no code implementations • 7 Nov 2021 • Eivind Bøhn, Sebastien Gros, Signe Moe, Tor Arne Johansen
Its high computational complexity results in high power consumption from the control algorithm, which could account for a significant share of the energy resources in battery-powered embedded systems.
no code implementations • 22 Feb 2021 • Eivind Bøhn, Sebastien Gros, Signe Moe, Tor Arne Johansen
Model predictive control (MPC) is a powerful trajectory optimization control technique capable of controlling complex nonlinear systems while respecting system constraints and ensuring safe operation.
1 code implementation • 26 Nov 2020 • Eivind Bøhn, Sebastien Gros, Signe Moe, Tor Arne Johansen
In control applications there is often a compromise that needs to be made with regards to the complexity and performance of the controller and the computational resources that are available.
no code implementations • L4DC 2020 • Signe Moe, Filippo Remonato, Esten Ingar Grøtli, Jan Tommy Gravdahl
Recurrent Neural Networks (RNNs) have a form of memory where the output from a node at one timestep is fed back as input the next timestep in addition to data from the previous layer.
no code implementations • 21 Nov 2019 • Eivind Bøhn, Signe Moe, Tor Arne Johansen
Reinforcement Learning in domains with sparse rewards is a difficult problem, and a large part of the training process is often spent searching the state space in a more or less random fashion for any learning signals.