Threat Detection & Tracking Simulation
The evaluation will focus on the system's ability to autonomously detect, classify, and track simulated undersea threats within a specified time frame, minimizing false positives and maximizing coverage, while leveraging the AI for dynamic decision-making and re-planning.
Evaluation overview
How the linked challenge is judged: tasks, benchmarks, and criteria count.
Task templates
Inputs and expected outputs.
Threat Detection & Tracking Simulation
Simulate an undersea environment with multiple UUVs and a hidden, moving 'threat' object. The system must coordinate UUVs to detect, classify, and continuously track the threat over a specified duration.
JSON configuration for UUV initial positions, sensor types (e.g., sonar range, FOV, noise), threat trajectory, and environmental noise parameters.
JSON log of UUV positions over time, detected threat positions, estimated threat classifications, and Llama 3.1's decision logs (e.g., re-planning commands, threat assessments).
AI Mission Re-planning
Introduce an unexpected event (e.g., a new threat appearing, UUV sensor failure, communication drop) during a simulated mission. The system must use Llama 3.1 to propose and execute an updated mission plan in response to the event.
JSON log from 'Threat Detection & Tracking Simulation' up to the event, plus event details (e.g., {"event_type": "new_threat", "location": [50, 50, -30], "time": 50}).
JSON log of subsequent UUV positions, new threat detection status, and Llama 3.1's re-planning rationale and commands.