UESMANN is the subject of my recently completed PhD, and is a rather odd kind of artificial neural network which can modulate between multiple behaviours. It is inspired by how neuromodulators change the behaviour of neurons in biology.
My PhD thesis, exploring the UESMANN neural network architecture which can learn two (or possibly more) functions in a single set of weights and can be trained using gradient descent.
A look at how well UESMANN performs in a homeostatic robot problem.
A brief introduction to the UESMANN network which is further explored in my thesis.
A simple method for balancing motor load in wheeled rovers using a simulation of cytokine mediated allodynia: simply put, when a particular wheel motor "gets sore" (i.e. has a high operating temperature) the rover lowers the power to it.
Comparing two walking gaits with normal rolling on a Mars simulant surface, using leg deployment motors on a rover modelled after the ExoMars chassis. An artificial endocrine system is used to switch gaits, which are implemented with a Brooks …