Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal Robot

This article presents the mechanical design of Otto, a lightweight 8-degrees-of-freedom (8-DoF) quadrupedal robot employing series elastic actuators, and a training framework for learning locomotion control policies in simulation using reinforcement learning (RL). Otto's design differs from typ...

Full description

Saved in:
Bibliographic Details
Main Authors: Antonello Scaldaferri, Simone Tolomei, Francesco Iotti, Paolo Gambino, Michele Pierallini, Franco Angelini, Manolo Garabini
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Industrial Electronics Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10988638/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849761236237942784
author Antonello Scaldaferri
Simone Tolomei
Francesco Iotti
Paolo Gambino
Michele Pierallini
Franco Angelini
Manolo Garabini
author_facet Antonello Scaldaferri
Simone Tolomei
Francesco Iotti
Paolo Gambino
Michele Pierallini
Franco Angelini
Manolo Garabini
author_sort Antonello Scaldaferri
collection DOAJ
description This article presents the mechanical design of Otto, a lightweight 8-degrees-of-freedom (8-DoF) quadrupedal robot employing series elastic actuators, and a training framework for learning locomotion control policies in simulation using reinforcement learning (RL). Otto's design differs from typical 12-DoF quadrupeds by lacking hip adduction–abduction DoF. This reduces the robot's cost and weight and increases complexity for tasks involving base rotation and angular twist following. The elastic elements at the joints improve compliance, energy efficiency, safety, and stability, increase robustness, and reduce damage to robot hardware components. Our locomotion control approach leverages RL to optimize policies in simulation, allowing stable and efficient movement despite mechanical constraints, i.e., an 8-DoF quadrupedal robot. Through extensive simulation training, leveraging highly parallel Graphics Processing Unit (GPU)-accelerated robotic simulators, we ensure the policy is well-suited for deployment in real-world scenarios, where accurate motion control is critical for performance. The trained policy is then transferred to the physical robot platform. We demonstrate its effectiveness in various tasks and real-life scenarios with varying payloads and terrains, and compare it with a state-of-the-art model-based method. The results show that Otto, equipped with our RL-based locomotion control, achieves robust performance, compensating for the reality gap and managing the reduced DoF available in Otto.
format Article
id doaj-art-230e4898006b4e7bbf13806ee1d2b714
institution DOAJ
issn 2644-1284
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Industrial Electronics Society
spelling doaj-art-230e4898006b4e7bbf13806ee1d2b7142025-08-20T03:06:05ZengIEEEIEEE Open Journal of the Industrial Electronics Society2644-12842025-01-01682083910.1109/OJIES.2025.356711210988638Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal RobotAntonello Scaldaferri0https://orcid.org/0000-0002-7146-1635Simone Tolomei1https://orcid.org/0009-0006-7928-3518Francesco Iotti2https://orcid.org/0009-0000-9257-6231Paolo Gambino3https://orcid.org/0009-0000-4204-4413Michele Pierallini4https://orcid.org/0000-0003-0547-2747Franco Angelini5https://orcid.org/0000-0003-2559-9569Manolo Garabini6https://orcid.org/0000-0002-5873-3173Centro di Ricerca “Enrico Piaggio” and Dipartimento di Ingegneria dell'Informazione, Università di Pisa, Pisa, ItalyCentro di Ricerca “Enrico Piaggio” and Dipartimento di Ingegneria dell'Informazione, Università di Pisa, Pisa, ItalyCentro di Ricerca “Enrico Piaggio” and Dipartimento di Ingegneria dell'Informazione, Università di Pisa, Pisa, ItalyCentro di Ricerca “Enrico Piaggio” and Dipartimento di Ingegneria dell'Informazione, Università di Pisa, Pisa, ItalyCentro di Ricerca “Enrico Piaggio” and Dipartimento di Ingegneria dell'Informazione, Università di Pisa, Pisa, ItalyCentro di Ricerca “Enrico Piaggio” and Dipartimento di Ingegneria dell'Informazione, Università di Pisa, Pisa, ItalyCentro di Ricerca “Enrico Piaggio” and Dipartimento di Ingegneria dell'Informazione, Università di Pisa, Pisa, ItalyThis article presents the mechanical design of Otto, a lightweight 8-degrees-of-freedom (8-DoF) quadrupedal robot employing series elastic actuators, and a training framework for learning locomotion control policies in simulation using reinforcement learning (RL). Otto's design differs from typical 12-DoF quadrupeds by lacking hip adduction–abduction DoF. This reduces the robot's cost and weight and increases complexity for tasks involving base rotation and angular twist following. The elastic elements at the joints improve compliance, energy efficiency, safety, and stability, increase robustness, and reduce damage to robot hardware components. Our locomotion control approach leverages RL to optimize policies in simulation, allowing stable and efficient movement despite mechanical constraints, i.e., an 8-DoF quadrupedal robot. Through extensive simulation training, leveraging highly parallel Graphics Processing Unit (GPU)-accelerated robotic simulators, we ensure the policy is well-suited for deployment in real-world scenarios, where accurate motion control is critical for performance. The trained policy is then transferred to the physical robot platform. We demonstrate its effectiveness in various tasks and real-life scenarios with varying payloads and terrains, and compare it with a state-of-the-art model-based method. The results show that Otto, equipped with our RL-based locomotion control, achieves robust performance, compensating for the reality gap and managing the reduced DoF available in Otto.https://ieeexplore.ieee.org/document/10988638/Articulated soft robotslocomotion controlquadrupedal robotsreinforcement learning (RL)sim2real transfer
spellingShingle Antonello Scaldaferri
Simone Tolomei
Francesco Iotti
Paolo Gambino
Michele Pierallini
Franco Angelini
Manolo Garabini
Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal Robot
IEEE Open Journal of the Industrial Electronics Society
Articulated soft robots
locomotion control
quadrupedal robots
reinforcement learning (RL)
sim2real transfer
title Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal Robot
title_full Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal Robot
title_fullStr Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal Robot
title_full_unstemmed Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal Robot
title_short Otto—Design and Control of an 8-DoF SEA-Driven Quadrupedal Robot
title_sort otto x2014 design and control of an 8 dof sea driven quadrupedal robot
topic Articulated soft robots
locomotion control
quadrupedal robots
reinforcement learning (RL)
sim2real transfer
url https://ieeexplore.ieee.org/document/10988638/
work_keys_str_mv AT antonelloscaldaferri ottox2014designandcontrolofan8dofseadrivenquadrupedalrobot
AT simonetolomei ottox2014designandcontrolofan8dofseadrivenquadrupedalrobot
AT francescoiotti ottox2014designandcontrolofan8dofseadrivenquadrupedalrobot
AT paologambino ottox2014designandcontrolofan8dofseadrivenquadrupedalrobot
AT michelepierallini ottox2014designandcontrolofan8dofseadrivenquadrupedalrobot
AT francoangelini ottox2014designandcontrolofan8dofseadrivenquadrupedalrobot
AT manologarabini ottox2014designandcontrolofan8dofseadrivenquadrupedalrobot