Bayesian Optimisation of SLIP model parameters

Bayesian Optimisation of Spring Loaded Inverted Pendulum (SLIP) model to find stable gait patterns

The Spring Loaded Inverted Pendulum (SLIP) gait model can be characterised with various parameters, including spring stiffness, mass of the robot, touchdown angle and leg length. Tuning the parameters can be time consuming and Bayesian Optimisation provides an efficient way for finding the optimal gait parameters.
The user can set the initial conditions of the system and Bayesian optimisation finds the optimal spring stiffness and touchdown angles for the given initial conditions.
Depending on the initial conditions, Bayesian optimisation can find different gait patterns, including walking, running and skipping gait pattern.
See attached pdf file for further information.