implementation

Multi-Sensor Fusion & Object Tracking Implementation

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Real-time C-UAS Threat Assessment & Countermeasure Planning with Claude 3.5 Haiku

Format

Text-first

Lines

Sections

Linked challenge

Real-time C-UAS Threat Assessment & Countermeasure Planning with Claude 3.5 Haiku

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Implement the multi-sensor fusion module using Python. This module should take simulated raw sensor data (radar tracks, EO/IR detections, acoustic signatures) and fuse them into a coherent, tracked object state for each identified UAS. Utilize a Kalman filter or similar state estimation technique for robust tracking. Explain your choice of fusion algorithm and demonstrate its effectiveness with sample simulated data.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

implementation

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Real-time C-UAS Threat Assessment & Countermeasure Planning with Claude 3.5 Haiku

The proliferation of small Unmanned Aerial Systems (UAS) presents significant security challenges. This challenge focuses on building a sophisticated Counter-UAS (C-UAS) system capable of autonomously detecting, identifying, and recommending appropriate countermeasures in real-time. Leveraging multi-modal sensor inputs (e.g., radar, optical, acoustic), participants will develop a robust data fusion pipeline. The core innovation lies in integrating Claude 3.5 Haiku via Marvin for structured data extraction and intelligent threat assessment, alongside Browserless for dynamic external data fetching. The system must analyze real-time sensor streams, identify potential drone threats, extract critical attributes like type, velocity, and payload, and then synthesize this information with contextual data (e.g., geofencing rules, environmental conditions, rules of engagement). Based on this comprehensive understanding, the system will use the LLM to provide actionable, prioritized countermeasure recommendations (e.g., soft kill jamming, kinetic interception, alert generation) that balance effectiveness with minimizing collateral damage.

Open challenge

Related prompts

Browse library

System Architecture Design

planning

LLM Integration for Threat Assessment

implementation

System Performance & Robustness Testing

testing