ABSTRACT As urban air‐traffic density rises, the risk of mid‐air collisions among low‐altitude logistics drones has become a critical concern. We therefore introduce Dynamic Controlled Interactive Collaborative Fusion (DCICF), a framework that couples multimodal perception with Probabilistic Reciprocal Velocity Obstacles (P‐RVO) modeling to enable safe, cooperative flight in dynamic environments. Simulations with 50 static obstacles yielded zero collisions; in dynamic‐obstacle scenarios the collision rate was 0.083 while each drone completed an average of 2.400 missions; and in clustered multi‐drone tasks the collision rate fell to 0.043 with 2.350 missions per drone. Hardware tests further demonstrated an average decision latency of 120–150 ms, minimum separation distances of > 0.8 m indoors and > 1.2 m outdoors, and a 100% mission‐success rate. Relative to state‐of‐the‐art baselines such as DQN, MILP and RRT*, DCICF offers superior safety, real‐time responsiveness, and scalability, making it a robust solution for urban logistics drone operations.
Zhang et al. (Sun,) studied this question.