Perception-aware Exploration for Consumer-grade UAVs
Enables autonomous exploration for low-cost, consumer-level UAVs, addressing a gap in applying SOTA methods to resource-constrained platforms.
Extended multi-UAV exploration to consumer-grade UAVs by selecting viewpoint pairs for depth estimation and planning trajectories that satisfy odometry motion constraints, with a semi-distributed communication scheme for balanced workload. Demonstrated safe exploration and map reconstruction in simulation despite hardware limitations.
In our work, we extend the current state-of-the-art approach for autonomous multi-UAV exploration to consumer-level UAVs, such as the DJI Mini 3 Pro. We propose a pipeline that selects viewpoint pairs from which the depth can be estimated and plans the trajectory that satisfies motion constraints necessary for odometry estimation. For the multi-UAV exploration, we propose a semi-distributed communication scheme that distributes the workload in a balanced manner. We evaluate our model performance in simulation for different numbers of UAVs and prove its ability to safely explore the environment and reconstruct the map even with the hardware limitations of consumer-grade UAVs.