This paper proposes a motion planning method which focuses on the consideration of moving 3D objects along the route of the unmanned vehicles. The goal of the method is to detect conflict situations and to avoid collisions to the objects. The proposed method continuously recognizes conflict situations using a clustering algorithm. The motion planning with a reinforcement-learning-based (RL) agent is facilitated, which can result in efficient and collision-free motion. The effectiveness of the method is illustrated on the route planning for an unmanned drone, which has to fly in an area with moving obstacles.