Sensor-Driven Mission Synthesis for UAV/UGV Swarms: A TB-CSPN Coordination Architecture with Hardware-Enforced Safety
Authors: Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi
Organizations: Institute for Software Technology, University of the Bundeswehr Munich, 85579 Neubiberg, Germany · Department of Computer Science, Sapienza University of Rome, 00161 Rome, Italy · SofTware And Knowledge Engineering Lab, STAKE lab, 86100 Campobasso, Italy
This paper presents a coordination architecture for heterogeneous UAV/UGV swarms that synthesises mission actions from uncertain, multi-modal sensor evidence while preserving hardware-enforced safety at the actuation boundary. The approach combines radar, RF, acoustic, and visual observations with Topic-Based Communication Space Petri Net (TB-CSPN) orchestration to support incremental mission formation under partial and evolving information. Consultant agents transform sensor outputs into temporally bounded semantic tokens, while supervisor agents provide authorisation and policy-governed release of mission transitions. This separation between interpretation, coordination, and execution yields auditable decision paths, constrains non-determinism within the coordination layer through guards and synchronisation, and enables bounded-time integration of heterogeneous evidence. To improve resilience in contested environments, including cyber compromise, spoofing, jamming, and communication loss, the digital coordination layer is complemented by independent analogue safety envelopes that clamp or veto unsafe actuator commands issued to individual vehicles. A coastal-surveillance case study illustrates how the proposed architecture enables dependable, governed, and physically safe swarm coordination under operational uncertainty.
Figures & tables
Figure 1: Conceptual overview of the Guarded Swarms architecture. The digital layer transforms multi-modal sensor inputs into semantic tokens and coordinates mission formation through TB-CSPN, exhibiting constrained non-determinism: multiple admissible coordination paths may exist, but are strictly bounded by token availability, guard conditions, and temporal constraints. Human-in-the-loop governance enforces authorisation policies before mission release. The analogue safety envelope provides independent, hardware-enforced veto mechanisms that ensure deterministic, physically safe actuation.
Boundary
Primary Guarantee
Human–AI
Accountability and governance
Role separation
Clear authority and delegation
Semantic–coordination
Scalable, verifiable orchestration
Digital–physical
Deterministic safety
Table 1: Architectural boundaries and their primary guarantees.
Figure 2: Architectural boundaries in autonomous AI systems. As decisions propagate downward, their reversibility decreases and the cost of error increases, motivating progressively stronger guarantees.
Figure 3: Overall architecture for sensor-driven mission synthesis in guarded UAV/UGV swarms.
Figure 4: Incremental mission formation in the coastal-surveillance case study. Heterogeneous sensor observations arrive asynchronously and are interpreted by consultant agents as semantic tokens, where labels such as PossibleUAV , LikelyDroneLink , and ConfirmedAerialObject denote typed interpretations associated with specific topics. TB-CSPN transitions perform both validation (through guards on signal consistency and timeliness) and semantic interpretation, progressively producing and refining semantic tokens, from CandidateTarget to ConfirmedThreat . These tokens represent emergent semantic constructs arising from the integration of heterogeneous signals. Once the required authorisation token is provided by the human-in-the-loop, the mission-release transition fires and produces an InterceptMission token. A dispatch transition then generates task-specific tokens that worker agents consume, which are translated into platform-specific execution commands for the UAV and UGV executors.
Autonomous UAV swarms require scalable coordination mechanisms that maintain mission performance under limited communication, environmental uncertainty, and component failures. Centralized approaches provide global coordination but suffer from communication bottlenecks and single-node vulnerabilities, whereas fully decentralized methods often lack mission-level consistency. This paper presents Layered Autonomous Edge Intelligence (LAEI), a UAV-swarm framework that combines onboard learned policies with lightweight mission-level supervision. Each UAV performs local perception, obstacle avoidance, and action selection onboard, while the supervisory layer provides adaptive goal reassignment, fault-aware recovery, and context-dependent policy guidance without directly controlling low-level actions. LAEI further incorporates recovery strategies, including dynamic reassociation, backup supervisory support, and fallback local autonomy, to maintain mission continuity under representative failure scenarios. We evaluate LAEI in simulated UAV-swarm scenarios using mission completion time, collision rate, and coverage efficiency. The results show that LAEI reduces mission completion time and improves operational efficiency while maintaining collision-aware distributed UAV-level decision-making.
Changmin Park, Wooyong Jung, Hwangnam Kim
School of Electrical Engineering Korea University Seoul 02841, Korea
The certification of Unmanned Aerial Vehicle (UAV) swarms for safety-critical operations requires verifiable design assurance. Airworthiness standards demand deterministic reliability, whereas multi-agent coordination algorithms execute non-deterministic models. This paper proposes a mixed-criticality architectural framework that applies SAE ARP4754B methods to swarm reconfiguration. First, a hardware-isolated Safety Monitor functions as a Run-Time Assurance (RTA) gateway, decoupling the flight-critical core from the non-deterministic Swarm Manager. Second, the monitor enforces formal safety contracts based on agent Health Vectors derived systematically from a Functional Hazard Assessment (FHA). Third, the framework propagates these Health Vectors to the collective planner to trigger fail-operational task reallocation, enabling intelligent swarm behaviors without compromising flight-critical isolation. Markov reliability modeling demonstrates that the 10−7 failures per flight hour Hazardous target is theoretically achievable for our SAIL IV scenario, provided the Safety Monitor meets Cmonitor>0.9991, consistent with DAL B CMD/MON implementations.
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