Robust UAV coordination for target tracking using output-feedback model predictive control with moving horizon estimation

A Predictive Deep Learning Approach to Output Regulation: The Case of Collaborative Pursuit Evasion

“…In this paper the pursuers do not have an a-priori knowledge of the evader's game or its structure, and they employ an NN in real time to identify its input-output mapping. We use our tracking-control technique [7] rather than MPC, and obtain similar results to [22]. Furthermore, the input to the system has a lesser dimension that its output, and hence the control is underactuated.…”

“…Recently, authors of this paper have applied NN for on-line model construction in a control application [21]. This paper applies an NN technique to the pursuit-evasion problem investigated in [22], which is more challenging than the problem addressed in [21]. The strategies of both pursuers and evader are based on respective games.…”

“…In Ref. [22], the pursuers know the game of the evader ahead of time, and an MPC technique is used to determine their trajectories. In this paper the pursuers do not have an a-priori knowledge of the evader's game or its structure, and they employ an NN in real time to identify its input-output mapping.…”

A Robust Reach Set MPC Scheme for Control of AUVs

“…A wide variety of MPC controllers for formations of robotic vehicles were designed to deal with key challenges such as communications failures and delays in continuum and discrete times, centralized and decentralized contexts, linear and nonlinear dynamics, leader-follower and leaderless schemes, collision-free motion, cooperative and competitive strategies, single and multiple objectives. Moreover, a wide range of applications (surveillance, exploration, tracking paths and trajectories), have been considered in a vast literature of which we single out 15,16,17,18,19,20,21,22,23 . The power and computational requirements for running most of these MPC schemes in a are weakly suitable for AUVs: (i) intense on-line computational burden, and (ii) design issues to ensure the required performances do note consider onboard resource constraints.…”

Model predictive control and moving horizon estimation for water level regulation in inland waterways

“…Unlike MPC, this estimation technique started receiving wider attention only in the recent years [9]. Indeed, the combination of MPC and MHE has been applied in diverse fields such as autonomous agricultural vehicles [10], unmanned aerial vehicles [11], preventive sensor maintenance [12], airborne wind energy systems [13] and blood glucose regulation [14]. Concerning water systems, the combination of these techniques is not so common, although it has been used for flood prevention in rivers [15] and pollution mitigation for combined sewer networks [16].…”