NeuroRover and NeuroCopter : artificial minibrains for autonomous robots
Insects show a rich repertoire of goal-directed and adaptive behaviors that are still beyond the capabilities of
today’s artiﬁcial systems. We develop artificial minibrains to control autonomous robots. In a first step this requires to investigate sensory processing, memory formation and decision making in insects. Our primary animal model is the honeybee. Central to our approach is the simulation of spiking neural network models that represent a simplified version of the biologicla brain. When operated in real-time, this artificial nervous system can make a robot sense, learn, and control its behavior. Related to this research topic we develop insect-inspired neural networks to operate on neuromorphic chips.
Recent updates on NeuroRover and NeuroCopter can be found on our project page.
This project is funded by the German Ministry of Education and Research within the Bernstein Focus Neuronal Basis of Learning: Insect inspired robots - The role of memory in decision making.
24.02.2014 Radiobeitrag auf RBB InfoRadio in der Sendung Wissenswerte
14.02.2104 Interview article Robots with Insect Brains on the technology news platform KurzweilAI
09.10.2009 Wie Insekten Roboter inspirieren, erschienen im Berliner Tagesspiegel
18.04.2009 Riechen für die Roboter, erschienen im Berliner Tagesspiegel
- Schmuker M, Pfeil T, Nawrot MP (2014) A neuromorphic network for generic multivariate data classification. PNAS, published ahead of print, doi: 10.1073/pnas.1303053111 [abstract] [PDF]
- Helgadottir LI, Haenicke J, Landgraf T, Rojas R, Nawrot MP (2013) Conditioned behavior in a robot controlled by a spiking neural network. 6th International IEEE EMBS Conference on Neural Engineering, San Diege, USA, Nov 5-8, p. 891 - 894, doi: 10.1109/NER.2013.6696078 [Preprint] [video]
- Landgraf T, Wild B, Ludwig T, Nowak P, Helgadottir L, Daumenlang B, Breinlinger P, Nawrot MP, Rojas R (2013) NeuroCopter: Neuromorphic Computation of 6D Ego-Motion of a Quadcopter. Biomimetic and Biohybrid Systems. Lecture Notes in Computer Science 8064:143-153 [abstract] [PDF]
- Helgadottir L, Haenicke J, Landgraf T, Nawrot MP (2012) A Robotic Platform for Spiking Neural Control Architectures Front. Comput. Neurosci. Conference Abstract: Bernstein Conference 2012. [abstract]
- Meyer J, Haenicke J, Landgraf T, Schmuker M, Rojas R and Nawrot M (2011) A digital receptor neuron connecting remote sensor hardware to spiking neural networks. Front. Comput. Neuroscience. Conference Abstract: BC11 : Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting 2011, October 4-6 2011, Freiburg, Germany. [doi]