I am a PhD student affiliated to EPFL and working at the Idiap Research Institute under the supervision of Dr. Sylvain Calinon since August 2016. My research interests cover human-robot interactions and machine learning. I am interested in exploring new possibilities of intelligent systems, especially bio-inspired and mobile robots. I obtained a Bachelor in Microengineering (2014), a Master in Robotics and Autonomous Systems (2016) and a Minor in Computational Neurosciences (2016) from EPFL.

My work focuses on extending regression methods to take into account the stucture and geometry of the data by exploiting tensor methods and Riemannian manifolds. I am part of the collaborative project TACT-HAND supported by the Swiss National Science Foundation. I use the developped regression methods to improve the control of prosthetic hands.

Current research

Regression methods for structured data

In many sensing and control applications, data are represented in the form of multidimensional arrays with particular geometric properties such as symmetries. Considering the underlying structure and geometry of the data can be beneficial in many robotics applications. Considering the structure and geometry of the data is even more important when a small set of multimodal data is available.

Representation of the Riemannian manifold of symmetric positive definite matrices. Projection of points to the tangent space allows to perform operations in Euclidean space.

Examples of Gaussian mixture regression (GMR) with time as input and output data in the form of symmetric positive definite (SPD) matrices. The joint density is modeled by a 2-components Gaussian mixture model.

I exploit tensor methods and Riemannian geometry to develop structure and geometry-aware statistical learning techniques. Instead of transforming high-order data into vectors, I aim at considering their potential multimode relations and handling their underlying geometry. I also consider the case where input modality is complex, meaning that different structured data with different geometries are available and should be combined efficiently and meaningfully.

Application to the control of prosthetic hands

The aim of the TACT-HAND project is to improve the reliability and the stability of the control of prosthetic hands. It proposes to augment the traditional electromyography (EMG) sensors with tactile myography (TMG) in the form of a muscle bulgings measuring bracelet made of pressure sensors.

Control of prosthetic hands using TMG and EMG.

EMG sensors (left) and tactile bracelet (right) placed on the forearm.

We treat the control of prosthetics as a regression problem, fusing information from tactile sensing and EMG sensors. We aim at keeping the structure of the data as EMG are often processed as covariance features and TMG is naturally represented by a cylindric grid. Tensor methods and Riemannian geometry allows us to exploit the spatial and temporal patterns that appear in EMG and TMG data and to improve the detection of hand and wrist movements.

Manipulability transfer

Body posture greatly influences human performance when carrying out manipulation tasks. Adopting an appropriate pose helps us regulate our motion and strengthen our capability to achieve a given task. Similarly, in robotic manipulation, the robot joint configuration affects both the ability to move freely in all directions in the workspace and the capability to generate forces along different axes.

Examples of manipulability for different postures in pushing and pulling tasks.

Left: Gaussian mixture model (GMM) computed from demonstrated manipulability ellipsoids (gray). Right: learned and reproduced manipulability profiles (in green and red respectively).

In this context, manipulability ellipsoids are posture-dependent measures indicating the preferred directions to perform velocity, force or dynamic control commands. We propose to transfer manipulability-based posture variation between robots: a teacher robot demonstrates how to perform a task with a desired manipulability profile and a learner robot reproduces the task while matching the learned manipulability profile. This approach allows to transfer posture-dependent task requirements such as preferred directions for motion and force exertion. We encode, retrieve and track robot manipulability ellipsoids using geometry-aware learning and tracking frameworks based on Riemannian geometry and tensor formulation.



Journal papers

Jaquier, N. and Calinon, S. Improving the control of prosthetic hands with tactile sensing, Micro & Nano Magazine, Micronarc.
[pdf] [bibtex] [publisher's website]

Conference papers

Jaquier, N., Rozo, L., Caldwell, D. G. and Calinon, S. Geometry-aware Tracking of Manipulability Ellipsoids, in Robotics: Science and Systems (R:SS), Pittsburgh, USA, June 2018.
[pdf] [bibtex] [video] [code] [publisher's website]

Workshop papers

Jaquier, N., Rozo, L. and Calinon, S. Geometry-aware Robot Manipulability Transfer, in Learning and Inference in Robotics: Integrating Structure, Priors and Models (LAIR) Workshop at Robotics: Science and Systems Conference (R:SS), Pittsburgh, USA, June 2018.
[pdf] [bibtex] [publisher's website]

Jaquier, N. and Calinon, S. Geometry-aware Control and Learning in Robotics, in Robotics: Science and Systems (R:SS) Pioneers Workshop, Pittsburgh, USA, June 2018.
[pdf] [bibtex] [publisher's website]


Journal papers

Jaquier, N., Connan, M., Castellini, C. and Calinon, S. Combining electromyography and tactile myography to improve hand and wrist activity detection in prostheses, Technologies, 5:4, Special issue on assistive robotics.
[pdf] [bibtex] [code] [publisher's website]

Conference papers

Jaquier, N. and Calinon, S. Gaussian mixture regression on symmetric positive definite matrices manifolds: Application to wrist motion estimation with sEMG, in IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 2017.
[pdf] [bibtex] [publisher's website]

Rozo, L., Jaquier, N., Calinon, S. and Caldwell, D. G. Learning manipulability ellipsoids for task compatibility in robot manipulation, in IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 2017.
[pdf] [bibtex] [publisher's website]

Jaquier, N., Castellini, C. and Calinon, S. Improving hand and wrist activity detection using tactile sensors and tensor regression methods on Riemannian manifolds, in Myoelectric control (MEC) Symposium, Fredericton, New Brunswick, Canada, August 2017.
[pdf] [bibtex] [publisher's website]

Invited talks

28.11 Swiss Machine Learning Day, EPFL, Switzerland

14.11 Applied Mathematics Seminar, Applied Mathematic Dept., UCL, Belgium

24.09 Workshop on Micro-data: the next frontier in robot learning?, IROS 2017, Vancouver, Canada

23.05 Numerical Analysis Seminar. Mathematic Dept., University of Geneva

31.01 Rapid-fire talk. Applied Machine Learning Days, EPFL, Switzerland

20.01 Operating room technicians class, Upper School of the Health (ES Santé), Lausanne, Switzerland

Past projects

Master project: Improving the drawing skills of a humanoid robot with visual feedback
(Idiap Research Institute)

I developed controllers for the humanoid robot Baxter to reproduce a simple image with pen strokes while exploiting the compliance of the arms of the robot and the visual feedback provided by its cameras.

Summer internship at SenseFly

I was part of the research and development team designing aerial imaging drones for professional applications. My task was to develop flight control algorithms for an intelligent mapping and inspection quadrotor (the albris).

Semester project: EEG-based control of a 7-DOF upper-limb prosthesis (CNBI, EPFL)

I implemented a shared-control paradigm, already implemented in simulation, on a WAM robot. The neuroprosthesis executed actions that were evaluated by the user as onerous or correct and the brain correlates of this assessment was exploited to learn suitable motor behaviours.

Semester project: Sensor fusion for speed estimation on quadrupedal robots (BioRob, EPFL)

I used model-free techniques for speed estimation on data collected in two different robots; Oncilla and Pleurobot. This allowed to estimate their instantaneous velocity and to know if they get trapped, fall, are deviated or move as expected.

Semester project: Evolution of a ground controller for a flying and walking robot with adaptive morphology (LIS, EPFL)

I modelled a multi-modal bio-inspired walking and flying robot on the simulator Webots and used genetic algorithms to evolve the parameters of the motors to optimize the gait of the robot. This allows to reduce the cost of transport of the gait and to optimise the gait depending on the terrain.


Noémie Jaquier
Idiap Research Institute
Centre du Parc
Rue Marconi 19
PO Box 592
1920 Martigny

Email: noemie.jaquier@idiap.ch