[Amdnl] [meetings] BMVA Workshop on Visual, tactile and force sensing for robot manipulation

[Lorenzo Jamone]

BMVA Workshop on Visual, tactile and force sensing for robot manipulation

One Day BMVA symposium in London, UK on Wednesday 9th December, 2015

Chairs: Lorenzo Jamone & Serena Ivaldi

Keynote speakers:  Kaspar Althoefer (King's College London, UK). Jeremy
Wyatt (University of Birmingham, UK). Bruno Siciliano (University of Naples
Federico II, Italy).

www.bmva.org/meetings


<http://www.bmva.org/meetings>

Call for contributions:

We invite contributions to the workshop in the form of a one-page abstract,
to be submitted via email to ljamone at isr.ist.utl.pt (please, insert the [
BMVA meeting] tag in the subject), by the 22nd of July 2015.


Topic

Robotic manipulation has received considerable attention in the last
decades, as witnessed by a large number of international projects (e.g.
Handle, Grasp, DARPA's ARM, Poeticon) and scientific publications (see
Sahbani et al. 2012 for a recent review). Robots can perform repetitive
tasks with high speed and accuracy in industrial settings (e.g. car
manufacturing). However, their applications in semi-structured environments
is still very limited due to their poor adaptation capabilities: examples
are situations in which accurate object models cannot be obtained (e.g.
food, fabrics), or in which complex manipulation is required (e.g.
electronics assembly). Most of the state of the art solutions for robotic
manipulation rely on vision more than on tactile/force sensing, and only a
few integrate different sensory modalities (e.g. Grzyb et al. 2009, Geng et
al. 2011, Felip et al. 2014). While both technologies can be improved in
isolation, it is their combined used that can have a tremendous impact on
the manipulation skills of robots. Indeed, multisensory integration is
fundamental to achieve robot autonomy and robustness: visual,
proprioceptive, tactile and force sensing must be consider together, and
fused in an optimal way that allows taking the best control decisions.

The workshop will bring together researchers that are investigating
data-driven strategies for learning and control of robotic manipulation, as
well as specialists from academia and industry that are working on the
development of novel sensing technologies that are relevant for grasping
and manipulation, e.g. 2D and 3D vision, depth sensors, soft tactile
sensors, compliant force sensing.

The workshop will consist in a mixture of oral presentations,
poster/interactive sessions and/or live demonstrations, and a final panel
discussion.

Topics of interest include, but are not limited to:

3D object reconstruction
object segmentation/recognition/classification
visual attention for object exploration and manipulation
new tactile/force sensors technologies
sensors and robot automatic calibration
haptic exploration of rigid and compliant objects
multimodal object exploration and representation
data fusion techniques
hierarchical sensory representations
motor primitives for sensor-based grasping and manipulation
grasping and in-hand manipulation of non-modeled objects
teleoperation for complex manipulation
dynamic simulation of robotic hands with tactile/force sensors models
challenges in learning from high-dimensional, multi-modal sensor data
combined visual and tactile/force sensing for manipulation control

The Organizers,
Lorenzo & Serena

-- 
===================================================================

Lorenzo Jamone - Research Associate
http://lorejam.blogspot.pt/
ljamone at isr.tecnico.ulisboa.pt <Tecnicojasv at isr.tecnico.ulisboa.pt>

VisLab - http://vislab.isr.ist.utl.pt
Instituto Superior Técnico - http://tecnico.ulisboa.pt/

Institute for Systems and Robotics, Torre Norte (7th floor).
Av. Rovisco Pais, 1
1049-001 Lisbon, Portugal

Office (room 7.25): +351218418299
Laboratory (room 7.26): +351218418050

====================================================================
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cse.msu.edu/pipermail/amdnl/attachments/20150701/beafb977/attachment-0001.html>