Link: http://www.cs.cmu.edu/~cga/humanoids16workshop/

Abstract

This will be the 2nd workshop entitled “Can we build Baymax?”. The 1st workshop was held at Humanoids 2015 in Korea. Baymax is the soft humanoid character in Disney's feature animation "Big Hero 6." It is a healthcare robot with an inflatable body, capable of walking, bumping into surrounding objects and physically interacting with people. However, in the real world, it is not an easy robot to build. For the realization of this robot, awareness of the environment, especially a sense of touch and vision, is very important. Covering robots with soft material to protect both humans and the robot is also required. Integrating these features into actual hardware using reasonable fabrication methods is a challenging task. In this workshop, we will discuss topics related to building robots like Baymax with special features including but not limited to implementation of skin sensors, methods to protect humans and robots, and fabrication of soft skin for humanoids.

url: https://iros2016torquecontrolledactuation.wordpress.com/

Objectives and Motivation
Research on legged robots has focused mainly on reliable perception, planning, and control methods for completing challenging tasks. The DARPA Robotics Challenge 2015 showed that when the tether is removed, legged robots may inevitable fall over during a task in an unstructured environment; either when they walk on a flat or rough terrain, or when they are cutting a wall with a drill, opening a door, and turning a valve. In a lot of cases if a legged robot falls over, it may end up with a serious damage. If not, the robot in a real world scenario should stand up and complete the task. Being able to detect such a fall, apply the appropriate actions to prevent a big damage both on the robot and the environment around it, and recover if possible, are necessary for a real world application, where legged robots will need to deal with even rougher terrain and more complicated manipulation tasks under significant uncertainty either for static or dynamically changing environments.
This workshop will provide a platform for researchers from all areas in robotics to disseminate and exchange ideas, evaluating their advantages and drawbacks. This will include from the mechanical design and biomechanics to the perception, planning, and whole-body control methods on real robot and simulations for fall detection, damage prevention, and recovery actions in a falling over scenario. The aim is to foster collaboration among researchers that are working on legged robots to advance the very limited state of the art work in this area.
We propose a half-day workshop consisting of a mixture of presentations on topics including design, sensing, perception, planning, biomechanics, and motion generation for various types of legged robots designed to work indoors and outdoors. To stimulate interaction, we will also organize a poster/video session to encourage the participation of young researchers and promote the discussion with the speakers and the audience. Moreover we will allocate adequate time for questions and discussion to make the workshop as interactive as possible.
Workshops as the IROS’15 “The Path to Success: Failures in Real Robots”, the Humanoids “Workshop on Humanoid Soccer Robots”, and the ICRA’15 “Dynamic Locomotion and Balancing of Humanoids: State of the Art and Challenges” were focused more on analyzing the cause of a fall, the fall recovery for toy-robots, and balancing correspondingly. The proposed workshop will focus on the action to follow an inevitable fall after it has been detected. Given that the DRC this year focused on legged locomotion and a large number of falls took place, we believe that such a workshop will attract a large number of participants and promote interaction and collaboration.

Topics of Interest:

• mechanical design for a falling scenario and soft robotics
• robotic simulation for falling
• exteroceptive and proprioceptive perception for fall detection
• fall planning and recovery
• damage prevention control
• collision avoidance and self-collision avoidance
• reactive behaviors and emergency behaviors
• biomechanical analysis of human fall detection
• whole-body control fall/recovery strategies

Support of an IEEE RAS Technical Committee
This proposed workshop is supported by:
1) IEEE RAS Technical Committee on Humanoids Robotics as confirmed as confirmed by the Technical Committee co-chairs Aude Billard, Eiichi Yoshida, and James Kuffner.
2) IEEE RAS Technical Committee on Algorithms for Planning and Control of Robot Motion as confirmed by the Technical Committee co-chairs Fabrizio Flacco, Sertac Karaman, Hanna Kurniawati, and Lydia Tapia.
3) IEEE RAS Technical Committee on Whole-Body Control as confirmed by the Tehnical Committee co-chairs Federico Moro, Luis Sentis, and Jaeheung Park.

Workshop Overview

Soft robotics design, either due to the hardware or control, has led to the emergence of several promising applications in which humans come in contact or coexist with robots or assistive devices to achieve a certain task in unstructured environments. In such applications, the establishment of a suitable level of shared autonomy between the robot and the user has shown to be a key factor to demonstrate versatile and stable human-robot-environment interactions. This, however, requires that the robot functionalities are appropriately associated with the human motor behavior and intention. Indeed, this workshop aims at discussing the pertinence and the feasibility of the establishment of human-robot interfaces to enhance the robot or assistive device’s physical interaction performance. This goal will be achieved by - bringing together researchers working on the relevant fields and tackling challenges that lay ahead for achieving an intuitive, safe, and stable human-robot interface, and - evaluating the underlying concepts and tools while targeting real-world applications such as rehabilitation robotics, human-robot cooperation, teleoperation, etc. It is as well expected to encourage synergistic collaborations among researchers working on different areas of human-robot interfaces and physical interaction to extend views toward required key technologies, in terms of hardware or software, as a take-home message.

Scope and Topics

- Human-in-the-loop Control of Robotic Systems

- Active Exoskeletons and Assistive Devices for Rehabilitation and Power Augmentation

- Co-operative and Collaborative Human-Machine Systems for Manufacturing

- Characterization of Variable Impedance to Enhance Human-Robot Interaction

-Learning Human Sensorimotor Control for Advanced Human-to-Robot Skill Transfer

- Mutual Learning and Adaptation in Human-Robot Systems

- Stability and Robustness of Human-Robot Interfaces

- Objective Measures: How to Quantify Efficacy, Safety and Intuitiveness in Human-Robot Interaction?

- Novel Sensors and Actuators for Advanced Human-Robot Interaction Control

- Case Studies, Experiments, Ethics and Outreach

Speakers http://robotics.ozyegin.edu.tr/icra16workshop/speakers/

Organizers http://robotics.ozyegin.edu.tr/icra16workshop/organizers/

IEEE-RAS Technical Committee support http://robotics.ozyegin.edu.tr/icra16workshop/support-letters/

url: http://www.neuralrehabilitation.org/benchmarking/workshop-humanoids-2015/

url: http://www.cs.cmu.edu/~cga/humanoids15workshop/

Abstract:

Humanoid robots need to reliably locomote and manipulate continuously in very uncertain environments.  For completing challenging tasks, sensor data need to be used for estimating the robot’s own state with respect to the environment.  Simultaneous localization and mapping (SLAM) has been studied a lot over the last few years but still there is not a commonly accepted solution to the problem, especially since different tasks may require different estimation accuracy.  From one side, exteroception, like the visual perception, has been used to build either sparse or dense maps of the environment, localizing continuously the robot in it, but with potentially big errors and drifts over time.  From the other side, proprioception, like the robot kinematics, could provide a more accurate state estimation of the joints but under some assumptions, for instance that the robot maintains either non-slipping or static contacts with the environment.  Sensor data fusion is required for a more accurate and continuous state estimation, in order to allow a reliable whole-body control.  The problem becomes even more challenging when the sensors not only provide uncertain measurements but also provide them in an non-continuous base.

This workshop will provide a platform for researchers working on SLAM from the proprioception and/or exteroception point of view, to exchange ideas on sensor data fusion methods for a better state estimation.  The aim is to foster collaboration among researchers that are working on SLAM and sensor fusion, either they work on the control, the planning, or the perception side of the problem, to advance the state of the art in robot locomotion and manipulation in challenging and uncertain environments.  We propose a full day workshop consisting of a mixture of presentations on topics including SLAM, sensing, and data fusion with the goal of applying them to humanoids. Moreover we will allocate adequate time for questions and discussion to make the workshop as interactive as possible.

Keywords: data fusion; state estimation; whole-body control; integration of perception and control.

Program:

List of speakers:

Abstract:

Invited Speakers

Support
This proposed workshop is supported by:

https://iros2015wsperceptionandplanning.wordpress.com

This workshop is organized to serve three goals with respect to humanoid locomotion and balancing. The first goal is to bring together the researchers working on humanoid locomotion and balancing to present and discuss the recent advancement of their recent work. A lot of novel advancements are, for example, expected to be made and demonstrated by the groups from European projects and teams participating in DRC. The timing of this workshop is perfectly aligned with the DRC finals, thus provides a good opportunity to present the very recent developments in the area of humanoid locomotion in more realistic conditions.  

The second goal is to introduce the up-to-date findings from biomechanical studies of human movement in order to understand better the biological motor control skills, and most interestingly, to propose mathematical models of human locomotion. This will provide insights for developing new control algorithms for controlling and optimizing the walking of humanoids more effectively.

The third goal is to inspire the integration of control principles and algorithms developed in actively powered humanoids and the passive dynamic walkers, and therefore, to bridge the gap between these two research paradigms. It is to be foreseen that collaboration among researchers from these two paradigms will emerge and the complementary advantages of these two control methodologies will eventually be adopted and integrated to create a more robust and efficient dynamic locomotion for humanoid robots.

As a follow-up event after the workshop, the preparation of a special issue for a prestigious robotics journal will be started shortly. To conclude, with this workshop we aim at:

• Demonstrating the recent developments in humanoid locomotion in real world scenarios (including the effort made inside DRC), which provides the opportunity of presenting and discussing recent results in this cutting edge and challenging area of  humanoid robotics research.
• Advancing the state of the art in humanoid locomotion and balance control by fostering collaboration among researchers working on different areas of locomotion control, e.g. powered bipeds and passive walkers, classical position controlled humanoids and those powered by torque/impedance controlled actuators and/or intrinsically elastic actuators.

A full day workshop is proposed which will cover a broad spectrum of presentations related to the scientific developments in the locomotion and balancing of humanoids. The scientific and technological topics of the workshop are summarized as follows:

1. Humanoid balance control and push recovery
2. Locomotion in unstructured terrains
3. Adaptive/Reactive bipedal gait generators
4. Impedance regulation in locomotion
5. Compliant and torque control based locomotion
6. Gait reflexive behaviours
7. Human inspired locomotion gaits
8. Adaptive path and footstep planning
9. Passive and under-actuated locomotion
10. Affordances for locomotion and balance control

Timetable:

08:30 – 10:00 3 talks
10:00 – 10:30 coffee break
10:30 – 12:00 3 talks
12:00 – 13:30 Lunch
13:30 – 14:30 2 talks
14:30 – 14:40 poster teaser
14:40 – 15:00 poster session
15:00 – 15:30 coffee break
15:30 – 15:50 poster session
15:50 – 16:50 2 talks
16:50 – 17:00 Final discussion

List of confirmed speakers:

1. Baek-Kyu Cho (Kookmin University, South Korea)
   "Bipedal Walking in Team DRC-Hub"
2. Patrick Wensing (Ohio State University (OSU), USA)
   "Exploiting SLIP-Based Models to Maintain Dynamic Balance"
3. Tomomichi Sugihara (Osaka University, Japan)
   "To Combine the Stand-still and Maneuvering"
4. Kenji Hashimoto (Waseda University, Japan)
   "Waseda's Biped Walking Technology on Rough Terrain"
5. Rong Xiong (Zhejiang University, China)
   "Torque Controlled Jumping Robot: Modelling and Control Strategies"
6. Olivier Stasse (LAAS-CNRS, Toulouse, France)
   "Vision-guided Motion Primitives for Humanoid Reactive Walking"
7. Katja Mombaur (University of Heidelberg, Germany)
   "Using Model-based Optimization to Improve Stability of Dynamic Humanoid Locomotion"
8. Art Kuo (University of Michigan, USA)
   "Control of Dynamic Bipedal Locomotion"  
9. Zhibin Li (Istituto Italiano di Tecnologia (IIT), Italy)
   "Humanoid Balance Recovery with the Use of Human Footwear"
10. Thomas Buschmann (Technical University of Munich (TUM), Germany / Google, USA)
    "Towards Flexible and Robust Biped Walking Control"

Poster and Live Demo Session:

1. Oscar E. Ramos (Duke University, USA)
   "Generalizations of the Capture Point to Nonlinear Curves on Uneven Terrain"
2. Nicolas Van der Noot (Universite catholique de Louvain (UCL), Belgium / EPFL, Switzerland)
   "Porting Reflex-Based Muscles Control to Real Humanoid Robots"
3. Vittorio Lippi (Universitätsklinik Freiburg, Germany)
   "Coupling Forces in Human-like Posture Control"
4. Cenk Oguz Saglam (University of California, Santa Barbara, USA)
   "Quantification and Optimization of Bipedal Locomotion on Rough Terrain"
5. Mingguo Zhao (Tsinghua University, China)
   "A Simple Biped Dynamics Walking Method Based on Hip Actuation"
   with real demo of powered passive dynamic walker

CONTENT:

With growing research interest in humanoid robotics, robots have become increasingly proficient in performing many different, non-trivial tasks, such as running, jumping, climbing stairs, and manipulating objects. In most cases, however, each of these tasks is addressed individually, and this imposes a fundamental limitation on the use of robots in the real world. While humans may occasionally be outperformed by robots in a single task, they are vastly more capable of adapting and combining behaviors to solve multiple different tasks. This flexibility allows humans to generalize their knowledge, and to successfully perform tasks that they have never explicitly faced before. This also opens the door for simultaneous execution of multiple tasks. To address these constraints, Whole-Body Control Systems have been proposed as a promising research direction. They represent a wide range of complex movement skills in the form of low-dimensional task descriptors which are projected on to the robot’s actuators, thereby exploiting the full capabilities of the entire body.

Until recent years, limitations on hardware relegated Whole-Body Control to almost purely theoretical research. Recently a growing number of experimental platforms have become available (in particular torque-controlled humanoids). This new opportunity has triggered the deployment on real robots of the theoretical outcomes of research in the field. This is backed up by a number of new research projects addressing issues in this domain, including WALK-MAN, CoDyCo, KoroiBot, and the Darpa Robotic Challenge (DRC) which presents a more application-oriented development of these methods.

This full-day workshop and special issue aim to bring together the main actors in the field to:

• disseminate knowledge of the rapidly evolving state-of-the-art in Whole-Body Control, with dual goals of understanding the new theoretical studies and applying this experience to real robots, with particular emphasis on the latter;
• encourage discussion among speakers, and between speakers and attendees to the workshop to understand better what are the current main problems that still need to be solved to attain the target of having robots capable of moving in and interacting with the real world;
• trigger new collaborations among researchers in the field for a faster and more effective development of Whole-Body Control methods to be applied on real robots.

Contributors are invited to discuss their hands-on experience on the Whole-Body Control of real robots. The platforms that are currently being used by the WS invited speakers/organizers in their research consist of 8 different humanoid robots (ASIMO, ATLAS, COMAN, HRP-2, iCub, TORO, Sarcos robot, Valkyrie). This number grows to at least 16 if we also consider robots with which the speakers have had previous research experience. From this list at least 4 will be participants in the DRC, whose finals will take place in 2015.

LIST OF TOPICS:

The focus will be on real experiences in Whole-Body Control with real robots. The WS and SI will cover, but not be limited to, the following topics:

• Whole-body position/force control
• Model-based robot dynamics
• Centroidal momentum
• Contacts planning and control
• Torque-control
• Compliant body behavior
• Practical tips on whole-body control with real robots
• Whole-body agile locomotion and dexterous manipulation

IROS14 WORKSHOP:

Schedule:

[08.45 - 09.00] Introduction    

[09.00 - 09.30] Christian Ott (DLR)

   “Practical Experiences with the Torque-Controlled Humanoid Robot TORO”

[09.30 - 10.00] Yoshihiko Nakamura (Univ. of Tokyo)

  “On Reuse of Human Motion for Robot Control”

[10.00 - 10.30] Patrick M. Wensing and David E. Orin (OSU)

  “Centroidal Dynamics for Whole-Body Humanoid Control”     

[10.30 - 11.00] Coffee Break

[11.00 - 11.30] Siyuan Feng (CMU)

  "Full-Body Control for the Atlas Robot"     

[11.30 - 12.00] Federico L. Moro (IIT)

  “An Attractor-based Whole-Body Motion Control (WBMC) System - Tests with the COMAN Robot”     

[12.00 - 12.30] Russ Tedrake (MIT)

  “Optimization-based estimation, planning, and control”

[12.30 - 13.30] Lunch Break

[13.30 - 14.15] Interactive Session (see below)

[14.15 - 14.45] Andrea Del Prete (LAAS-CNRS)

  "Joint-Torque Control with Electric Motors and Harmonic Drives"     

[14.45 - 15.15] Silvio Traversaro  (IIT)

  “Whole-body Dynamic Computations on the iCub Humanoid”

[15.15 - 15.45] Coffee Break

[15.45 - 16.15] Luis Sentis (UT Austin)

  “Middleware for Rapid Application Programming”

[16.15 - 16.45] Mitsuharu Morisawa (AIST)

  "Locomotion and Manipulation in Unknown Environment by HRP-2"

[16.45 - 17.15] Ludovic Righetti (MPI)

  “Experiments with Hierarchical Inverse Dynamics Control on a Torque-Controlled Humanoid”

[17.15 - 18.00] Round Table

Interactive Session: 

• Hongkai Dai (MIT), Andres Valenzuela (MIT), Russ Tedrake (MIT)

“Whole-body Motion Planning with Simple Dynamics and Full Kinematics”       

• Michele Focchi (IIT), Andrea Del Prete (LAAS-CNRS), Ioannis Havoutis (IIT), Claudio Semini (IIT), Roy Featherstone (IIT), Darwin G. Caldwell (IIT)

“High-slope Terrain Locomotion for Torque-Controlled Quadruped Robots”    

• Gerardo Jarquin (IPN), Gustavo Arechavaleta (IPN), Adrien Escande (AIST), Eiichi Yoshida (AIST)

“Time-Constrained Whole Body Control With Smooth Task Transitions”       

• Jaeheung Park (SNU)

“Experimental Results of Whole-body Control Framework on Torque Controlled Humanoid Legged Robot and Dual Arm-Hand Manipulator”     

• Alessio Rocchi (IIT), Enrico Mingo Hoffman (IIT), Edoardo Farnioli (IIT), Nikos G. Tsagarakis (IIT)

“A Whole-Body Stack-of-Tasks compliant control for the Humanoid Robot COMAN”      

• Jesper Smith (IHMC), Sylvain Bertrand (IHMC), Peter Neuhaus (IHMC), Matthew Johnson (IHMC), Jerry Pratt (IHMC), and the IHMC team

“Momentum-based whole-body control framework – Application to the humanoid robots Atlas and Valkyrie”       

• Wael Suleiman (Univ. of Sherbrooke Quebec)

“Inverse Kinematics: New Method for Minimum Jerk Trajectory generation”       

• Hilario Tome (PAL), Luca Marchionni (PAL), Adolfo Rodriguez Tsouroukdissian (PAL)

“Whole body control using Robust & Online hierarchical quadratic optimization”      

Call for contributions CALL CLOSED

Perspective contributors are invited to submit an extended abstract (1 to 3 pages) describing their related research. All relevant and distinguished works will be selected and organized in the form of interactive session, or invited to give an oral talk presentation.

Submissions must be in PDF format, and have to be sent to This email address is being protected from spambots. You need JavaScript enabled to view it..

Important dates

Submission deadline: June 15^th, 2014 July 15^th, 2014

Notification of acceptance: July 15^th, 2014 July 31^st, 2014

Workshop date: Sept 18^th, 2014

IJHR SPECIAL ISSUE:

Call for papers    

Perspective contributors are invited to submit a full paper on their related research. All papers will undergo the regular IJHR review process.

IJHR Website: http://www.worldscientific.com/page/ijhr/callforpapers-details#Whole-Body%20Control

Authors should follow the guidelines of the International Journal of Humanoid Robotics (IJHR). The format is described at:
http://www.worldscientific.com/page/ijhr/submission-guidelines

Prospective authors should submit an electronic copy of their completed manuscripts through the on-line submission system at:
http://www.editorialmanager.com/ijhr/default.asp?pg=login.asp with the note "This paper is submitted to the Special Issue on Whole-Body Control for Robots in the Real World" according to the submission schedule.

Important dates

Submission deadline: 27^th Mar 2015 24^th May 2015

To appear in the issue of Dec 2015

FURTHER NOTES

• A contribution can be either only for the Workshop or for the Special Issue, or (better) for both events.
• Speakers at either oral or interactive session of the WS will be invited to submit a contribution to the IJHR SI.
• There is no limitation on the number of contributions from the same author/institution.

Contact: This email address is being protected from spambots. You need JavaScript enabled to view it.

Acknowledgment:

The IROS14 WS & IJHR SI on Whole-Body Control for Robots in the Real World are supported by the IEEE-RAS Technical Committee on Whole-Body Control - http://www.wholebodycontrol.eu/