A Biologically Constrained Cerebellar Model with Reinforcement Learning for Robotic Limb Control

Simple item page
dc.contributor.authorLiu , Rong
dc.contributor.authorZhang, Qi
dc.contributor.authorChen , Yaru
dc.contributor.authorWang , Jiaxing
dc.contributor.authorYang, Le
dc.date.accessioned2023-11-23T21:00:21Z
dc.date.available2023-11-23T21:00:21Z
dc.date.issued2020
dc.date.updated2023-07-03T04:49:19Z
dc.description.abstractThe cerebellum is known to be critical for accurate adaptive control and motor learning. It has long been recognized that the cerebellum acts as a supervised learning machine. However, recent evidence shows that cerebellum is integral to reinforcement learning. This paper proposes a biologically plausible cerebellar model with reinforcement learning based on the cerebellar neural circuitry to eliminate the need for explicit teacher signals. The learning capacity of cerebellar reinforcement learning is first demonstrated by constructing a simulated cerebellar neural network agent and a detailed model of the human arm and muscle system in the Emergent virtual environment. Next, the cerebellar model is incorporated in both a simulated arm and a Geomagic Touch device to further verify the effectiveness of the cerebellar model in reaching tasks. Results from these experiments indicate that the cerebellar simulation is capable of driving the 'arm plant' to arrive at the target positions accurately. Moreover, by examining the effect of the number of basic units, we find the results are consistent with previous findings that the central nervous system may recruit the muscle synergies to realize motor control. The study described here prompts several hypotheses about the relationship between motor control and learning and may be useful in the development of general-purpose motor learning systems for machines.
dc.identifier.citationLiu R, Zhang Q, Chen Y, Wang J, Yang L (2020). A Biologically Constrained Cerebellar Model with Reinforcement Learning for Robotic Limb Control. IEEE Access. 8. 222199-222210.
dc.identifier.doihttp://doi.org/10.1109/ACCESS.2020.3042994
dc.identifier.issn2169-3536
dc.identifier.urihttps://hdl.handle.net/10092/106508
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.rightsAll rights reserved unless otherwise stated
dc.rights.urihttp://hdl.handle.net/10092/17651
dc.subjectCerebellum
dc.subjectcerebellar model
dc.subjectreinforcement learning
dc.subjectrobotic limb control
dc.subject.anzsrc32 - Biomedical and clinical sciences::3209 - Neurosciences::320903 - Central nervous system
dc.subject.anzsrc40 - Engineering::4003 - Biomedical engineering::400309 - Neural engineering
dc.titleA Biologically Constrained Cerebellar Model with Reinforcement Learning for Robotic Limb Control
dc.typeJournal Article
uc.collegeFaculty of Engineering
uc.departmentElectrical and Computer Engineering
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2020 - IEEE ACCESS - A_Biologically_Constrained_Cerebellar_Model_With_Reinforcement_Learning_for_Robotic_Limb_Control.pdf
Size:
1.16 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download
Collections
Engineering: Journal Articles