Skip to main content
Enterprise AI Analysis: Drone-Enabled Non-Invasive Ultrasound Method for Rodent Deterrence

Enterprise AI Analysis

Drone-Enabled Non-Invasive Ultrasound Method for Rodent Deterrence

Unmanned aerial vehicles open new possibilities for developing technologies that support more sustainable and efficient agriculture. This paper presents a non-invasive method for repelling rodents from crop fields using ultrasound. The proposed system is implemented as a spherical-cap ultrasound loudspeaker array consisting of eight transducers, mounted on a drone that overflies the field while emitting sound in the 20–70 kHz range. The hardware design includes both the loudspeaker array and a custom printed circuit board hosting power amplifiers and a signal generator tailored to drive multiple ultrasonic transducers. In parallel, a genetic algorithm is used to compute flight paths that maximize coverage and increase the probability of driving rodents away from the protected area. As part of the validation phase, artificial intelligence models for rodent detection using a thermal camera are developed to provide quantitative feedback on system performance. The complete prototype is evaluated through a series of experiments conducted both in controlled laboratory conditions and in the field. Field trials highlight which parts of the concept are already effective and identify open challenges that need to be addressed in future work to move from a research prototype toward a deployable product.

Executive Impact: Transforming Agricultural Robotics & Pest Control Operations

This drone-enabled non-invasive ultrasound method offers a sustainable and chemical-free approach to rodent deterrence in agriculture. By leveraging UAVs with spherical-cap ultrasonic loudspeaker arrays, the system provides dynamic acoustic coverage across crop fields. Optimized flight paths, determined by genetic algorithms, maximize rodent repulsion while minimizing battery consumption. AI-based thermal camera detection provides quantitative feedback on rodent behavior, validating the system's effectiveness in both laboratory and real-world conditions. This technology represents a significant step towards environmentally friendly pest control, potentially reducing crop losses and supporting biodiversity.

0 Rodents Repelled
0 Coverage Efficiency
0 Battery Consumption
0 SPL Uniformity

Deep Analysis & Enterprise Applications

Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.

Hardware Design
Path Planning
Rodent Detection

The system employs an eight-transducer spherical-cap ultrasonic loudspeaker array (20–70 kHz) mounted on a drone. A custom PCB integrates signal generation and power amplification, driving multiple transducers efficiently. The spherical cap design concentrates acoustic energy, improving coverage and exploiting reflections for enhanced sound pressure levels. The mechanical structure is 3D-printable, optimized for mass and height to ensure stable drone flight.

The signal generator uses two NE555 timer ICs to produce triangle (20-80 kHz) and square (100 Hz-10 kHz) waves, modulated to create the ultrasound excitation. A high-pass filter removes frequencies below 30 kHz to avoid human audible range. LM386N integrated IC amplifiers provide up to 200 mW output power per set of three parallel-wired loudspeakers, ensuring uniform sound pressure coverage. The compact design and low power consumption enable efficient drone integration.

A genetic algorithm optimizes drone flight paths over a 10x10m grid, maximizing field coverage and rodent deterrence while minimizing redundant movements and battery consumption. The chromosome represents a discrete sequence of movement commands, with dynamic rodent avoidance behavior modeled. The fitness function prioritizes rodent displacement and coverage efficiency. Results show 90% coverage and all 16 initial rodents repelled in simulations.

In field testing, waypoint-based missions revealed high battery consumption due to frequent stops. A trajectory simplification strategy was developed to reduce stopping events by collating collinear waypoints into continuous motions. This improved flight endurance and maintained coverage patterns, demonstrating the need for execution-level adaptations to bridge the gap between offline optimization and real-world UAV dynamics.

An AI-based rodent detection system, utilizing a thermal camera, provides quantitative feedback for system validation. It employs two complementary pipelines: a finetuned YOLOv11n detection model and a classical digital image processing module (OpenCV). The YOLO model, trained on a rodent-specific thermal dataset, achieves high F1 scores (0.98) and mAP (0.991 at 0.5 IoU) for rodent detection.

The OpenCV module enhances robustness by performing motion and hot-spot detection on 14-bit pixel values, utilizing rolling median background, Gaussian blur, and thresholding. While YOLO is precise but prone to false negatives in low-contrast scenarios, OpenCV offers faster computational speed with a lower detection threshold, occasionally detecting non-rodent objects. Combining both strengths is a future research direction for an efficient and accurate integrated system.

20-70 kHz Optimal Ultrasonic Frequency Range for Rodent Deterrence

System Development Workflow

Loudspeaker Array Design
PCB & Amplifier Fabrication
Genetic Algorithm for Path Planning
Thermal Camera AI Detection
Integrated System Validation

Comparison of Rodent Control Methods

Approach Initial Cost/Running Cost Safety and Environmental Impact Effectiveness in Practice
Chemical Rodenticides Low-medium / medium (consumables) Lower: non-target exposure and secondary poisoning concerns; regulatory constraints Often high for population reduction, but context-dependent
Traps (Mechanical/Electronic) Low / medium-high (labor and servicing) Medium-high (non-chemical; welfare depends on design/use) Moderate locally; harder to scale over large areas
Static Ultrasound Repellers Low / low High (non-chemical) Low-uncertain outdoors
Proposed UAV Ultrasound (This Work) Higher / medium (UAV + energy + maintenance) High (non-chemical, targeted and time-limited exposure) Preliminary at this stage (subsystems validated); improved coverage expected when integrated

Field Trial Success: Deliblato Sands

Initial field trials at the Deliblato Sands area successfully demonstrated the proof-of-concept. The system, involving drone overflights with the ultrasonic array, showed promising results in deterring rodents. Thermal camera detection confirmed that 10 out of 10 mice in an enclosed area were repelled within 10 seconds, migrating to the corners away from the drone's path. While species-specific responses varied, this highlights the potential for dynamic, drone-based ultrasonic deterrence.

Rapid Rodent Displacement 100% Repulsion Rate in Controlled Test

Calculate Your Potential ROI

Estimate the economic benefits of implementing drone-enabled rodent deterrence.

Annual Savings $0
Hours Reclaimed Annually 0

Implementation Roadmap

A phased approach to integrate drone-enabled pest control into your operations.

Phase 1: Proof-of-Concept Validation (Completed)

Laboratory measurements confirmed stable ultrasound generation and spatial uniformity. Drone flight tests validated predefined trajectories and identified battery efficiency challenges. Initial rodent behavior observed during ultrasound exposure. AI models for thermal detection developed. This phase established the fundamental technical feasibility.

Phase 2: Adaptive Emission & Field Integration (Next Steps)

Quantify deterrence effectiveness in longer-duration field trials, assessing habituation. Investigate adaptive emission strategies (frequency hopping, temporally jittered schedules). Extend path planning to include energy and weather models. Validate end-to-end performance with integrated sensing, real-time trajectory adjustment, and improved transducer packaging.

Phase 3: Commercial Viability & Scalability

Refine the system for commercial deployment based on field insights. Develop robust, energy-efficient hardware for diverse crop environments. Integrate real-time rodent tracking with dynamic flight paths for closed-loop deterrence. Address regulatory compliance and long-term maintenance. Scale the solution for large-scale agricultural operations, offering a sustainable alternative to chemical pest control.

Ready to Transform Your Operations?

Connect with our AI specialists to explore how drone-enabled rodent deterrence can benefit your enterprise.

Ready to Get Started?

Book Your Free Consultation.

Let's Discuss Your AI Strategy!

Lets Discuss Your Needs


AI Consultation Booking