FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308784435> ?p ?o ?g. }

• W4308784435 endingPage "58" @default.
• W4308784435 startingPage "42" @default.
• W4308784435 abstract "Humans demonstrate a variety of interesting behavioral characteristics when performing tasks, such as selecting between seemingly equivalent optimal actions, performing recovery actions when deviating from the optimal trajectory, or moderating actions in response to sensed risks. However, imitation learning, which attempts to teach robots to perform these same tasks from observations of human demonstrations, often fails to capture such behavior. Specifically, commonly used learning algorithms embody inherent contradictions between the learning assumptions (e.g., single optimal action) and actual human behavior (e.g., multiple optimal actions), thereby limiting robot generalizability, applicability, and demonstration feasibility. To address this, this paper proposes designing imitation learning algorithms with a focus on utilizing human behavioral characteristics, thereby embodying principles for capturing and exploiting actual demonstrator behavioral characteristics. This paper presents the first imitation learning framework, Bayesian Disturbance Injection (BDI), that typifies human behavioral characteristics by incorporating model flexibility, robustification, and risk sensitivity. Bayesian inference is used to learn flexible non-parametric multi-action policies, while simultaneously robustifying policies by injecting risk-sensitive disturbances to induce human recovery action and ensuring demonstration feasibility. Our method is evaluated through risk-sensitive simulations and real-robot experiments (e.g., table-sweep task, shaft-reach task and shaft-insertion task) using the UR5e 6-DOF robotic arm, to demonstrate the improved characterization of behavior. Results show significant improvement in task performance, through improved flexibility, robustness as well as demonstration feasibility." @default.
• W4308784435 created "2022-11-15" @default.
• W4308784435 creator A5003221518 @default.
• W4308784435 creator A5018794368 @default.
• W4308784435 creator A5042074952 @default.
• W4308784435 creator A5064634210 @default.
• W4308784435 date "2023-01-01" @default.
• W4308784435 modified "2023-09-26" @default.
• W4308784435 title "Bayesian Disturbance Injection: Robust imitation learning of flexible policies for robot manipulation" @default.
• W4308784435 cites W1945123189 @default.
• W4308784435 cites W1968936982 @default.
• W4308784435 cites W1973624057 @default.
• W4308784435 cites W1986014385 @default.
• W4308784435 cites W2036084078 @default.
• W4308784435 cites W2049033813 @default.
• W4308784435 cites W2100993276 @default.
• W4308784435 cites W2101392974 @default.
• W4308784435 cites W2111836555 @default.
• W4308784435 cites W2114355534 @default.
• W4308784435 cites W2129202194 @default.
• W4308784435 cites W2136719407 @default.
• W4308784435 cites W2296673577 @default.
• W4308784435 cites W2337392266 @default.
• W4308784435 cites W2403171414 @default.
• W4308784435 cites W2795577874 @default.
• W4308784435 cites W2962736495 @default.
• W4308784435 cites W2963669336 @default.
• W4308784435 cites W2964319110 @default.
• W4308784435 cites W2968029133 @default.
• W4308784435 cites W3155877522 @default.
• W4308784435 cites W3191504080 @default.
• W4308784435 cites W3199648348 @default.
• W4308784435 cites W3205195733 @default.
• W4308784435 cites W4213438864 @default.
• W4308784435 cites W4280630155 @default.
• W4308784435 doi "https://doi.org/10.1016/j.neunet.2022.11.008" @default.
• W4308784435 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36442373" @default.
• W4308784435 hasPublicationYear "2023" @default.
• W4308784435 type Work @default.
• W4308784435 citedByCount "1" @default.
• W4308784435 countsByYear W43087844352023 @default.
• W4308784435 crossrefType "journal-article" @default.
• W4308784435 hasAuthorship W4308784435A5003221518 @default.
• W4308784435 hasAuthorship W4308784435A5018794368 @default.
• W4308784435 hasAuthorship W4308784435A5042074952 @default.
• W4308784435 hasAuthorship W4308784435A5064634210 @default.
• W4308784435 hasBestOaLocation W43087844352 @default.
• W4308784435 hasConcept C104317684 @default.
• W4308784435 hasConcept C105795698 @default.
• W4308784435 hasConcept C119857082 @default.
• W4308784435 hasConcept C126388530 @default.
• W4308784435 hasConcept C127413603 @default.
• W4308784435 hasConcept C138496976 @default.
• W4308784435 hasConcept C154945302 @default.
• W4308784435 hasConcept C15744967 @default.
• W4308784435 hasConcept C185592680 @default.
• W4308784435 hasConcept C201995342 @default.
• W4308784435 hasConcept C27158222 @default.
• W4308784435 hasConcept C2780451532 @default.
• W4308784435 hasConcept C2780598303 @default.
• W4308784435 hasConcept C33923547 @default.
• W4308784435 hasConcept C41008148 @default.
• W4308784435 hasConcept C55493867 @default.
• W4308784435 hasConcept C63479239 @default.
• W4308784435 hasConcept C77805123 @default.
• W4308784435 hasConcept C90509273 @default.
• W4308784435 hasConcept C97541855 @default.
• W4308784435 hasConceptScore W4308784435C104317684 @default.
• W4308784435 hasConceptScore W4308784435C105795698 @default.
• W4308784435 hasConceptScore W4308784435C119857082 @default.
• W4308784435 hasConceptScore W4308784435C126388530 @default.
• W4308784435 hasConceptScore W4308784435C127413603 @default.
• W4308784435 hasConceptScore W4308784435C138496976 @default.
• W4308784435 hasConceptScore W4308784435C154945302 @default.
• W4308784435 hasConceptScore W4308784435C15744967 @default.
• W4308784435 hasConceptScore W4308784435C185592680 @default.
• W4308784435 hasConceptScore W4308784435C201995342 @default.
• W4308784435 hasConceptScore W4308784435C27158222 @default.
• W4308784435 hasConceptScore W4308784435C2780451532 @default.
• W4308784435 hasConceptScore W4308784435C2780598303 @default.
• W4308784435 hasConceptScore W4308784435C33923547 @default.
• W4308784435 hasConceptScore W4308784435C41008148 @default.
• W4308784435 hasConceptScore W4308784435C55493867 @default.
• W4308784435 hasConceptScore W4308784435C63479239 @default.
• W4308784435 hasConceptScore W4308784435C77805123 @default.
• W4308784435 hasConceptScore W4308784435C90509273 @default.
• W4308784435 hasConceptScore W4308784435C97541855 @default.
• W4308784435 hasFunder F4320321034 @default.
• W4308784435 hasLocation W43087844351 @default.
• W4308784435 hasLocation W43087844352 @default.
• W4308784435 hasLocation W43087844353 @default.
• W4308784435 hasOpenAccess W4308784435 @default.
• W4308784435 hasPrimaryLocation W43087844351 @default.
• W4308784435 hasRelatedWork W2149328105 @default.
• W4308784435 hasRelatedWork W2795551190 @default.
• W4308784435 hasRelatedWork W2890430415 @default.
• W4308784435 hasRelatedWork W2959276766 @default.
• W4308784435 hasRelatedWork W2961085424 @default.

• next