Hannes Saal PhD

Hannes Saal


Publications:
2011
  Effects of fingertip hysteresis on information coding in human primary tactile afferents
Saal, HP, Vijayakumar, S & Johansson, R 2011, 'Effects of fingertip hysteresis on information coding in human primary tactile afferents' Society for Neuroscience (SfN) 2011, Washington DC, United States, 12/11/11 - 16/11/11, .
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Saal, Hannes P., Vijayakumar, Sethu & Johansson, Roland.
Publication Date: 2011
Publication Information
Category: Poster
Original Language: English
  Multimodal Nonlinear Filtering Using Gauss-Hermite Quadrature
Saal, H, Heess, N & Vijayakumar, S 2011, Multimodal Nonlinear Filtering Using Gauss-Hermite Quadrature. in D Gunopulos, T Hofmann, D Malerba & M Vazirgiannis (eds), Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2011, Athens, Greece, September 5-9, 2011, Proceedings, Part III. Lecture Notes in Computer Science, vol. 6913, Springer Berlin Heidelberg, pp. 81-96. DOI: 10.1007/978-3-642-23808-6_6
In many filtering problems the exact posterior state distribution is not tractable and is therefore approximated using simpler parametric forms, such as single Gaussian distributions. In nonlinear filtering problems the posterior state distribution can, however, take complex shapes and even become multimodal so that single Gaussians are no longer sufficient. A standard solution to this problem is to use a bank of independent filters that individually represent the posterior with a single Gaussian and jointly form a mixture of Gaussians representation. Unfortunately, since the filters are optimized separately and interactions between the components consequently not taken into account, the resulting representation is typically poor. As an alternative we therefore propose to directly optimize the full approximating mixture distribution by minimizing the KL divergence to the true state posterior. For this purpose we describe a deterministic sampling approach that allows us to perform the intractable minimization approximately and at reasonable computational cost. We find that the proposed method models multimodal posterior distributions noticeably better than banks of independent filters even when the latter are allowed many more mixture components. We demonstrate the importance of accurately representing the posterior with a tractable number of components in an active learning scenario where we report faster convergence, both in terms of number of observations processed and in terms of computation time, and more reliable convergence on up to ten-dimensional problems.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Saal, Hannes, Heess, Nicolas & Vijayakumar, Sethu.
Number of pages: 16
Pages: 81-96
Publication Date: 2011
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1007/978-3-642-23808-6_6
2010
  Active Estimation of Object Dynamics Parameters with Tactile Sensors
Saal, H, Ting, J-A & Vijayakumar, S 2010, Active Estimation of Object Dynamics Parameters with Tactile Sensors. in Proc. IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS 2010), Taiwan (2010).. IEEE, New York, pp. 916-921. DOI: 10.1109/IROS.2010.5649191
The estimation of parameters that affect the dynamics of objects—such as viscosity or internal degrees of freedom—is an important step in autonomous and dexterous robotic manipulation of objects. However, accurate and efficient estimation of these object parameters may be challenging due to complex, highly nonlinear underlying physical processes. To improve on the quality of otherwise hand-crafted solutions, automatic generation of control strategies can be helpful. We present a framework that uses active learning to help with sequential gathering of data samples, using information-theoretic criteria to find the optimal actions to perform at each time step. We demonstrate the usefulness of our approach on a robotic hand-arm setup, where the task involves shaking bottles of different liquids in order to determine the liquid’s viscosity from only tactile feedback. We optimize the shaking frequency and the rotation angle of shaking in an online manner in order to speed up convergence of estimates.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Saal, Hannes, Ting, Jo-Anne & Vijayakumar, Sethu.
Keywords: (Informatics, Computer Science, Robotics. )
Number of pages: 6
Pages: 916-921
Publication Date: 2010
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/IROS.2010.5649191
  Active sequential learning with tactile feedback
Vijayakumar, S, Saal, H & Ting, J-A 2010, Active sequential learning with tactile feedback. in Proc. 13th Int. Conf. on Artificial Intelligence and Statistics (AISTATS 2010), JMLR: W&CP 9:677-684, Chia Laguna, Sardinia, Italy (2010).. pp. 8.
We consider the problem of tactile discrimination, with the goal of estimating an underlying state parameter in a sequential setting. If the data is continuous and high- dimensional, collecting enough representative data samples becomes difficult. We present a framework that uses active learning to help with the sequential gathering of data samples, using information-theoretic criteria to find optimal actions at each time step. We consider two approaches to recursively update the state parameter belief: an analytical Gaussian approximation and a Monte Carlo sampling method. We show how both active frameworks improve convergence, demonstrating results on a real robotic hand-arm system that estimates the viscosity of liquids from tactile feedback data.
General Information
Organisations: Neuroinformatics DTC.
Authors: Vijayakumar, Sethu, Saal, Hannes & Ting, Jo-Anne.
Keywords: (Informatics, Computer Science. )
Number of pages: 8
Pages: 8
Publication Date: 2010
Publication Information
Category: Conference contribution
Original Language: English
2009
  Active Filtering for Robot Tactile Learning
Saal, H, Ting, J-A & Vijayakumar, S 2009, 'Active Filtering for Robot Tactile Learning' Workshop on Adaptive Sensing, Active Learning and Experimental Design: Theory, Methods and Applications (NIPS 2009), Whistler, Canada, 11/12/09, .
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Saal, Hannes, Ting, Jo-Anne & Vijayakumar, Sethu.
Keywords: (Informatics, Computer Science, Robotics. )
Number of pages: 1
Publication Date: 2009
Publication Information
Category: Poster
Original Language: English
  Information about Complex Fingertip Parameters in Individual Human Tactile Afferent Neurons
Saal, H, Vijayakumar, S & Johansson, R 2009, 'Information about Complex Fingertip Parameters in Individual Human Tactile Afferent Neurons' Journal of Neuroscience, vol 29, no. 25, pp. 8022-8031. DOI: 10.1523/JNEUROSCI.0665-09.2009
Although information in tactile afferent neurons represented by firing rates has been studied extensively over nearly a century, recent studies suggest that precise spike timing might be more important than firing rates. Here, we used information theory to compare the information content in the discharges of 92 tactile afferents distributed over the entire terminal segment of the fingertip when it was contacted by surfaces with different curvatures and force directions representative of everyday manipulations. Estimates of the information content with regard to curvature and force direction based on the precise timing of spikes were at least 2.2 times and 1.6 times, respectively, larger than that of spike counts during a 125 ms period of force increase. Moreover, the information regarding force direction based on the timing of the very first elicited spike was comparable with that provided by spike counts and more than twice as large with respect to object shape. For all encoding schemes, afferents terminating close to the stimulation site tended to convey more information about surface curvature than more remote afferents that tended to convey more information about force direction. Finally, coding schemes based on spike timing and spike counts overall contributed mostly independent information. We conclude that information about tactile stimuli in timing of spikes in primary afferents, even if limited to the first spikes, surpasses that contained in firing rates and that these measures of afferents' responses might capture different aspects of the stimulus.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Saal, Hannes, Vijayakumar, Sethu & Johansson, Roland.
Keywords: (, , . )
Number of pages: 10
Pages: 8022-8031
Publication Date: Jun 2009
Publication Information
Category: Article
Journal: Journal of Neuroscience
Volume: 29
Issue number: 25
ISSN: 0270-6474
Original Language: English
DOIs: 10.1523/JNEUROSCI.0665-09.2009
2008
  Information about present and past stimulus features in human tactile afferents
Saal, H, Vijayakumar, S & Johansson, R 2008, Information about present and past stimulus features in human tactile afferents. in Proc. Computational and Systems Neuroscience COSYNE '08, Salt Lake City, Utah (2008).
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Saal, Hannes, Vijayakumar, Sethu & Johansson, Roland.
Keywords: (Informatics. )
Number of pages: 1
Publication Date: 2008
Publication Information
Category: Conference contribution
Original Language: English
  Spatiotemporal distribution of tactile information across the human fingertip
Saal, H, Vijayakumar, S & Johansson, R 2008, Spatiotemporal distribution of tactile information across the human fingertip. in Proc. Sixth Forum of European Neuroscience (FENS 2008). pp. 1.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Saal, Hannes, Vijayakumar, Sethu & Johansson, Roland.
Number of pages: 1
Pages: 1
Publication Date: 2008
Publication Information
Category: Conference contribution
Original Language: English

Projects:
An information theoretic approach to tactile encoding and discrimination (PhD)