A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot

Ismael Baira Ojeda; Silvia Tolu; Moises Pacheco; David Johan Christensen; Henrik Hautop  Lund

A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot

Ismael Baira Ojeda, Silvia Tolu, Moises Pacheco, David Johan Christensen, Henrik Hautop Lund

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

We scaled up a bio-inspired control architecture for the motor control and motor learning of a real modular robot. In our approach, the Locally Weighted Projection Regression algorithm (LWPR) and a cerebellar microcircuit coexist, forming a Unit Learning Machine. The LWPR optimizes the input space and learns the internal model of a single robot module to command the robot to follow a desired trajectory with its end-effector. The cerebellar microcircuit refines the LWPR output delivering corrective commands. We contrasted distinct cerebellar circuits including analytical models and spiking models implemented on the SpiNNaker platform, showing promising performance and robustness results

Original language	English
Title of host publication	Proceedings of the ICAROB International Conference on Artificial Life and Robotics 2017
Number of pages	4
Publisher	ALife Robotics Co, Ltd.
Publication date	2017
ISBN (Electronic)	9784990835026
Publication status	Published - 2017
Event	2017 International Conference on Artificial Life and Robotics - Seagaia Convention Center, Miyazaki, Japan Duration: 19 Jan 2017 → 22 Jan 2017

Conference

Conference	2017 International Conference on Artificial Life and Robotics
Location	Seagaia Convention Center
Country/Territory	Japan
City	Miyazaki
Period	19/01/2017 → 22/01/2017

Keywords

Motor control
Cerebellum
Machine learning
Modular robot
Internal model
Adaptive behavior

Cite this

@inproceedings{80d5ba526cbb455b9ec055cd6652d193,

title = "A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot",

abstract = "We scaled up a bio-inspired control architecture for the motor control and motor learning of a real modular robot. In our approach, the Locally Weighted Projection Regression algorithm (LWPR) and a cerebellar microcircuit coexist, forming a Unit Learning Machine. The LWPR optimizes the input space and learns the internal model of a single robot module to command the robot to follow a desired trajectory with its end-effector. The cerebellar microcircuit refines the LWPR output delivering corrective commands. We contrasted distinct cerebellar circuits including analytical models and spiking models implemented on the SpiNNaker platform, showing promising performance and robustness results",

keywords = "Motor control, Cerebellum, Machine learning, Modular robot, Internal model, Adaptive behavior",

author = "{Baira Ojeda}, Ismael and Silvia Tolu and Moises Pacheco and Christensen, {David Johan} and Lund, {Henrik Hautop}",

year = "2017",

language = "English",

booktitle = "Proceedings of the ICAROB International Conference on Artificial Life and Robotics 2017",

publisher = "ALife Robotics Co, Ltd.",

note = "2017 International Conference on Artificial Life and Robotics , ICAROB 2017 ; Conference date: 19-01-2017 Through 22-01-2017",

}

Baira Ojeda, I, Tolu, S, Pacheco, M, Christensen, DJ & Lund, HH 2017, A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot. in Proceedings of the ICAROB International Conference on Artificial Life and Robotics 2017. ALife Robotics Co, Ltd., 2017 International Conference on Artificial Life and Robotics , Miyazaki, Japan, 19/01/2017.

A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot. / Baira Ojeda, Ismael; Tolu, Silvia; Pacheco, Moises; Christensen, David Johan; Lund, Henrik Hautop .

Proceedings of the ICAROB International Conference on Artificial Life and Robotics 2017. ALife Robotics Co, Ltd., 2017.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot

AU - Baira Ojeda, Ismael

AU - Tolu, Silvia

AU - Pacheco, Moises

AU - Christensen, David Johan

AU - Lund, Henrik Hautop

PY - 2017

Y1 - 2017

N2 - We scaled up a bio-inspired control architecture for the motor control and motor learning of a real modular robot. In our approach, the Locally Weighted Projection Regression algorithm (LWPR) and a cerebellar microcircuit coexist, forming a Unit Learning Machine. The LWPR optimizes the input space and learns the internal model of a single robot module to command the robot to follow a desired trajectory with its end-effector. The cerebellar microcircuit refines the LWPR output delivering corrective commands. We contrasted distinct cerebellar circuits including analytical models and spiking models implemented on the SpiNNaker platform, showing promising performance and robustness results

AB - We scaled up a bio-inspired control architecture for the motor control and motor learning of a real modular robot. In our approach, the Locally Weighted Projection Regression algorithm (LWPR) and a cerebellar microcircuit coexist, forming a Unit Learning Machine. The LWPR optimizes the input space and learns the internal model of a single robot module to command the robot to follow a desired trajectory with its end-effector. The cerebellar microcircuit refines the LWPR output delivering corrective commands. We contrasted distinct cerebellar circuits including analytical models and spiking models implemented on the SpiNNaker platform, showing promising performance and robustness results

KW - Motor control

KW - Cerebellum

KW - Machine learning

KW - Modular robot

KW - Internal model

KW - Adaptive behavior

M3 - Article in proceedings

BT - Proceedings of the ICAROB International Conference on Artificial Life and Robotics 2017

PB - ALife Robotics Co, Ltd.

T2 - 2017 International Conference on Artificial Life and Robotics

Y2 - 19 January 2017 through 22 January 2017

ER -

A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot

Abstract

Conference

Keywords

Fingerprint

Cite this