Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Introducing Probabilistic Bézier Curves for N-Step Sequence Prediction

: Hug, Ronny; Hübner, Wolfgang; Arens, Michael


Association for the Advancement of Artificial Intelligence -AAAI-:
Thirty-Fourth AAAI Conference on Artificial Intelligence 2020. Proceedings : Thirty-Second Conference on Innovative Applications of Artificial Intelligence, the Tenth Symposium on Educational Advances in Artificial Intelligence, February 7-12, 2020, New York, New York, USA
Menlo Park: AAAI Press, 2020 (AAAI Technical Tracks 34.2020, Nr.6)
ISBN: 978-1-57735-835-0
Conference on Artificial Intelligence (AAAI) <34, 2020, New York/NY>
Conference on Innovative Applications of Artificial Intelligence (IAAI) <32, 2020, New York/NY>
Symposium on Educational Advances in Artificial Intelligence (EAAI) <10, 2020, New York/NY>
Conference Paper
Fraunhofer IOSB ()

Representations of sequential data are commonly based on the assumption that observed sequences are realizations of an unknown underlying stochastic process, where the learning problem includes determination of the model parameters. In this context, a model must be able to capture the multi-modal nature of the data, without blurring between single modes. This paper proposes probabilistic Bezier curves (N-Curves) as a basis for effectively modeling continuous-time stochastic processes. The model is based on Mixture Density Networks (MDN) and Bezier curves with Gaussian random variables as control points. Key advantages of the model include the ability of generating smooth multi-mode predictions in a single inference step which reduces the need for Monte Carlo simulation. This property is in line with recent attempts to address the problem of quantifying uncertainty as a regression problem. Essential properties of the proposed approach are illustrated by several toy examples and the task of multi-step sequence prediction. As an initial proof of concept, the model performance is compared to an LSTM-MDN model and recurrent Gaussian processes on two real world use-cases, trajectory prediction and motion capture sequence prediction.