Walk the Robot: Exploring Soft Robotic Morphological Communication driven by Spiking Neural Networks
By: Matthew Meek , Guy Tallent , Thomas Breimer and more
Potential Business Impact:
Robot parts talk to each other using wiggles.
Recently, researchers have explored control methods that embrace nonlinear dynamic coupling instead of suppressing it. Such designs leverage dynamical coupling for communication between different parts of the robot. Morphological communication refers to when those dynamics can be used as an emergent data bus to facilitate coordination among independent controller modules within the same robot. Previous research with tensegrity-based robot designs has shown that evolutionary learning models that evolve spiking neural networks (SNN) as robot control mechanisms are effective for controlling non-rigid robots. Our own research explores the emergence of morphological communication in an SNN-based simulated soft robot in theEvoGym environment.
Similar Papers
Designing morphologies of soft medical devices using cooperative neuro coevolution
Neural and Evolutionary Computing
Designs soft robots that deliver medicine inside you.
Balancing Centralized Learning and Distributed Self-Organization: A Hybrid Model for Embodied Morphogenesis
Artificial Intelligence
Makes patterns grow like magic, faster and smarter.
Co-design is powerful and not free
Neural and Evolutionary Computing
Robots learn better by changing their bodies.