AlphaPilot: autonomous drone racing

This paper presents a novel system for autonomous, vision-based drone racing combining learned data abstraction, nonlinear filtering, and time-optimal trajectory planning. The system has successfully been deployed at the first autonomous drone racing world championship: the 2019 AlphaPilot Challenge. Contrary to traditional drone racing systems, which only detect the next gate, our approach makes use of any visible gate and takes advantage of multiple, simultaneous gate detections to compensate for drift in the state estimate and build a global map of the gates. The global map and drift-compensated state estimate allow the drone to navigate through the race course even when the gates are not immediately visible and further enable to plan a near time-optimal path through the race course in real time based on approximate drone dynamics. The proposed system has been demonstrated to successfully guide the drone through tight race courses reaching speeds up to $${8}\,{\hbox {m}/\hbox {s}}$$ 8 m / s and ranked second at the 2019 AlphaPilot Challenge.

Optimal Trajectory Planning of the Variable-Stiffness Flexible Manipulator Based on CADE Algorithm for Vibration Reduction Control

Robotic manipulators are widely used for precise operation in the medical field. Vibration suppression control of robotic manipulators has become a key issue affecting work stability and safety. In this paper an optimal trajectory planning control method to suppress the vibration of a variable-stiffness flexible manipulator considering the rigid-flexible coupling is proposed. Through analyzing the elastic deformation of the variable-stiffness flexible manipulator, a distributed dynamic physical model of the flexible manipulator is constructed based on the Hamilton theory. Based on the mathematical model of the system, the design of the vibration damping controller of the flexible manipulator is proposed, and the control system with nonlinear input is considered for numerical analysis. According to the boundary conditions, the vibration suppression effect of the conventional and the variable-stiffness flexible manipulator is compared. The motion trajectory of the variable-stiffness flexible manipulator and compare the vibration response from different trajectories. Then, with minimum vibration displacement, minimum energy consumption and minimum trajectory tracking deviation as performance goals, the trajectory planning of the variable-stiffness flexible manipulator movement is carried out based on the cloud adaptive differential evolution (CADE) optimization algorithm. The validity of the proposed trajectory planning method is verified by numerical simulation.