Soft robotics

Picture_soft

Description

Although advances in robotics have been undisputed for the past 50 years, robots made of rigid materials still have many limitations. Nowadays, there exists a new trend on biologically inspired robots with “soft” elements that are able to perform tasks which are not available to robots with rigid limbs. This new paradigm is known as Soft Robotics and is presented as an innovation beyond already existing flexible robots or other robots that include variable stiffness actuators (VSA). The technological challenge is in the incorporation of soft links into the robotic structure.

In the case of humanoid robotics, and in comparison with a rigid design, a robot with soft links has the following main advantages: a) simplicity of design, favouring an underactuated architecture without the need of increasing the number of degrees of freedom; b) increased accessibility and adaptability to complex environments, with a postural control that can hardly be implemented in rigid robots; and c) safer interaction with the human and the environment, with a high level of absorption of possible impacts, increasing the stability of the robot.
The main objective of this research topic is the development of a new type of links to create softer humanoid robots that meet the characteristics of simplicity, accessibility and safety. These soft links may be used interchangeably in various limbs of the humanoid robots, like arms, neck and spine, under the constraints of scalability, controllability of their stiffness and integration. To achieve this goal, this research proposes the following sub-objectives: 1) design and development of a prototype of soft link with definition of its material and its actuation system. As a result the electromechanical prototype will be obtained with the premise of easy integration into the rigid structure of a humanoid robot; 2) reconfigurable embedded control system for the soft link, using fractional order and robust control techniques. As a result a controller easily implementable in the humanoid robot TEO will be obtained; 3) substitution (integration) of various links of the life-size humanoid robot TEO by soft links properly scaled to act like arms, neck and spine. As a result a new soft humanoid will be available; and 4) final evaluation of the system, developing new metrics for the analysis of the behaviour of the soft robot, especially in human-robot interaction.

Entries:
An autonomous social robot in fear
IEEE Transactions on Autonomous Mental Development. num. 2 , vol. 5 , pages: 135 – 151 , 2013
A. Castro-Gonzalez M. Malfaz M.A. Salichs
A biologically inspired architecture for an autonomous and social robot
IEEE Transactions on Autonomous Mental Development. num. 3 , vol. 3 , pages: 232 – 246 , 2011
M. Malfaz A. Castro-Gonzalez R. Barber M.A. Salichs
Learning to avoid risky actions
Cybernetics and Systems: An International Journal. . num. 8 , vol. 42 , pages: 636 – 658 , 2011
M. Malfaz M.A. Salichs
Using MUDs as an experimental platform for testing a decision making system for self-motivated autonomous agents
Artificial Intelligence and Simulation of Behaviour Journal (AISBJ).. num. 1 , vol. 2 , pages: 21 – 44 , 2010
M. Malfaz M.A. Salichs
Toma de Decisiones en Robótica
Revista Iberoamericana de Automática e Informática industrial (RIAI). num. 4 , vol. 7 , pages: 5 – 16 , 2010
M.A. Salichs M. Malfaz Javi F. Gorostiza

Entries:
Selection of Actions for an Autonomous Social Robot
International Conference on Social Robotics. Best Student Paper Finalist (http://dx.doi.org/10.1007/978-3-642-17248-9_12), 2010, Singapore, Singapore
A. Castro-Gonzalez M. Malfaz M.A. Salichs
The Use of Emotions in an Autonomous Agent’s Decision Making Process
Ninth International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems (EpiRob09), Venice, Italy
M. Malfaz M.A. Salichs
Learning to deal with objects
ICDL09: The 8th International Conference on Development and Learning , Shanghai, China
M. Malfaz M.A. Salichs
Multimodal Human-Robot Interaction Framework for a Personal Robot
RO-MAN 06: The 15th IEEE International Symposium on Robot and Human Interactive Communication, 2006, Hatfield, United Kingdom
E. Delgado A. Corrales R. Rivas R. Pacheco A.M. Khamis Javi F. Gorostiza M. Malfaz R. Barber M.A. Salichs
Using Emotions for Behaviour-Selection Learning
The 17th European Conference on Artificial Intelligence. ECAI 2006, 2006, Riva del Garda, Italy
M. Malfaz M.A. Salichs
Maggie: A Robotic Platform for Human-Robot Social Interaction
IEEE International Conference on Robotics, Automation and Mechatronics (RAM 2006), 2006, Bangkok, Thailand
E. Delgado A. Corrales R. Rivas R. Pacheco A.M. Khamis Javi F. Gorostiza M. Malfaz R. Barber M.A. Salichs
Emotion-Based Learning of Intrinsically Motivated Autonomous Agents living in a Social World
International Conference on Development and Learning 2006. ICDL5, 2006, Bloomington, In, USA
M. Malfaz M.A. Salichs
Learning Behaviour-Selection Algorithms for Autonomous Social Agents living in a Role-Playing Game
Narrative AI and Games, part of AISB'06: Adaptation in Artificial and Biological Systems. University of Bristol, Bristol, England
M. Malfaz M.A. Salichs
Using Emotions on Autonomous Agents. The Role of Happiness, Sadness and Fear
Integrative Approaches to Machine Consciousness, part of AISB'06: Adaptation in Artificial and Biological Systems, Bristol, England
M. Malfaz M.A. Salichs
A new architecture for autonomous robots based on emotions
Fifth IFAC Symposium on Intelligent Autonomous Vehicles, Lisbon, Portugal
M. Malfaz M.A. Salichs
Design of an Architecture Based on Emotions for an Autonomous Robot
2004 AAAI Spring Symposium, 2004, Stanford, California
M. Malfaz M.A. Salichs

Previous Research topics

next Research topics