Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308016422> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4308016422 endingPage "21" @default.
- W4308016422 startingPage "21" @default.
- W4308016422 abstract "<ns4:p><ns4:bold>Background: </ns4:bold>In physical human-robot interaction (pHRI), admittance control is widely used. The most critical thing in admittance control is the configuration of admittance parameters, but a constant admittance value can not meet the needs of interactive indicators smoothness especially. Variable admittance control is a method to overcome this limitation by adjusting the admittance value in real time. This paper proposes a fuzzy Q-learning (FQL) variable admittance control system, which integrates the fuzzy system (FIS) and reinforcement learning method Q-learning. </ns4:p><ns4:p> <ns4:bold>Methods:</ns4:bold> FIS is used to turn a continuous input state into fuzzy set and Q-learning is used to train the premise strength of fuzzy rules to get the optimal policy of variable admittance value. To verify the performance of this method, an experiment was performed using an AUBO i5 robot. Training trajectory is point-to-point (PTP) trajectory, several interaction variables before and after training by the algorithm are compared to show the validity of algorithm.</ns4:p><ns4:p> <ns4:bold>Results:</ns4:bold> Experimental results show that the reward converges to a smaller value in about 25 episodes, and the reward of the last five episodes reduces by 68%. The motion trajectory after algorithm training is closer to the ideal min-jerk trajectory and the deviation and mean value of interaction force become smaller.</ns4:p><ns4:p> <ns4:bold>Conclusions: </ns4:bold>The proposed FQL method can converge in a few episodes and can improve the performance of pHRI by minimizing the jerk based cost function.</ns4:p>" @default.
- W4308016422 created "2022-11-07" @default.
- W4308016422 creator A5016773235 @default.
- W4308016422 creator A5044206847 @default.
- W4308016422 creator A5086383463 @default.
- W4308016422 date "2022-11-01" @default.
- W4308016422 modified "2023-10-10" @default.
- W4308016422 title "Fuzzy Q-Learning interaction controller design for collaborative robot" @default.
- W4308016422 cites W1511864092 @default.
- W4308016422 cites W1885639605 @default.
- W4308016422 cites W1978023077 @default.
- W4308016422 cites W2009192474 @default.
- W4308016422 cites W2075586348 @default.
- W4308016422 cites W2087527234 @default.
- W4308016422 cites W2093945540 @default.
- W4308016422 cites W2097919178 @default.
- W4308016422 cites W2101392974 @default.
- W4308016422 cites W2126585005 @default.
- W4308016422 cites W2142196876 @default.
- W4308016422 cites W2156060469 @default.
- W4308016422 cites W2305205647 @default.
- W4308016422 cites W2586687222 @default.
- W4308016422 cites W2771354076 @default.
- W4308016422 cites W2939037429 @default.
- W4308016422 cites W2948014490 @default.
- W4308016422 doi "https://doi.org/10.12688/cobot.17595.1" @default.
- W4308016422 hasPublicationYear "2022" @default.
- W4308016422 type Work @default.
- W4308016422 citedByCount "0" @default.
- W4308016422 crossrefType "journal-article" @default.
- W4308016422 hasAuthorship W4308016422A5016773235 @default.
- W4308016422 hasAuthorship W4308016422A5044206847 @default.
- W4308016422 hasAuthorship W4308016422A5086383463 @default.
- W4308016422 hasConcept C108811297 @default.
- W4308016422 hasConcept C119599485 @default.
- W4308016422 hasConcept C121332964 @default.
- W4308016422 hasConcept C127413603 @default.
- W4308016422 hasConcept C1276947 @default.
- W4308016422 hasConcept C13662910 @default.
- W4308016422 hasConcept C154945302 @default.
- W4308016422 hasConcept C17829176 @default.
- W4308016422 hasConcept C195975749 @default.
- W4308016422 hasConcept C2775924081 @default.
- W4308016422 hasConcept C41008148 @default.
- W4308016422 hasConcept C44154836 @default.
- W4308016422 hasConcept C47446073 @default.
- W4308016422 hasConcept C58166 @default.
- W4308016422 hasConcept C90509273 @default.
- W4308016422 hasConceptScore W4308016422C108811297 @default.
- W4308016422 hasConceptScore W4308016422C119599485 @default.
- W4308016422 hasConceptScore W4308016422C121332964 @default.
- W4308016422 hasConceptScore W4308016422C127413603 @default.
- W4308016422 hasConceptScore W4308016422C1276947 @default.
- W4308016422 hasConceptScore W4308016422C13662910 @default.
- W4308016422 hasConceptScore W4308016422C154945302 @default.
- W4308016422 hasConceptScore W4308016422C17829176 @default.
- W4308016422 hasConceptScore W4308016422C195975749 @default.
- W4308016422 hasConceptScore W4308016422C2775924081 @default.
- W4308016422 hasConceptScore W4308016422C41008148 @default.
- W4308016422 hasConceptScore W4308016422C44154836 @default.
- W4308016422 hasConceptScore W4308016422C47446073 @default.
- W4308016422 hasConceptScore W4308016422C58166 @default.
- W4308016422 hasConceptScore W4308016422C90509273 @default.
- W4308016422 hasFunder F4320321001 @default.
- W4308016422 hasFunder F4320335777 @default.
- W4308016422 hasLocation W43080164221 @default.
- W4308016422 hasOpenAccess W4308016422 @default.
- W4308016422 hasPrimaryLocation W43080164221 @default.
- W4308016422 hasRelatedWork W1535194415 @default.
- W4308016422 hasRelatedWork W1548742399 @default.
- W4308016422 hasRelatedWork W1967640207 @default.
- W4308016422 hasRelatedWork W2027477630 @default.
- W4308016422 hasRelatedWork W2073993785 @default.
- W4308016422 hasRelatedWork W2090938943 @default.
- W4308016422 hasRelatedWork W2138538913 @default.
- W4308016422 hasRelatedWork W2172143357 @default.
- W4308016422 hasRelatedWork W2320841773 @default.
- W4308016422 hasRelatedWork W2539575485 @default.
- W4308016422 hasVolume "1" @default.
- W4308016422 isParatext "false" @default.
- W4308016422 isRetracted "false" @default.
- W4308016422 workType "article" @default.