The honeybee waggle dance motivates a communication mechanism in which one agent's motion guides the subsequent work of other agents. For aerial robots, realizing this mechanism requires a link from observed movement to a complete message, local task selection, and execution. This paper presents a MuJoCo system for comparing RGB and synthetic event vision within that link. One performer broadcasts six-bit task offers to one to three observers, each of which independently decodes both offers before selecting a task. The RGB receiver extracts trajectories using sparse optical flow; the event receiver uses only local event support and packet timing. Both use a common motion alphabet and explicit null delimiters. Because event silence does not establish target visibility, the event version includes a physical acquisition motion and continuity-qualified null confirmation. In the nominal three-observer case, each version produced 12 complete message receptions, six completed work units, and reassignment after withdrawal of a depleted task. Six paired functional cases produced the same message and work counts; an additional event-stream dropout case preserved inactivity of the affected observer. Replaying 42,060,633 recorded synthetic events reproduced all 12 event-message payloads and completion timestamps. Total nominal mission time was 493.80 s for RGB and 517.40 s for events, with the difference dominated by the event acquisition schedule. These fixed simulation results establish functional feasibility across two receiver implementations, rather than a sensor-performance advantage or hardware validation.
Figures & tables
Figure 1: Research motivation and scope. (a) The biological inspiration is a functional link from dance advertisement to recruited work. (b) Within the MoCom research line, point-to-point communication and multi-observer navigation motivate a task-level extension to offers, allocation, and reassignment. (c) The study compares alternative RGB and synthetic-event receivers under the same task semantics, examines conditional event silence, and links each observer’s decoding to its own action. Icons and event dots are schematic; task maps and flight-safety infrastructure remain shared.
Figure 2: Two visual frontends connect motion signaling to recruitment. (a) Alternative RGB and synthetic-event receiving chains feed the same framing and allocation logic, instantiated separately for each observer. Event generation uses rendered luminance, while event recognition has no RGB input. Navigation and scheduling retain shared simulation support. (b) The nominal three-observer sequence: two observers work at A and one at B, then a withdrawal offer redirects all three to B. Arrows represent information or task transitions, not measured flight paths.
Figure 3: Principle of motion-mediated recruitment. (a) Closed image-plane primitives encode the four action symbols. (b) Alternative sensing paths estimate motion from RGB feature displacement or synthetic event support. (c) Six payload bits and nine observed NULL delimiters form a complete frame; its final NULL releases an offer, and task selection requires both A and B offers. Event NULL also requires prior closed-path acquisition, near-anchor quiet, continuous valid packets, and time-limited tracking. Silence cannot prove continued target visibility. Traces and event dots are schematic, not recorded measurements.
Setting
RGB
Synthetic events
Image resolution
640×480
640×480
Source / receiver rate
25 / 25 Hz
100 / 25 Hz
Trajectory measurement
Robust KLT displacement
Local event-support center
Minimum path support
12 points, 28 px span
12 points, 28 px span
Best-template error limit
0.17
0.21
Runner-up error margin
0.075
0.065
Table 1: Receiver settings used in the reported runs. Values differ by frontend; this is a comparison of complete implementations.
Figure 4: Corresponding observer-camera outputs during (a) acquisition motion, (b) acquired quiet, and (c) transmission of bit 0 (V). Top: actual MuJoCo RGB renders at the indicated times. Bottom: synthetic events from the same camera over the preceding 40 ms; blue denotes ON and red OFF, with the last polarity shown at each active pixel. White denotes no events. Each pair uses identical 80×60 px inset bounds; the full 640×480 field remains visible. Phase labels describe session context and receiver history, not classification from one packet. These are simulation outputs, not physical camera recordings.
Complete messages
Work units
Time (s)
Case
RGB
Events
RGB
Events
RGB
Events
1 observer
4
4
2
2
451.56
475.16
2 observers
4/4
4/4
4
4
463.16
486.76
3 observers
4/4/4
4/4/4
6
6
493.80
517.40
O2 black input
4/0/4
4/0/4
4
4
454.48
478.08
No broadcast
0/0/0
0/0/0
0
0
15.04
15.04
Table 2: Final functional cases. Each row is one fixed run per available modality. Message vectors follow O1/O2/O3 order. All listed runs met their expected outcome and recorded zero contact steps. A dash denotes an untested RGB condition, not a failure.
Measurement
RGB
Synthetic events
First offer broadcast start
5.002
16.850
Offer start to final NULL , observed range
95.570–95.638
95.520–95.590
Latest final reception
448.000
471.600
Latest reception to mission completion
45.800
45.800
Total mission duration
493.800
517.400
Table 3: Timing in the nominal three-observer missions. All values are simulation seconds. Offer intervals include physical signaling and null confirmation, not just computational processing.
The honeybee waggle dance motivates a communication mechanism in which one agent's movement conveys spatial information that guides other agents' actions. This paper presents a MuJoCo system that extends the point-to-point motion communication setting of MoCom to one performer and multiple observers. A performer broadcasts a six-bit navigation payload using four flight primitives and explicit null signals. Each of one to five observers processes its own onboard RGB images, extracts optical-flow trajectories, recognizes symbols, parses the message, and starts navigation only after confirming its own complete frame. Reception states and execution triggers are separate across observers, while simulation control and safety checks use shared ground truth. With stationary observers, 25 Hz image input, and ideal state-feedback control, a fixed standard suite yielded 44 correct complete messages from 53 receiver exposures across 17 nominal broadcasts; 13 broadcasts passed all group-level decoding and execution checks. Three additional no-message or input-fault controls met their expected outcomes. A separately reported supplemental suite, using the same frozen code at the default geometry, achieved 14 successful receiver exposures across three broadcasts. Near-range and wide-angle configurations exposed tracking and recognition failures, while unsuccessful receivers remained stationary. These finite simulation results support the feasibility of a waggle-dance-inspired broadcast-to-action mechanism under the tested conditions and identify the present perceptual and protocol limits.
Zhang Nengbo
School of Aerospace Engineering, Engineering Campus Universiti Sains Malaysia, 14300 Nibong Tebal, Pulau Pinang, Malaysia
Multi UAV missions in complex environments require the system to understand both the surrounding scene and the intent of a human operator while maintaining feasible task allocation as mission conditions change. This paper presents AgenticSwarm, an agentic framework for semantic perception and adaptive task allocation in heterogeneous multi UAV missions. An agent interprets aerial imagery and natural language instructions to construct a grounded mission representation that links perceived objects and regions with task requirements, capability constraints, and mission dependencies. This information augments a constrained task allocation process in which obstacle aware path feasibility, energy consumption, and protected return home requirements are incorporated before assignment. During execution, changes such as UAV failure, battery degradation, or task modification trigger residual mission reconstruction from the current system state, while completed work and reconnaissance progress are retained. AgenticSwarm is evaluated across five diverse Gazebo environments and an indoor real test environment, demonstrating its ability to connect semantic reasoning with constrained allocation and adaptive multi UAV mission execution. Compared with a Grounding DINO+SAM~2.1 perception baseline, the SAM3-based pipeline improves class-aware recall by 25.2 percentage points (pp) and semantic label accuracy by 29.5 pp. Ablating residual mission replanning increases mean repeated work from 0% to 61.7% and post-event recovery time by 58.6%, highlighting the contribution of adaptive replanning to mission execution.
Muhammad Ahsan Mustafa, Yasheerah Yaqoot, Faryal Batool +3
We present QuadAgent, a training-free agent system for agile quadrotor flight guided by vision-language inputs. Unlike prior end-to-end or serial agent approaches, QuadAgent decouples high-level reasoning from low-level control using an asynchronous multi-agent architecture: Foreground Workflow Agents handle active tasks and user commands, while Background Agents perform look-ahead reasoning. The system maintains scene memory via the Impression Graph, a lightweight topological map built from sparse keyframes, and ensures safe flight with a vision-based obstacle avoidance network. Simulation results show that QuadAgent outperforms baseline methods in efficiency and responsiveness. Real-world experiments demonstrate that it can interpret complex instructions, reason about its surroundings, and navigate cluttered indoor spaces at speeds up to 5 m/s.