Matches in SemOpenAlex for { <https://semopenalex.org/work/W4364302709> ?p ?o ?g. }
- W4364302709 endingPage "36040" @default.
- W4364302709 startingPage "36029" @default.
- W4364302709 abstract "The lower-limb exoskeleton for human performance augmentation (LEHPA) in sensitivity amplification control (SAC) is vulnerable to model parameter uncertainties and unmodeled dynamics due to its large sensitivity to external disturbances. This paper proposes sensitivity adaptation based on deep reinforcement learning (SADRL) to reduce the dependence on the model accuracy and tackle the ever-changing human-exoskeleton interaction (HEI) dynamics by interpreting the sensitivity adjustment as a Markov Decision Process (MDP). The agent learns an appropriate sensitivity for each exoskeleton state. To train the control policy safely and efficiently, a multibody simulation environment is created to implement the training process, accompanied by a novel hybrid inverse-forward dynamics simulation method to carry out the simulation. For comparison purposes, the SAC controller is introduced as a benchmark. A novel performance evaluation method based on the HEI forces at the back, thighs, and shanks is proposed to evaluate the control effect of the trained SADRL controller quantitatively. The SADRL controller is compared with the SAC controller at five specified walking speeds, resulting in a lumped HEI force ratio of 0.54. The total decrease of HEI forces demonstrates the superior control effect of the SADRL strategy." @default.
- W4364302709 created "2023-04-12" @default.
- W4364302709 creator A5015729655 @default.
- W4364302709 creator A5020249061 @default.
- W4364302709 creator A5048379858 @default.
- W4364302709 creator A5058394999 @default.
- W4364302709 creator A5072007157 @default.
- W4364302709 creator A5080000298 @default.
- W4364302709 date "2023-01-01" @default.
- W4364302709 modified "2023-10-16" @default.
- W4364302709 title "Sensitivity Adaptation of Lower-Limb Exoskeleton for Human Performance Augmentation Based on Deep Reinforcement Learning" @default.
- W4364302709 cites W1996907893 @default.
- W4364302709 cites W2034922363 @default.
- W4364302709 cites W2066275561 @default.
- W4364302709 cites W2070054839 @default.
- W4364302709 cites W2081254081 @default.
- W4364302709 cites W2138300314 @default.
- W4364302709 cites W2145339207 @default.
- W4364302709 cites W2182339254 @default.
- W4364302709 cites W2207129347 @default.
- W4364302709 cites W2222399534 @default.
- W4364302709 cites W2276448469 @default.
- W4364302709 cites W2326141327 @default.
- W4364302709 cites W2414517470 @default.
- W4364302709 cites W2525083240 @default.
- W4364302709 cites W2561015862 @default.
- W4364302709 cites W2626078568 @default.
- W4364302709 cites W2729893323 @default.
- W4364302709 cites W2756487600 @default.
- W4364302709 cites W2796290181 @default.
- W4364302709 cites W2807720470 @default.
- W4364302709 cites W2808056355 @default.
- W4364302709 cites W2885815163 @default.
- W4364302709 cites W2899718839 @default.
- W4364302709 cites W2907645993 @default.
- W4364302709 cites W2911087563 @default.
- W4364302709 cites W2913889693 @default.
- W4364302709 cites W2949794134 @default.
- W4364302709 cites W2963177351 @default.
- W4364302709 cites W2964114602 @default.
- W4364302709 cites W2981479926 @default.
- W4364302709 cites W3039737909 @default.
- W4364302709 cites W3041481682 @default.
- W4364302709 cites W3100366369 @default.
- W4364302709 cites W3100789280 @default.
- W4364302709 cites W3100958881 @default.
- W4364302709 cites W3101808543 @default.
- W4364302709 cites W3104876774 @default.
- W4364302709 cites W3104883169 @default.
- W4364302709 cites W3105609823 @default.
- W4364302709 cites W3152878473 @default.
- W4364302709 cites W3206620955 @default.
- W4364302709 cites W4205430897 @default.
- W4364302709 cites W4213104648 @default.
- W4364302709 cites W4307479981 @default.
- W4364302709 doi "https://doi.org/10.1109/access.2023.3265895" @default.
- W4364302709 hasPublicationYear "2023" @default.
- W4364302709 type Work @default.
- W4364302709 citedByCount "1" @default.
- W4364302709 crossrefType "journal-article" @default.
- W4364302709 hasAuthorship W4364302709A5015729655 @default.
- W4364302709 hasAuthorship W4364302709A5020249061 @default.
- W4364302709 hasAuthorship W4364302709A5048379858 @default.
- W4364302709 hasAuthorship W4364302709A5058394999 @default.
- W4364302709 hasAuthorship W4364302709A5072007157 @default.
- W4364302709 hasAuthorship W4364302709A5080000298 @default.
- W4364302709 hasBestOaLocation W43643027091 @default.
- W4364302709 hasConcept C111919701 @default.
- W4364302709 hasConcept C120665830 @default.
- W4364302709 hasConcept C121332964 @default.
- W4364302709 hasConcept C127413603 @default.
- W4364302709 hasConcept C13280743 @default.
- W4364302709 hasConcept C133731056 @default.
- W4364302709 hasConcept C139807058 @default.
- W4364302709 hasConcept C146549078 @default.
- W4364302709 hasConcept C154945302 @default.
- W4364302709 hasConcept C185798385 @default.
- W4364302709 hasConcept C187523126 @default.
- W4364302709 hasConcept C203479927 @default.
- W4364302709 hasConcept C205649164 @default.
- W4364302709 hasConcept C21200559 @default.
- W4364302709 hasConcept C24326235 @default.
- W4364302709 hasConcept C2775924081 @default.
- W4364302709 hasConcept C39920418 @default.
- W4364302709 hasConcept C41008148 @default.
- W4364302709 hasConcept C44154836 @default.
- W4364302709 hasConcept C47446073 @default.
- W4364302709 hasConcept C6557445 @default.
- W4364302709 hasConcept C74650414 @default.
- W4364302709 hasConcept C86803240 @default.
- W4364302709 hasConcept C97541855 @default.
- W4364302709 hasConcept C98045186 @default.
- W4364302709 hasConceptScore W4364302709C111919701 @default.
- W4364302709 hasConceptScore W4364302709C120665830 @default.
- W4364302709 hasConceptScore W4364302709C121332964 @default.
- W4364302709 hasConceptScore W4364302709C127413603 @default.
- W4364302709 hasConceptScore W4364302709C13280743 @default.
- W4364302709 hasConceptScore W4364302709C133731056 @default.