Adaptive neural network dynamic surface control for musculoskeletal robots

Jantsch, Michael; Wittmeier, Steffen; Dalamagkidis, Konstantinos; Herrmann, Guido; Knoll, Alois

doi:10.1109/cdc.2014.7039460

Cited by 4 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A generic model for the class of musculoskeletal robots was presented in [1], proposing a subdivision into skeletal dynamics, muscle dynamics and muscle kinematics. The resulting submodels are presented in the following.…”

Section: Modelingmentioning

confidence: 99%

“…In the presence of spherical joints this definition can be extended by introducing (2), such that [1]:…”

Section: B Muscle Kinematicsmentioning

confidence: 99%

“…where the system state is given by the actuator velocity, the system input is the actuator voltage v A and f 2 , and g 2 are defined as possibly non-linear functions [1]. More elaborate models include the motor current as a system state which is neglected in this work.…”

Section: Muscle Dynamicsmentioning

confidence: 99%

“…For a detailed derivation as well as a proof of stability the reader is referred to [1]. In the following, this controller is introduced shortly:…”

Section: Dynamic Surface Controlmentioning

confidence: 99%

“…In this work, we compare the feedback control technique of Computed Force Control (CFC), which has been developed for tendon-driven robots without additional compliance and well defined muscle routing [6], [7], to a novel control approach based on Dynamic Surface Control (DSC), an extension to backstepping, which takes inspiration from [8] and was presented in [1]. The Anthrob serves as an ideal testbed for those control strategies, due to its sensorization and relatively simple skeletal kinematics.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Adaptive neural network Dynamic Surface Control: An evaluation on the musculoskeletal robot Anthrob

Jantsch

Wittmeier

Dalamagkidis

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-The soft robotics approach is widely considered to enable robots in the near future to leave their cages and move freely in our modern homes and manufacturing sites. Musculoskeletal robots are such soft robots which feature passively compliant actuation, while leveraging the advantages of tendon-driven systems. Even though these robots have been intensively researched within the last decade, high-performance feedback control laws have only very recently been developed. In [1], a controller was developed utilizing Dynamic Surface Control (DSC), an extension to backstepping, with an adaptive neural network compensator for joint as well as muscle friction. We compare these novel control strategies to Computed Force Control (CFC), an existing technique from the field of tendondriven control, yielding highly improved trajectory tracking. The musculoskeletal robot Anthrob [2] serves as a benchmark.

show abstract

Section: Modelingmentioning

confidence: 99%

“…In the presence of spherical joints this definition can be extended by introducing (2), such that [1]:…”

Section: B Muscle Kinematicsmentioning

confidence: 99%

Section: Muscle Dynamicsmentioning

confidence: 99%

“…For a detailed derivation as well as a proof of stability the reader is referred to [1]. In the following, this controller is introduced shortly:…”

Section: Dynamic Surface Controlmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Adaptive neural network Dynamic Surface Control: An evaluation on the musculoskeletal robot Anthrob

Jantsch

Wittmeier

Dalamagkidis

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

Hebbian learning for online prediction, neural recall and classical conditioning of anthropomimetic robot arm motions

Feldotto¹,

Walter²,

Röhrbein³

et al. 2018

Bioinspir. Biomim.

View full text Add to dashboard Cite

Classical conditioning plays a vital role in learning in every mammal. It is based on unsupervised neural learning embodied in a physical body that is in continuous interaction with the environment. Embedding the hierarchical temporal memory (HTM) in the closed loop of the sensorimotor space of a Myorobotics tendon-driven robotic arm we demonstrate learning, prediction and control of biomimetic body motions. Experiments finally lead to conditioned reactions in natural interaction with a human partner. The HTM is able to learn arm movements generated by interaction with a human partner in a short time. It predicts future positions in different time scales up to seconds in advance. Closing the loop we utilize HTM predictions for motor control. Hereby learned motions are recalled from synaptic connections proactively continuing motion execution. Association, prediction and control are required by the HTM for conditioning according to Pavlov: neutral stimuli get associated with motions, and after learning sensor impulses can trigger single arm lifting motions. Hereby, both the motions and the stimuli are learned from the environment and get associated efficiently. We can demonstrate high biological plausibility as for example even input variations result in similar variations in the action output. The robotic system consisting of biologically-derived hardware and software components utilizes only unsupervised Hebbian learning to act autonomously. Learning is executed in real time, can handle natural variations of human motions and takes morphologically plausible sensor input into account. The setup is fully scalable due to its modularity. Hereby, novel applications for the HTM are opened: it can be used in musculoskeletal robot control scenarios and robots being able to interactively learn from human partners and the environment.

show abstract

Sliding Muscle Surface Control of the Muscle-Driven Musculoskeletal System

Fan

Yuan

et al. 2022

2022 International Conference on Automation, Robotics and Computer Engineering (ICARCE)

View full text Add to dashboard Cite

Adaptive neural network dynamic surface control for musculoskeletal robots

Cited by 4 publications

References 20 publications

Adaptive neural network Dynamic Surface Control: An evaluation on the musculoskeletal robot Anthrob

Adaptive neural network Dynamic Surface Control: An evaluation on the musculoskeletal robot Anthrob

Hebbian learning for online prediction, neural recall and classical conditioning of anthropomimetic robot arm motions

Sliding Muscle Surface Control of the Muscle-Driven Musculoskeletal System

Contact Info

Product

Resources

About