bibliography.bib
@article{Shafti2016a,
author = {A. Shafti and R. B. Ribas Manero and A. M. Borg and
K. Althoefer and Matthew Howard},
journal = {IEEE Transactions on Neural Systems and
Rehabilitation Engineering},
title = {Textile-integrated Embroidered Electrodes for
Wearable Surface Electromyography},
year = {2016}
}
@inproceedings{Manero2016,
author = {R. B. Ribas Manero and B. Michael and A. Shafti and
K. Althoefer and J. Ll. Ribas Fernandez and
Matthew Howard},
booktitle = {IEEE International Conference Engineering in Medicine
and Biology Society},
title = {Wearable Embroidered Muscle Activity Sensing Device
for the Human Upper Leg},
year = {2016},
url = {https://arxiv.org/abs/1602.04841}
}
@inproceedings{Shafti2016,
author = {A. Shafti and R. B. Ribas Manero and A. M. Borg and
K. Althoefer and Matthew Howard},
booktitle = {IEEE International Conference Robotics and
Automation},
title = {Designing Embroidered Electrodes for Wearable Surface
Electromyography},
year = {2016}
}
@inproceedings{Martinez-Miranda2016,
author = {Enrique Martinez-Miranda and Peter McBurney and
Matthew Howard},
booktitle = {IEEE International Conference on Evolving and
Adaptive Intelligent Systems},
title = {Learning Unfair Trading: a Market Manipulation
Analysis From the Reinforcement Learning Perspective},
year = {2016}
}
@article{Michael2016a,
author = {Brendan Michael and Matthew Howard},
journal = {IEEE Transactions on Neural Systems and
Rehabilitation Engineering},
title = {Learning Predictive Movement Models from
Fabric-mounted Wearable Sensors},
year = {2016}
}
@inproceedings{Lin2015,
author = {Hsiu-Chin Lin and Matthew Howard and
Sethu Vijayakumar},
booktitle = {IEEE International Conference Robotics and
Automation},
title = {Learning Null Space Projections},
year = {2015}
}
@article{Lin2014a,
author = {Lin,Hsiu-Chin and Matthew Howard and
Vijayakumar, Sethu},
journal = {Robotica},
month = {12},
pages = {1225--1244},
title = {A novel approach for representing and generalising
periodic gaits},
volume = {32},
year = {2014},
abstract = {Our goal is to introduce a more appropriate method of
representing, generalising and comparing gaits;
particularly, walking gait. Human walking gaits are a
result of complex, interdependent factors that
include variations resulting from embodiments,
environment and tasks, making techniques that use
average template frameworks suboptimal for systematic
analysis or corrective interventions. The proposed
work aims to devise methodologies for being able to
represent gaits and gait transitions such that
optimal policies that eliminate the inter-personal
variations from tasks and embodiments may be
recovered. Our approach is built upon (i) work in the
domain of nullspace policy recovery and (ii) previous
work in generalisation for point-to-point movements.
The problem is formalised using a walking-phase
model, and the nullspace learning method is used to
generalise a consistent policy from multiple
observations with rich variations. Once recovered,
the underlying policies (mapped to different gait
phases) can serve as reference guideline to quantify
and identify pathological gaits while being robust
against interpersonal and task variations. To
validate our methods, we have demonstrated robustness
of our method with simulated sagittal two-link gait
data with multiple ground truth constraints and
policies. Pathological gait identification was then
tested on real-world human gait data with induced
gait abnormality, with the proposed method showing
significant robustness to variations in speed and
embodiment compared to template-based methods. Future
work will extend this to kinetic features and higher
dimensional features.},
doi = {10.1017/S026357471400188X},
issn = {1469-8668},
url = {http://journals.cambridge.org/article_S026357471400188X}
}
@inproceedings{Lin2014,
author = {Hsiu-Chin Lin and Matthew Howard and
Sethu Vijayakumar},
booktitle = {IEEE RAS/EMBS International Conference on Biomedical
Robotics and Biomechatronics},
title = {Generalising Walking Gaits across Subjects and
Walking Speeds},
year = {2014}
}
@inproceedings{Michael2014,
author = {Brendan Michael and Matthew Howard},
booktitle = {IEEE International Conference Humanoid Robots},
title = {Eliminating motion artifacts from fabric-mounted
wearable sensors},
year = {2014}
}
@inproceedings{Sornkarn2014,
author = {Nantachai Sornkarn and Matthew Howard and
Thrishantha Nanayakkara},
booktitle = {IEEE International Conference Robotics and
Automation},
title = {Internal Impedance Control helps Information Gain in
Embodied Perception},
year = {2014}
}
@inproceedings{Howard2013b,
author = {Matthew Howard and Yoshihiko Nakamura},
booktitle = {IEEE International Conference Intelligent Robots and
Systems},
title = {Locally Weighted Least Squares Policy Iteration for
Model-free Learning in Uncertain Environments},
year = {2013}
}
@article{Howard2013a,
author = {Matthew Howard and David Braun and Sethu Vijayakumar},
journal = {IEEE Transactions on Robotics},
number = {4},
pages = {847-862},
title = {Transferring Human Impedance Behavior to
Heterogeneous Variable Impedance Actuators},
volume = {29},
year = {2013},
abstract = {This paper presents a comparative study of approaches
for controlling robots with variable impedance
actuators (VIAs), in ways that imitate the behaviour
of humans. We focus on problems where impedance
modulation strategies are recorded from human
demonstrators for transfer to robotic systems with
differing levels of heterogeneity, both in terms of
the dynamics and actuation. We categorise three
classes of approach that may be applied to this
problem, namely, (i) direct, (ii) feature-based, and
(iii) inverse optimal approaches to transfer. While
the first is restricted to highly biomorphic plants,
the latter two are shown to be sufficiently general
to be applied to various VIAs in a way that is
independent of the mechanical design. As
instantiations of such transfer schemes, (i) a
constraint-based method, and (ii) an apprenticeship
learning framework are proposed, and their
suitability to different problems in robotic
imitation, in terms of efficiency, ease of use and
task performance is characterised. The approaches are
compared in simulation on systems of varying
complexity, and robotic experiments are re- ported
for transfer of behaviour from human
electromyographic data to two different variable
passive compliance robotic devices.},
doi = {10.1109/TRO.2013.2256311},
issn = {1552-3098},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
arnumber=6510474}
}
@inproceedings{Howard2013,
author = {Matthew Howard and Yoshihiko Nakamura},
booktitle = {European Symposium Artificial Neural Networks},
title = {Locally Weighted Least Squares Temporal Difference
Learning},
year = {2013}
}
@inproceedings{Radulescu2012,
author = {Andreea Radulescu and Matthew Howard and David Braun and
Sethu Vijayakumar},
booktitle = {IEEE/ASME International Conference Advanced
Intelligent Mechatronics},
title = {Exploiting Variable Physical Damping in Rapid
Movement Tasks},
year = {2012}
}
@article{Braun2012,
author = {David Braun and Matthew Howard and Sethu Vijayakumar},
journal = {Autonomous Robots},
pages = {237-253},
title = {Optimal Variable Stiffness Control: Formulation and
Application to Explosive Movement Tasks},
volume = {33},
year = {2012},
abstract = {It is widely recognised that compliant actuation is
advantageous to robot control once dynamic tasks are
considered. However, the benefit of intrinsic
compliance comes with high control complexity.
Specifically, coordinating the motion of the system
through a compliant actuator and finding a
task-specific impedance profile that leads to better
performance is known to be non-trivial. Here, we
propose an optimal control formulation to compute the
motor position commands, and the associated
time-varying torque and stiffness profiles. To
demonstrate the utility of the approach, we consider
an "explosive" ball-throwing task where exploitation
of the intrinsic dynamics of the compliantly actuated
system leads to improved task perfor- mance (i.e.,
distance thrown). In this example we show that: (i)
the proposed control methodology is able to tailor
impedance strategies to specific task objectives and
system dynamics, (ii) the ability to vary stiffness
can be exploited to achieve better performance, (iii)
in systems with variable physical compliance, the
present formulation enables exploitation of the
energy storage capabilities of the actuators to
improve task performance. We illustrate these in
numerical simulations, and in hardware experiments on
a two-link variable stiffness robot.},
doi = {10.1007/s10514-012-9302-3},
url = {http://link.springer.com/article/10.1007%2Fs10514-012-9302-
3}
}
@inproceedings{Braun2011,
address = {Los Angeles, CA, USA},
author = {David Braun AND Matthew Howard AND Sethu Vijayakumar},
booktitle = {Robotics: Science and Systems},
month = jun,
title = {Exploiting Variable Stiffness in Explosive Movement
Tasks},
year = {2011}
}
@inproceedings{Mori2011,
author = {Takeshi Mori and Matthew Howard and
Sethu Vijayakumar},
booktitle = {IEEE International Conference Humanoid Robots},
title = {Model-free apprenticeship learning for transfer of
human impedance behaviour},
year = {2011}
}
@inproceedings{Howard2011,
author = {Matthew Howard and David Braun and Sethu Vijayakumar},
booktitle = {IEEE International Conference Robotics and
Automation},
title = {Constraint-based Equilibrium and Stiffness Control of
Variable Stiffness Actuators},
year = {2011}
}
@inproceedings{Mitrovic2010b,
author = {Djordje Mitrovic and Stefan Klanke and Matthew Howard and
Sethu Vijayakumar},
booktitle = {IEEE International Conference Humanoid Robots},
title = {Exploiting Sensorimotor Stochasticity for Learning
Control of Variable Impedance Actuators},
year = {2010}
}
@inproceedings{Towell2010,
author = {Chris Towell and Matthew Howard and
Sethu Vijayakumar},
booktitle = {IEEE International Conference Intelligent Robots and
Systems},
title = {Learning Null Space Policies},
year = {2010}
}
@inproceedings{Bitzer2010,
author = {Sebastian Bitzer and Matthew Howard and
Sethu Vijayakumar},
booktitle = {IEEE International Conference Intelligent Robots and
Systems},
title = {Using Dimensionality Reduction to Exploit Constraints
in Reinforcement Learning},
year = {2010}
}
@inproceedings{Howard2010,
author = {Matthew Howard and Djordje Mitrovic and
Sethu Vijayakumar},
booktitle = {IEEE International Conference Humanoid Robots},
title = {Transferring Impedance Control Strategies Between
Heterogeneous Systems via Apprenticeship Learning},
year = {2010}
}
@phdthesis{Howard2009d,
author = {Matthew Howard},
school = {University of Edinburgh},
title = {Learning Control Policies from Constrained Motion},
year = {2009}
}
@inproceedings{Howard2009c,
author = {Matthew Howard and Stefan Klanke and Michael Gienger and
Christian Goerick and Sethu Vijayakumar},
booktitle = {IEEE International Conference Intelligent Robots and
Systems},
title = {Robust Constraint-consistent Learning},
year = {2009},
doi = {10.1109/IROS.2009.5354663}
}
@article{Howard2009b,
author = {Matthew Howard and Stefan Klanke and Michael Gienger and
Christian Goerick and Sethu Vijayakumar},
journal = {Autonomous Robots},
pages = {105-121},
title = {A Novel Method for Learning Policies from Variable
Constraint Data},
volume = {27},
year = {2009},
abstract = {Many everyday human skills can be framed in terms of
performing some task subject to constraints imposed
by the environment. Constraints are usually
unobservable and frequently change between contexts.
In this paper, we present a novel approach for
learning (unconstrained) control policies from
movement data, where observations come from movements
under different constraints. As a key ingredient, we
introduce a small but highly effective modification
to the standard risk functional, allowing us to make
a meaningful comparison between the estimated policy
and constrained observations. We demonstrate our
approach on systems of varying complexity, including
kinematic data from the ASIMO humanoid robot with 27
degrees of freedom, and present results for learning
from human demonstration.},
doi = {10.1007/s10514-009-9129-8},
url = {http://www.springerlink.com/content/r5u85525p6171g17/}
}
@incollection{Howard2009a,
author = {Matthew Howard and Klanke, S. and Gienger, M. and
Goerick, C. and Vijayakumar, S.},
booktitle = {From Motor to Interaction Learning in Robots},
publisher = {Springer},
title = {Methods for Learning Control Policies from
Variable-constraint Demonstrations},
year = {2009}
}
@incollection{Vijayakumar2009,
author = {Sethu Vijayakumar and Marc Toussaint and
Georgios Petkos and Matthew Howard},
booktitle = {Creating Brain Like Intelligence: From Principles to
Complex Intelligent Systems},
editor = {Sendhoff and Koerner and Sporns and Ritter and Doya},
publisher = {Springer-Verlag},
series = {Lecture Notes in Artificial Intelligence},
title = {Planning and Moving in Dynamic Environments: A
statistical machine learning approach},
volume = {5436},
year = {2009}
}
@inproceedings{Howard2009,
author = {Matthew Howard and Stefan Klanke and Michael Gienger and
Christian Goerick and Sethu Vijayakumar},
booktitle = {IEEE International Conference Robotics and
Automation},
title = {A Novel Method for Learning Policies from Constrained
Motion},
year = {2009}
}
@article{Howard2008a,
author = {Matthew Howard and Stefan Klanke and Michael Gienger and
Christian Goerick and Sethu Vijayakumar},
journal = {Applied Bionics and Biomechanics},
month = dec,
number = {4},
pages = {195-211},
title = {Behaviour Generation in Humanoids by Learning
Potential-based Policies from Constrained Motion},
volume = {5},
year = {2008},
doi = {10.1080/11762320902789830},
url = {http://www.tandfonline.com/doi/full/10.1080/
11762320902789830}
}
@inproceedings{Howard2008,
author = {Matthew Howard and Stefan Klanke and Michael Gienger and
Christian Goerick and Sethu Vijayakumar},
booktitle = {IEEE International Conference Humanoid Robots},
title = {Learning Potential-based Policies from Constrained
Motion},
year = {2008}
}
@inproceedings{Howard2007,
author = {Matthew Howard and Sethu Vijayakumar},
booktitle = {Workshop on Robotics and Mathematics},
month = {September},
title = {Reconstructing Null-space Policies Subject to Dynamic
Task Constraints in Redundant Manipulators},
year = {2007}
}
@inproceedings{Howard2006,
author = {Matthew Howard and Michael Gienger and
Christian Goerick and Sethu Vijayakumar},
booktitle = {IEEE International Conference on Robotics and
Biomimetics},
title = {Learning Utility Surfaces for Movement Selection},
year = {2006}
}