In this talk I will present our ICRA 2021 paper "Trajectory Optimisation in Learned Multimodal Dynamical Systems via Latent-ODE Collocation".
Synergising Bayesian inference and Riemannian geometry for control in multimodal dynamical systems.
This talk presented recent work synergising Bayesian inference and probabilistic Riemannian geometries to control multimodal dynamical systems (quadcopters). The work combines theory from probabilistic Riemannian geometry, that addressed issues of …
This work presents a two-stage method to perform trajectory optimisation in multimodal dynamical systems with unknown nonlinear stochastic transition dynamics. The method finds trajectories that remain in a preferred dynamics mode where possible and in regions of the transition dynamics model that have been observed and can be predicted confidently.
The first stage leverages a mixture of Gaussian process experts method (mogpe) written in GPflow/TensorFlow to learn a predictive dynamics model from historical data.
This work introduces a variational lower bound for the Mixture of Gaussian Process Experts model with a GP-based gating network based on sparse GPs. The model (and inference) are implemented in GPflow/TensorFlow.
This post introduces the theory underpinning Gaussian process regression and provides a basic walk-through in python.