Achieving multi uav best viewpoint coordination in obstructed environments

Abstract

Wildfire suppression is a complex task that poses high risks to humans. Using robotic teams for wildfire suppression enhances the safety and efficiency of detecting, monitoring, and extinguishing fires. We propose a control architecture based on task hierarchical control for the autonomous steering of a system of flying robots in wildfire suppression. We incorporate a novel line-of-sight obstacle avoidance method that calculates the best viewpoints and ensures an occlusion-free view for the suppression robot during the mission. Path integral control generates optimal trajectories towards the goals. We conduct an ablation study to assess the effectiveness of our approach by comparing it to scenarios where these key components are excluded, in order to validate the approach in simulations using Matlab and Unity. The results demonstrate significant performance improvements, with 44.0 % increase in effectiveness with the new line-of-sight obstacle avoidance task and up to 39.6 % improvement when using path integral control.

Figures (5)

• Figure 1: Illustration for avoiding obstacles on the LoS: $\bm{p}^\textup{main}(k)$ and $\bm{p}^\textup{aux}(k)$ are points where the main and auxiliary UAVs are respectively located; $\bm{p}^\textup{obs}$ is the center of volume of obstacle $\mathcal{O}$; $\alpha$ is the imposed distance between the two UAVs; $\theta$ is the angle of the FoV; $\bm{p}_1(k)$, $\bm{p}_2(k)$ and $\bm{p}_3(k)$ are intersection points. In the figure, we avoid the use of $k$ for making the illustrations less busy.
• Figure 2: Cases of the threshold (1 to 3, respectively, from left to right): $\bm{p}^\textup{main}(k)$ and $\bm{p}^\textup{aux}(k)$ are the points where main UAV and auxiliary UAV are located, respectively, while $\bm{p}^\textup{obs}$ is the center of volume of obstacle $\mathcal{O}$. Moreover, $\theta$ is the FoV angle, and $\bm{p}_1(k)$, $\bm{p}_2(k)$, $\bm{p}_3(k)$ represent the considered intersection points. In the figure, we avoid the use of $k$ for making the illustrations less busy.
• Figure 3: Illustration of the scenario simulated in Unity: From left to right, the 3D view of the simulated outdoor environment, the top and side views of the environment, and views of the cameras of the two auxiliary UAVs. The main UAV has cyan color, the auxiliary UAVs have red and orange colors.
• Figure 4: Comparison of the intersection of the FoV with obstacles, with LoS obstacle avoidance task active (blue) or inactive (red): volume of intersection of FoV with obstacles (occluded view). Plots from left to right represent the results for scenarios from 1 to 5.
• Figure 5: Comparison of the distance between main UAV and auxiliary UAV 1 (top plots) and 2 (bottom plots), with the distance task active (blue curves) or inactive (red curves). The black dashed lines indicate the desired distance. Plots from left to right represent the results for scenarios from 1 to 5.

Theorems & Definitions (4)

• Theorem 1
• proof
• Remark 1
• Remark 2