Abstract
In this paper we investigate how directional distance signals can be incorporated in RNN-based adaptive goal-direction behavior inference mechanisms, which is closely related to formalizations of active inference. It was shown previously that RNNs can be used to effectively infer goal-directed action control policies online. This is achieved by projecting hypothetical environmental interactions dependent on anticipated motor neural activities into the future, back-projecting the discrepancies between predicted and desired future states onto the motor neural activities. Here, we integrate distance signals surrounding a simulated robot flying in a 2D space into this active motor inference process. As a result, local obstacle avoidance emerges in a natural manner. We demonstrate in several experiments with static as well as dynamic obstacle constellations that a simulated flying robot controlled by our RNN-based procedure automatically avoids collisions, while pursuing goal-directed behavior. Moreover, we show that the flight direction dependent regulation of the sensory sensitivity facilitates fast and smooth traversals through tight maze-like environments. In conclusion, it appears that local and global objectives can be integrated seamlessly into RNN-based, model-predictive active inference processes, as long as the objectives do not yield competing gradients.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Botvinick, M., Niv, Y., Barto, A.C.: Hierarchically organized behavior and its neural foundations: a reinforcement learning perspective. Cognition 113(3), 262–280 (2009). https://doi.org/10.1016/j.cognition.2008.08.011
Botvinick, M., Weinstein, A.: Model-based hierarchical reinforcement learning and human action control. Philos. Trans. Roy. Soc. London B: Biol. Sci. 369(1655) (2014). https://doi.org/10.1098/rstb.2013.0480
Butz, M.V.: Towards a unified sub-symbolic computational theory of cognition. Front. Psychol. 7(925) (2016). https://doi.org/10.3389/fpsyg.2016.00925
Butz, M.V., Bilkey, D., Humaidan, D., Knott, A., Otte, S.: Learning, planning, and control in a monolithic neural event inference architecture. Neural Networks (2019). https://doi.org/10.1016/j.neunet.2019.05.001
Butz, M.V., Bilkey, D., Knott, A., Otte, S.: Reprise: a retrospective and prospective inference scheme. In: Proceedings of the 40th Annual Meeting of the Cognitive Science Society, pp. 1427–1432 (2018)
Butz, M.V., Kutter, E.F.: How the Mind Comes Into Being: Introducing Cognitive Science from a Functional and Computational Perspective. Oxford University Press, Oxford (2017)
Camacho, E.F., Bordons, C.: Model Predictive Control. Springer, London (1999). https://doi.org/10.1007/978-1-4471-3398-8
Friston, K.: The free-energy principle: a rough guide to the brain? Trends Cogn. Sci. 13(7), 293–301 (2009)
Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., Pezzulo, G.: Active inference: a process theory. Neural Comput. 29(1), 1–49 (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Kingma, D.P., Ba, J.L.: Adam: A method for stochastic optimization. In: 3rd International Conference for Learning Representations, abs/1412.6980 (2015)
Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017). https://doi.org/10.1017/S0140525X16001837
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015). https://doi.org/10.1038/nature14236
Otte, S., Hofmaier, L., Butz, M.V.: Integrative collision avoidance within RNN-driven many-joint robot arms. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 748–758. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01424-7_73
Otte, S., Schmitt, T., Friston, K., Butz, M.V.: Inferring adaptive goal-directed behavior within recurrent neural networks. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10613, pp. 227–235. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68600-4_27
Otte, S., Zwiener, A., Butz, M.V.: Inherently constraint-aware control of many-joint robot arms with inverse recurrent models. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10613, pp. 262–270. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68600-4_31
Otte, S., Zwiener, A., Hanten, R., Zell, A.: Inverse recurrent models – an application scenario for many-joint robot arm control. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9886, pp. 149–157. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44778-0_18
Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction (1998)
Werbos, P.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78(10), 1550–1560 (1990). https://doi.org/10.1109/5.58337
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Otte, S., Stoll, J., Butz, M.V. (2019). Incorporating Adaptive RNN-Based Action Inference and Sensory Perception. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series. ICANN 2019. Lecture Notes in Computer Science(), vol 11730. Springer, Cham. https://doi.org/10.1007/978-3-030-30490-4_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-30490-4_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30489-8
Online ISBN: 978-3-030-30490-4
eBook Packages: Computer ScienceComputer Science (R0)