Sweep-Your-Map: Efficient Coverage Planning for Aerial Teams in Large-Scale Environments

Abstract

The efficiency of path-planning in robot navigation is crucial in tasks such as search-and-rescue and disaster surveying, but this is emphasized even more when considering multirotor aerial robots due to the limited battery and flight time. In this spirit, this work proposes an efficient, hierarchical planner to achieve comprehensive visual coverage of large-scale outdoor scenarios for small drones. Following an initial reconnaissance flight, a coarse map of the scene gets built in real-time. Then, regions of the map that were not appropriately observed are identified and grouped by a novel perception-aware clustering process that enables the generation of continuous trajectories (sweeps) to cover them efficiently. Thanks to this partitioning of the map into a set of tasks, we can generalize the planning to an arbitrary number of drones and perform a well-balanced workload distribution among them. We compare our approach against a state-of-theart method for exploration and show the advantages of our pipeline in terms of efficiency for obtaining coverage in large environments. Video -https://youtu.be/V2UIrM91oQ8

Fast Multi-UAV Decentralized Exploration of Forests

“…To this end, Burgard et al [12] aims at reducing the overlap in explored areas, by down-scaling the information gain of a candidate frontier if another robot is assigned to a different frontier in its vicinity, while Tian et al [15] solve a Multiple Travelling Salesman Problem (mTSP) to allocate each agent to a candidate frontier. Instead, the approach in [16] is able to generate efficient trajectories for 3D reconstruction. However, this method requires a prior overhead flight over the area of interest, making it unsuitable for the exploration of forests.…”

Coordinated Multi-Agent Exploration, Rendezvous, & Task Allocation in Unknown Environments with Limited Connectivity

“…Multi-robot systems (MRS) have the potential to assist in many safety-critical applications such as search and rescue, military intelligence and surveillance, and inspection operations where it may be hazardous and costly to deploy humans. Looking to the state-of-the-art, we note that most MRS research assumes constant communication between robots [1]- [3]. However, within the aforementioned application space, long-range communication is often unreliable or unavailable.…”