Data-driven Fuzzy Control for Time-Optimal Aggressive Trajectory Following

TL;DR

This work presents a data-driven fuzzy controller synthesis framework that is guided by a time-optimal trajectory for multicopter tracking problems and considers an aggressive maneuver consisting of a mid-air flip and generates a time-optimal trajectory by numerically solving the two-point boundary value problem.

Abstract

Optimal trajectories that minimize a user-defined cost function in dynamic systems require the solution of a two-point boundary value problem. The optimization process yields an optimal control sequence that depends on the initial conditions and system parameters. However, the optimal sequence may result in undesirable behavior if the system's initial conditions and parameters are erroneous. This work presents a data-driven fuzzy controller synthesis framework that is guided by a time-optimal trajectory for multicopter tracking problems. In particular, we consider an aggressive maneuver consisting of a mid-air flip and generate a time-optimal trajectory by numerically solving the two-point boundary value problem. A fuzzy controller consisting of a stabilizing controller near hover conditions and an autoregressive moving average (ARMA) controller, trained to mimic the time-optimal aggressive trajectory, is constructed using the Takagi-Sugeno fuzzy framework.

Figures (10)

• Figure 1: A bicopter.
• Figure 2: Implementation of LBFSF controller.
• Figure 3: Implementation of ARMA controller.
• Figure 4: Optimal trajectory of the bicopter with a flip maneuver computed by solving a nonlinear program using CasADi.
• Figure 5: Bicopter states and inputs in the optimal trajectory.