The unaffordable computation load of nonlinear model predictive control (NMPC) has prevented it for being used in robots with high sampling rates decades. This paper is concerned the policy learning problem MPC system constraints, where learned offline and deployed online to resolve computational complexity issue. A deep neural networks (DNN) based (PL-MPC) method proposed avoid solving optimal...

This paper deals with the development and analysis of novel time-optimal point-to-point model predictive control concepts for nonlinear systems. Recent approaches in literature apply a time transformation, however, which do not maintain recursive feasibility piecewise constant parameterization. The key idea this is to introduce uniform grids variable discretization. A shrinking-horizon grid ada...

In a dynamic distribution market environment, residential prosumers with solar power generation and battery energy storage devices can flexibly interact the grid via exchange. Providing schedule for this bidirectional dispatch facilitate operational planning operator bring additional benefits to some economic incentives. However, major obstacle achieving win–win situation is difficulty in: 1) p...