A Scalable Neuro-inspired Robot Controller Integrating a Machine Learning Algorithm and a Spiking Cerebellar-Like Network
Combining Fable robot, a modular robot, with a neuroinspired controller, we present the proof of principle of a system that can scale to several neurally controlled compliant modules. The motor control and learning of a robot module are carried out by a Unit Learning Machine (ULM) that embeds the Locally Weighted Projection Regression algorithm (LWPR) and a spiking cerebellar-like microcircuit. The LWPR guarantees both an optimized representation of the input space and the learning of the dynamic internal model (IM) of the robot. However, the cerebellar-like sub-circuit integrates LWPR input-driven contributions to deliver accurate corrective commands to the global IM. This article extends the earlier work by including the Deep Cerebellar Nuclei (DCN) and by reproducing the Purkinje and the DCN layers using a spiking neural network (SNN) implemented on the neuromorphic SpiNNaker platform. The performance and robustness outcomes from the real robot tests are promising for neural control scalability.
KeywordsNeuro-robotics Bio-inspiration Motor control Cerebellum Machine learning Compliant control Internal model
This work has received funding from the EU-H2020 Programme under the grant agreement no. 720270 (Human Brain Project SGA1) and from the Marie Curie project no. 705100 (Biomodular). We are thankful to David Johan Christensen and Moisés Pacheco, CEO/CTO & Co-founders of Shape Robotics, for the Fable robot. A special thank is expressed to the University of Manchester and the University of Munich for SpiNNaker.
- 7.Verduzco-Flores, S.O., O’Reilly, R.C.: How the credit assignment problems in motor control could be solved after the cerebellum predicts increases in error. Front. Comput. Neurosci. 9 (2015)Google Scholar
- 14.Garrido, J.A., Luque, N.R., D’Angelo, E., Ros, E.: Distributed cerebellar plasticity implements adaptable gain control in a manipulation task: a closed-loop robotic simulation (2013)Google Scholar
- 15.Vannucci, L., Ambrosano, A., Cauli, N., Albanese, U., Falotico, E., Ulbrich, S., Pfotzer, L., Hinkel, G., Denninger, O., Peppicelli, D., Guyot, L., Arnim, A.V., Deser, S., Maier, P., Dillman, R., Klinker, G., Levi, P., Knoll, A., Gewaltig, M.O., Laschi, C.: A visual tracking model implemented on the icub robot as a use case for a novel neurorobotic toolkit integrating brain and physics simulation. In: 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 1179–1184 (2015)Google Scholar
- 23.Pacheco, M., Fogh, R., Lund, H.H., Christensen, D.J.: Fable: A modular robot for students, makers and researchers. In: Proceedings of the IROS workshop on Modular and Swarm Systems: from Nature to Robotics (2014)Google Scholar
- 25.Sjöström, J., Gerstner, W.: Spike-timing dependent plasticity. Spike-timing dependent plasticity, p. 35 (2010)Google Scholar
- 26.Davison, A., Brüderle, D., Kremkow, J., Muller, E., Pecevski, D., Perrinet, L., Yger, P.: PYNN: a common interface for neuronal network simulators (2009)Google Scholar