Scaffolding Haptic Attention with Controller Gating

Moringen A, Fleer S, Ritter H (2019)
In: Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I. Tetko IV, Kůrková V, Karpov P, Theis F (Eds); Lecture Notes in Computer Science, 11727. Cham: Springer: 669-684.

Sammelwerksbeitrag | Veröffentlicht | Englisch
 
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Herausgeber*in
Tetko, Igor V.; Kůrková, Věra; Karpov, Pavel; Theis, Fabian
Abstract / Bemerkung
A powerful concept that emerged within the field of educational psychology is scaffolding. Characterizing favourable expert-learner interaction, it can be defined as a temporal support that provides a novice an adaptable guidance to either learn tasks that would usually be beyond own capabilities or to speed up and refine the learning of manageable problems. In this work we apply the above-mentioned concept to implement a novel multi-strategy haptic exploration controller that is able to perform object identification using a robot.

In our previous work we have proposed a reinforcement learner that acquires haptic exploration capabilities for a goal-directed task by optimizing motor control in a strongly restricted attentional framework, called the haptic attention model (HAM). The resulting policy however was not characterized by a smooth energy-efficient exploration suitable for execution on a robot. In this work, we scaffold the designed learning architecture by imposing the so-called controller gating that is trained to switch between orientation and position control. Integrated in the same reinforcement learning setting as the HAM, controller gating guides and monitors the data acquisition. Inspired by the human expert scaffolding, it analyzes the HAM internal data representation, modulates the HAM weight update process, and forces data acquisition that achieves efficient and successful completion of the goal. Our computational scaffold adapts to the learner model, while it masters the skill. The evaluation demonstrated that it is more likely for the trained model to change either location or orientation than simultaneously change both, which significantly improves the smoothness and the energy-efficiency of the resulting exploration.
Stichworte
Haptic exploration; Reinforcement learning; Scaffolding; Gating; Haptic glances; Exploratory procedures; Robotics
Erscheinungsjahr
2019
Buchtitel
Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I
Band
11727
Seite(n)
669-684
Konferenz
28th International Conference on Artificial Neural Networks – ICANN 2019
Konferenzort
München
Konferenzdatum
2019-17-09 – 2019-19-09
ISBN
978-3-030-30486-7
eISBN
978-3-030-30487-4
Page URI
https://pub.uni-bielefeld.de/record/2939854

Zitieren

Moringen A, Fleer S, Ritter H. Scaffolding Haptic Attention with Controller Gating. In: Tetko IV, Kůrková V, Karpov P, Theis F, eds. Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I. Lecture Notes in Computer Science. Vol 11727. Cham: Springer; 2019: 669-684.
Moringen, A., Fleer, S., & Ritter, H. (2019). Scaffolding Haptic Attention with Controller Gating. In I. V. Tetko, V. Kůrková, P. Karpov, & F. Theis (Eds.), Lecture Notes in Computer Science: Vol. 11727. Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I (pp. 669-684). Cham: Springer. doi:10.1007/978-3-030-30487-4_51
Moringen, A., Fleer, S., and Ritter, H. (2019). “Scaffolding Haptic Attention with Controller Gating” in Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I, Tetko, I. V., Kůrková, V., Karpov, P., and Theis, F. eds. Lecture Notes in Computer Science, vol. 11727, (Cham: Springer), 669-684.
Moringen, A., Fleer, S., & Ritter, H., 2019. Scaffolding Haptic Attention with Controller Gating. In I. V. Tetko, et al., eds. Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I. Lecture Notes in Computer Science. no.11727 Cham: Springer, pp. 669-684.
A. Moringen, S. Fleer, and H. Ritter, “Scaffolding Haptic Attention with Controller Gating”, Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I, I.V. Tetko, et al., eds., Lecture Notes in Computer Science, vol. 11727, Cham: Springer, 2019, pp.669-684.
Moringen, A., Fleer, S., Ritter, H.: Scaffolding Haptic Attention with Controller Gating. In: Tetko, I.V., Kůrková, V., Karpov, P., and Theis, F. (eds.) Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I. Lecture Notes in Computer Science. 11727, p. 669-684. Springer, Cham (2019).
Moringen, Alexandra, Fleer, Sascha, and Ritter, Helge. “Scaffolding Haptic Attention with Controller Gating”. Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation.28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part I. Ed. Igor V. Tetko, Věra Kůrková, Pavel Karpov, and Fabian Theis. Cham: Springer, 2019.Vol. 11727. Lecture Notes in Computer Science. 669-684.
Link(s) zu Volltext(en)
Access Level
Restricted Closed Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche