Positioning Control on a Collaborative Robot by Sensor Fusion with Liquid State Machines

Davi Alberto Sala; Valner Joao Brusamarello; Ricardo de Azambuja; Angelo Cangelosi

doi:10.1109/I2MTC.2017.7969728

Positioning Control on a Collaborative Robot by Sensor Fusion with Liquid State Machines

Davi Alberto Sala, Valner Joao Brusamarello, Ricardo de Azambuja, Angelo Cangelosi

Machine Learning and Robotics

Research output: Contribution to conference › Paper › peer-review

Abstract

A positioning controller based on Spiking Neural Networks for sensor fusion suitable to run on a neuromorphic computer is presented in this work. The proposed framework uses the paradigm of reservoir computing to control the collaborative robot BAXTER. The system was designed to work in parallel with Liquid State Machines that performs trajectories in 2D closed shapes. In order to keep a felt pen touching a drawing surface, data from sensors of force and distance are fed to the controller. The system was trained using data from a Proportional Integral Derivative controller, merging the data from both sensors. The results show that the LSM can learn the behavior of a PID controller on different situations.

Original language	English
DOIs	https://doi.org/10.1109/I2MTC.2017.7969728
Publication status	Published - 2017
Event	2017 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2017 - Torino, Italy Duration: 22 May 2017 → 25 May 2017

Conference

Conference	2017 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2017
Country/Territory	Italy
City	Torino
Period	22/05/17 → 25/05/17

Keywords

Robot control
Sensor Fusion
Liquid State Machine
BAXTER robot
PID controller

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/I2MTC.2017.7969728

Cite this

@conference{676dcc81bb1343e6ab6453c1caaadd81,

title = "Positioning Control on a Collaborative Robot by Sensor Fusion with Liquid State Machines",

abstract = "A positioning controller based on Spiking Neural Networks for sensor fusion suitable to run on a neuromorphic computer is presented in this work. The proposed framework uses the paradigm of reservoir computing to control the collaborative robot BAXTER. The system was designed to work in parallel with Liquid State Machines that performs trajectories in 2D closed shapes. In order to keep a felt pen touching a drawing surface, data from sensors of force and distance are fed to the controller. The system was trained using data from a Proportional Integral Derivative controller, merging the data from both sensors. The results show that the LSM can learn the behavior of a PID controller on different situations.",

keywords = "Robot control, Sensor Fusion, Liquid State Machine, BAXTER robot, PID controller",

author = "Sala, {Davi Alberto} and Brusamarello, {Valner Joao} and {de Azambuja}, Ricardo and Angelo Cangelosi",

year = "2017",

doi = "10.1109/I2MTC.2017.7969728",

language = "English",

note = "2017 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2017 ; Conference date: 22-05-2017 Through 25-05-2017",

}

TY - CONF

T1 - Positioning Control on a Collaborative Robot by Sensor Fusion with Liquid State Machines

AU - Sala, Davi Alberto

AU - Brusamarello, Valner Joao

AU - de Azambuja, Ricardo

AU - Cangelosi, Angelo

PY - 2017

Y1 - 2017

N2 - A positioning controller based on Spiking Neural Networks for sensor fusion suitable to run on a neuromorphic computer is presented in this work. The proposed framework uses the paradigm of reservoir computing to control the collaborative robot BAXTER. The system was designed to work in parallel with Liquid State Machines that performs trajectories in 2D closed shapes. In order to keep a felt pen touching a drawing surface, data from sensors of force and distance are fed to the controller. The system was trained using data from a Proportional Integral Derivative controller, merging the data from both sensors. The results show that the LSM can learn the behavior of a PID controller on different situations.

AB - A positioning controller based on Spiking Neural Networks for sensor fusion suitable to run on a neuromorphic computer is presented in this work. The proposed framework uses the paradigm of reservoir computing to control the collaborative robot BAXTER. The system was designed to work in parallel with Liquid State Machines that performs trajectories in 2D closed shapes. In order to keep a felt pen touching a drawing surface, data from sensors of force and distance are fed to the controller. The system was trained using data from a Proportional Integral Derivative controller, merging the data from both sensors. The results show that the LSM can learn the behavior of a PID controller on different situations.

KW - Robot control

KW - Sensor Fusion

KW - Liquid State Machine

KW - BAXTER robot

KW - PID controller

U2 - 10.1109/I2MTC.2017.7969728

DO - 10.1109/I2MTC.2017.7969728

M3 - Paper

T2 - 2017 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2017

Y2 - 22 May 2017 through 25 May 2017

ER -

Positioning Control on a Collaborative Robot by Sensor Fusion with Liquid State Machines

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this