The Bella Project
This project aims to develop a robot platform, driven by artificial muscles, that has compliant touch (whiskers) and vision (artificial eye) systems. Bio-inspired sensory motor control algorithms based on a cerebellar chip will be used to control the robot platform.
Artificial muscles are soft, compliant actuators, with large strain capability, a relatively fast response and the capacity for self sensing. Such actuators are key to the development of safe, soft, compliant robots capable of operating in human centred, unstructured environments.
The control of these artificial muscles is challenging. We aim to develop bio-inspired controllers, based on the cerebellum. Such control systems aim to exploit the ability of the cerebellum to adapt to changes, and fine tune performance in a wide range of sensory and motor tasks.
More details on the Cerebellar EAP project.
This project uses robots to apply and evaluate novel, biological inspired algorithms for adaptive control.
The particular control platform studied is the biological control system for gaze stabilisation.
More details on the Eye-Robot project.
Adaptive Cancellation of Self Generated Signals
We investigate the problem of discriminating between self-generated sensory signals and signals generated by the external environment
in the context of a whiskered robot. The whisker sensory signal
comprises two components: one due to contact with an object (externally-generated) and another due to active movement of the
whisker (self-generated). We propose a solution to this discrimination problem based on adaptive noise cancellation, where the
robot learns to predict the sensory consequences of its own movements using an adaptive filter. This work was done as part of the Biotact Project .