Perception-Aware Communication-Free Multi-UAV Coordination in the Wild

Manuel Boldrer; Michal Kamler; Afzal Ahmad; Martin Saska

cs.ROMar 9, 2026

Perception-Aware Communication-Free Multi-UAV Coordination in the Wild

Authors: Manuel Boldrer, Michal Kamler, Afzal Ahmad, Martin Saska

Organizations: Department of Cybernetics, Czech Technical University in Prague, Karlovo namesti 13, 121 35 Prague 2, Czechia.

Abstract

We present a communication-free method for safe multi-robot coordination in complex environments such as forests with dense canopy cover, where GNSS is unavailable. Our approach relies on an onboard anisotropic 3D LiDAR sensor used for SLAM as well as for detecting obstacles and neighboring robots. We develop a novel perception-aware 3D navigation framework that enables robots to safely and effectively progress toward a goal region despite limited sensor field-of-view. The approach is evaluated through extensive simulations across diverse scenarios and validated in real-world field experiments, demonstrating its scalability, robustness, and reliability.

Figures & tables

Figure 1: Snapshot during a real-world experiment in the forest with $3$ UAVs.

EGO2 [ 3 ]	RMADER [ 5 ]	PACNAV [ 6 ]	RBL [ 4 ]	HDSM [ 7 ]	RVC-NMPC [ 8 ]	Chen et al. [ 9 ]	DREAM [ 10 ]	AMSWARM [ 11 ]	Choi et al. [ 12 ]	iRBL (our)

Table I : Qualitative comparison with state-of-the-art algorithms on the aspects of interest (i.e., implicit coordination ( ), anisotropic perception ( ), test in the wild ( ) and operational speed ( )). We indicate with “ ” if the algorithm does not implement the feature, “ ” if it does, and “ ” if it does only partially. In the last row the operational speed is indicated with arrows, where “ ” indicates poor performance, “ ” indicates high performance, while “ ” and “ ” indicate intermediate low and intermediate high performance respectively.

Figure 2: Graphical representation of the sensor field-of-view

\mathrm{FoV}=\{f_{x},f_{z},f_{a}\}\penalty\ (\deg)

Figure 3: 2D Graphical representation of the set

\mathcal{A}_{i}

. On the left, the case where the robots are separated by more than

2\Delta_{ij}

; on the right, the case where they are separated by less than

2\Delta_{ij}

. The half-spaces are constructed according to ( 1 ) such that all the points are collision-free.

Figure 4: 2D Graphical representation of the set

\mathcal{C}_{i}

(which in this particular case correspond also with the set

\mathcal{B}_{i}

) computed using the proposed seeds. The obstacles are represented by grey circles.

Figure 5: Illustration of the main variables associated with the $i$ -th robot during a real-world experiment. The robot’s pose $p_{i}$ is shown as an axis reference frame. The set $\mathcal{W}_{i}$ is represented by the magenta set, and the centroid position $c_{\mathcal{B}_{i}}$ is shown in orange. The planned path is depicted by a red line. The $wp_{i}$ and $e_{i}$ indicate respectively the active waypooint and the final goal positions. Other robots positions $p_{j}$ are indicated by a grey box. The colored point cloud illustrates obstacles, with different colors corresponding to different z-values.

Figure 6: Block diagram representation of the proposed pipeline.

Figure 7: Top view of the robot’s trajectory using iRBL in an environment with low traversability ( $\tau=1.57$ ), where EGO2 [ 17 ] and RBL [ 4 ] are unable to successfully navigate. The color scale represents the robot’s velocity, as indicated by the colorbar.

	$\tau$ (m)	$l$ (m)	$t$ (s)	$\bar{v}$ (m/s)	$d^{o}_{min}$ (m)	SR
EGO2 [ 17 ]	3.566	31.37	15.17	2.07	0.486	0.4 $\|$ 1 $\|$ 1
	2.036	36.01	20.32	1.82	0.46	0 $\|$ 1 $\|$ 1
	1.142	35.25	23.20	1.51	0.52	0.2 $\|$ 0.2 $\|$ 0.8
	0.984	-	-	-	-	0.0 $\|$ 0.0 $\|$ 0.8
RBL [ 4 ]	3.566	36.31	52.9	0.68	0.45	1 $\|$ 0.6 $\|$ 1
	2.036	34.56	71.92	0.48	0.43	1 $\|$ 0.4 $\|$ 1

Table II : Comparison with state-of-the-art. Simulation with

N=1

robot and

\delta_{i}=0.2

m in

4

different cluttered environments. We report the traversability

\tau

, the length of the path

l

, the time to reach the goal

t

, the average speed

\bar{v}

, the minimum distance to obstacles

d^{o}_{min}

, and the success rate SR in terms of violation of acceleration limits, covergence to the goal, and safety (

d^{o}_{min}\geq\delta_{i}

). We repeat each scenario

10

times, and report the average results. All the parameters are kept the same for all the different scenarios.

Panel of Figure 8 — Figure 8: Top view for the robots’ trajectories with the iRBL half FoV case and $\delta_{i}=0.2$ (m), in three different scenarios. The crossing circle without obstacle ( $N=10$ ), crossing circle with obstacles ( $N=10$ ) and forest-like environment ( $N=5$ ). The color indicates the velocities according to the colorbars.

	$\tau$ (m)	$\delta_{i}$ (m)	$l$ (m)	$t$ (s)	$\bar{v}$ (m/s)	$d_{\min}$ (m)
iRBL (lim.FoV)	-	0.2	33.14	23.43	1.41	0.737
	-	0.5	33.99	26.72	1.26	1.155
	-	1.0	35.51	33.95	1.04	2.17
iRBL (half FoV)	-	0.2	33.56	22.14	1.50	0.729
	-	0.5	34.30	25.09	1.35	1.402
	-	1.0	35.14	27.62	1.26	2.092

Table III : Simulation results with

N=10

robots in a crossing circle scenario without obstacles. We report the length of the path

l

, the time to reach the goal

t

, the average speed

\bar{v}

, and the minimum distance between the robots

d_{\min}

. We considered

4

different field-of-views (FoV). The limited FoV {180,59,-20} (deg), half FoV {180,180,-90} (deg), full FoV {180,360,0} (deg), and the two-dimensional case {360,0,0} (deg).

	$\tau$ (m)	$\delta_{i}$ (m)	$l$ (m)	$t$ (s)	$\bar{v}$ (m/s)	$d_{\min}$ (m)
iRBL (lim. FoV)	6.56	0.2	32.46	23.24	1.40	0.661
	4.60	0.5	35.83	33.07	1.08	1.165
	2.21	1.0	38.54	55.06	0.69	2.199
iRBL (half FoV)	6.56	0.2	32.70	23.74	1.37	0.878
	4.60	0.5	35.99	34.47	1.04	1.178
	2.21	1.0	38.17	43.75	0.86	2.119

Table IV : Simulation results with

N=10

robots in a crossing circle scenario with obstacles. We report the traversability

\tau

, the length of the path

l

, the time to reach the goal

t

, the average speed

\bar{v}

, and the minimum distance between the robots

d_{\min}

. We considered

4

different field-of-views (FoV). The limited FoV {180,59,-20} (deg), half FoV {180,180,-90} (deg), full FoV {180,360,0} (deg), and the two-dimensional case {360,0,0} (deg).

	$\tau$ (m)	$\delta_{i}$ (m)	$l$ (m)	$t$ (s)	$\bar{v}$ (m/s)	$d_{\min}$ (m)
iRBL (lim. FoV)	8.67	0.2	34.58	26.83	1.28	0.976
	7.01	0.5	36.51	30.94	1.18	1.723
	4.17	1.0	39.60	52.31	0.76	2.216
iRBL (half FoV)	8.67	0.2	35.10	26.52	1.33	1.151
	7.01	0.5	36.94	30.25	1.22	1.768
	4.17	1.0	37.31	34.77	1.07	2.235

Table V : Simulation results with

N=5

robots in a forest-like environment. We report the traversability

\tau

, the length of the path

l

, the time to reach the goal

t

, the average speed

\bar{v}

, and the minimum distance between the robots

d_{\min}

. We considered

4

different field-of-views (FoV). The limited FoV {180,59,-20} (deg), half FoV {180,180,-90} (deg), full FoV {180,360,0} (deg), and the two-dimensional case {360,0,0} (deg).

Panel of Figure 9 — Figure 9: Different experimental scenarios. The top row contains snapshots from the camera, while the bottom row shows the corresponding snapshots extracted from RViz for the same experiment. Similarly to Figure 5 , the robot pose is represented by an axis reference frame. The set $\mathcal{W}_{i}$ is depicted as blue dots, and the centroid $c_{\mathcal{B}_{i}}$ as an orange sphere. The planned path is shown as a red line. The active waypoint $wp_{i}$ lies on the planned path and is represented by a purple sphere. The grey boxes represent the positions of the other robots. The colored point cloud represents obstacles, where different colors correspond to different $z$ -values. The “eye” symbol indicates the robot whose viewpoint is currently shown in the bottom RViz visualization.

Panel of Figure 10 — Figure 10: Different viewpoints from experiment #1 in Table VI . We depict the trajectories followed by the two robots during the mission. The robots’ velocities can be inferred from the color-bars on the right-hand side. Different colors in the point cloud indicate different $z$ -values.

scenario	uav	$\tau$ (m)	$l$ (m)	$t$ (s)	$\bar{v}$ (m/s)	$v_{\max}$ (m/s)
#1 (40m)	1	3.10	45.77	23.00	1.99	2.60
#1 (40m)	2	3.10	41.98	23.45	1.79	2.85
#2 (80m)	1	16.02	86.97	35.07	2.48	2.79
	2	16.02	91.02	45.51	2.00	2.69
	3	16.02	94.34	53.00	1.78	2.81
#3 (40m)	1	6.73	46.06	23.03	2.00	3.32

Table VI : Quantitative results of experiments in three different scenarios. All the scenarios involve UAVs starting from close positions and with close goal locations. For all the scenarios we report the traversability

\tau

, the length of the path

l

, the time to reach the goal

t

, the average speed

\bar{v}

, and the maximum velocity achieved

v_{\max}

. The mission environments of scenario 1,2 and 3 are illustrated respectively in Figure 9 -(a),(b) and (c).

Explore similar work

Unsupervised Multi-agent and Single-agent Perception from Cooperative Views
Apr 7, 2026Haochen Yang, Baolu Li, Lei Li +5Lidar-Based 3D Object Detection 3D Object Detection
Cleveland State University
Collaborative Navigation and Exploration with $β$ -Sparse Gaussian Processes
May 25, 2026Evangelos Psomiadis, Dipankar Maity, Panagiotis TsiotrasMulti-Robot Systems Robot Navigation
D. Guggenheim School of Aerospace Engineering, Georgia Tech, Atlanta, GA, USA · Department of Electrical and Computer Engineering, UNC Charlotte, Charlotte, NC, USA
Line-of-Sight-Constrained Multi-Robot Mapless Navigation via Polygonal Visible Regions
Mar 27, 2026Ruofei Bai, Shenghai Yuan, Xinhang Xu +5Robot Navigation Multi-Robot Coordination

Apr 7, 2026J/K move · Enter open · S save

Unsupervised Multi-agent and Single-agent Perception from Cooperative Views

Haochen Yang, Baolu Li, Lei Li, Delin Ren+4

Cleveland State University

Lidar-Based 3D Object Detection 3D Object Detection Cooperative Perception

Open paper AskPDF arXiv

The LiDAR-based multi-agent and single-agent perception has shown promising performance in environmental understanding for robots and automated vehicles. However, there is no existing method that simultaneously solves both multi-agent and single-agent perception in an unsupervised way. By sharing sensor data between multiple agents via communication, this paper discovers two key insights: 1) Improved point cloud density after the data sharing from cooperative views could benefit unsupervised object classification, 2) Cooperative view of multiple agents can be used as unsupervised guidance for the 3D object detection in the single view. Based on these two discovered insights, we propose an Unsupervised Multi-agent and Single-agent (UMS) perception framework that leverages multi-agent cooperation without human annotations to simultaneously solve multi-agent and single-agent perception. UMS combines a learning-based Proposal Purifying Filter to better classify the candidate proposals after multi-agent point cloud density cooperation, followed by a Progressive Proposal Stabilizing module to yield reliable pseudo labels by the easy-to-hard curriculum learning. Furthermore, we design a Cross-View Consensus Learning to use multi-agent cooperative view to guide detection in single-agent view. Experimental results on two public datasets V2V4Real and OPV2V show that our UMS method achieved significantly higher 3D detection performance than the state-of-the-art methods on both multi-agent and single-agent perception tasks in an unsupervised setting.

Abstract

Explore similar work

Unsupervised Multi-agent and Single-agent Perception from Cooperative Views

Collaborative Navigation and Exploration with βββ-Sparse Gaussian Processes

Line-of-Sight-Constrained Multi-Robot Mapless Navigation via Polygonal Visible Regions

Collaborative Navigation and Exploration with $β$ -Sparse Gaussian Processes