Learning quadrotor maneuvers from optimal control and generalizing in real-time

In this paper, we present a method for learning and online generalization of maneuvers for quadrotor-type vehicles. The maneuvers are formulated as optimal control problems, which are solved using a general purpose optimal control solver. The solutions are then encoded and generalized with Dynamic Movement Primitives (DMPs). This allows for real-time generalization to new goals and in-flight modifications. An effective method for joining the generalized trajectories is implemented. We present the necessary theoretical background and error analysis of the generalization. The effectiveness of the proposed method is showcased using planar point-to-point and perching maneuvers in simulation and experiment.     «

In this paper, we present a method for learning and online generalization of maneuvers for quadrotor-type vehicles. The maneuvers are formulated as optimal control problems, which are solved using a general purpose optimal control solver. The solutions are then encoded and generalized with Dynamic Movement Primitives (DMPs). This allows for real-time generalization to new goals and in-flight modifications. An effective method for joining the generalized trajectories is implemented. We present th...     »

autonomous aerial vehicles; error analysis; helicopters; learning systems; mobile robots; optimal control; telerobotics; DMP; UAV; dynamic movement primitives; error analysis; general purpose optimal control solver; in-flight modifications; online maneuver generalization; optimal control problems; perching maneuvers; planar point-to-point maneuvers; quadrotor maneuver learning; quadrotor-type vehicles; real-time generalization; unmanned aerial vehicles; Acceleration; Damping; Force; Optimal control; Optimization; Real-time systems; Trajectory     «

autonomous aerial vehicles; error analysis; helicopters; learning systems; mobile robots; optimal control; telerobotics; DMP; UAV; dynamic movement primitives; error analysis; general purpose optimal control solver; in-flight modifications; online maneuver generalization; optimal control problems; perching maneuvers; planar point-to-point maneuvers; quadrotor maneuver learning; quadrotor-type vehicles; real-time generalization; unmanned aerial vehicles; Acceleration; Damping; Force; Optimal cont...     »