Abstract
Biological systems interact directly with the environment and learn by receiving multimodal feedback via sensory stimuli that shape the formation of internal neuronal representations. Drawing inspiration from biological concepts such as exploration and sensory processing that eventually lead to behavioral conditioning, we present a robotic system handling objects through multimodal learning. A small-scale organic neuromorphic circuit locally integrates and adaptively processes multimodal sensory stimuli, enabling the robot to interact intelligently with its surroundings. The real-time handling of sensory stimuli via low-voltage organic neuromorphic devices with synaptic functionality forms multimodal associative connections that lead to behavioral conditioning, and thus the robot learns to avoid potentially dangerous objects. This work demonstrates that adaptive neuro-inspired circuitry with multifunctional organic materials, can accommodate locally efficient bio-inspired learning for advancing intelligent robotics.
| Original language | English |
|---|---|
| Article number | 4765 |
| Number of pages | 9 |
| Journal | Nature Communications |
| Volume | 15 |
| Early online date | 4 Jun 2024 |
| DOIs | |
| Publication status | Published - Dec 2024 |
Funding
Y.v.d.B gratefully acknowledges funding from the European Research Council under the European Union\u2019s Horizon 2020 research and innovation program (grant no. 802615). P.G. gratefully acknowledges funding from the Carl-Zeiss Foundation. Y.v.d.B, I.K., and P.G. acknowledge funding from a joint project between the Max Planck Institute for Polymer Research and the Institute for Complex Molecular Systems, Eindhoven\u00A0University of Technology, grant MPIPICMS2019001. We thank Paul Beijer from the Equipment and Prototype Center of TU/e for his contribution to the design and realization of additional electronics. We also acknowledge Ren\u00E9 Janssen for opening his laboratory facilities to us and Irene Dobbelaer-Bosboom, Jaap de Hullu, and Katherine Pacheco Morillo for their assistance in the Microfablab at TU/e. We also acknowledge Paul W. M. Blom for hosting part of the research at the Department of Molecular Electronics, Max Plank Institute for Polymer Research, and Michelle Beuchel and Christian Bauer for their assistance in the clean room facilities of the Max Planck Institute for Polymer Research. We recognize the support of Charles-Th\u00E9ophile Coen and Simone Spolaor. Y.v.d.B gratefully acknowledges funding from the European Research Council under the European Union\u2019s Horizon 2020 research and innovation program (grant no. 802615). P.G. gratefully acknowledges funding from the Carl-Zeiss Foundation. Y.v.d.B, I.K., and P.G. acknowledge funding from a joint project between the Max Planck Institute for Polymer Research and the Institute for Complex Molecular Systems, Eindhoven University of Technology, grant MPIPICMS2019001. We thank Paul Beijer from the Equipment and Prototype Center of TU/e for his contribution to the design and realization of additional electronics. We also acknowledge Ren\u00E9 Janssen for opening his laboratory facilities to us and Irene Dobbelaer-Bosboom, Jaap de Hullu, and Katherine Pacheco Morillo for their assistance in the Microfablab at TU/e. We also acknowledge Paul W. M. Blom for hosting part of the research at the Department of Molecular Electronics, Max Plank Institute for Polymer Research, and Michelle Beuchel and Christian Bauer for their assistance in the clean room facilities of the Max Planck Institute for Polymer Research. We recognize the support of Charles-Th\u00E9ophile Coen and Simone Spolaor.
Keywords
- Neural Networks, Computer
- Learning/physiology
- Humans
- Electronics/instrumentation
- Robotics/instrumentation