Multi-target-point tracking obstacle avoidance method and device for unmanned aerial vehicle

The invention discloses a multi-target-point tracking obstacle avoidance method and device for an unmanned aerial vehicle, and the method comprises the steps: determining more than one path tracking point according to a global path of the unmanned aerial vehicle and the current position of the unmanned aerial vehicle, and enabling the global path to be a path plan for the unmanned aerial vehicle to fly from a path starting point to a path end point; based on the path end point and each path tracking point, state input data is obtained, and the state input data comprises laser radar data, the current action state of the unmanned aerial vehicle, the relative position of the unmanned aerial vehicle and the path end point and the relative position of the unmanned aerial vehicle and each path tracking point; obtaining a trained deep reinforcement learning model; and inputting the state input data to the trained deep reinforcement learning model to obtain an action instruction output by the trained deep reinforceme