasConceptScore W2963669306C12713177 @default.
- W2963669306 hasConceptScore W2963669306C150899416 @default.
- W2963669306 hasConceptScore W2963669306C154945302 @default.
- W2963669306 hasConceptScore W2963669306C2524010 @default.
- W2963669306 hasConceptScore W2963669306C2775924081 @default.
- W2963669306 hasConceptScore W2963669306C33923547 @default.
- W2963669306 hasConceptScore W2963669306C41008148 @default.
- W2963669306 hasConceptScore W2963669306C47446073 @default.
- W2963669306 hasConceptScore W2963669306C90509273 @default.
- W2963669306 hasLocation W29636693061 @default.
- W2963669306 hasLocation W29636693062 @default.
- W2963669306 hasOpenAccess W2963669306 @default.
- W2963669306 hasPrimaryLocation W29636693061 @default.
- W2963669306 hasRelatedWork W1746819321 @default.
- W2963669306 hasRelatedWork W2037346085 @default.
- W2963669306 hasRelatedWork W2091714857 @default.
- W2963669306 hasRelatedWork W2097381042 @default.
- W2963669306 hasRelatedWork W2165698076 @default.
- W2963669306 hasRelatedWork W2192203593 @default.
- W2963669306 hasRelatedWork W2585083595 @default.
- W2963669306 hasRelatedWork W2592857946 @default.
- W2963669306 hasRelatedWork W2605368761 @default.
- W2963669306 hasRelatedWork W2787174146 @default.
- W2963669306 hasRelatedWork W2925894593 @default.
- W2963669306 hasRelatedWork W2962816839 @default.
- W2963669306 hasRelatedWork W2963280855 @default.
- W2963669306 hasRelatedWork W2964050632 @default.
- W2963669306 hasRelatedWork W2964262254 @default.
- W2963669306 hasRelatedWork W2980113592 @default.
- W2963669306 hasRelatedWork W3013309904 @default.
- W2963669306 hasRelatedWork W3035219538 @default.
- W2963669306 hasRelatedWork W3038104799 @default.
- W2963669306 hasRelatedWork W3101442004 @default.
- W2963669306 isParatext "false" @default.
- W2963669306 isRetracted "false" @default.
- W2963669306 magId "2963669306" @default.
- W2963669306 workType "article" @default.