# US 2026/0305600 A1 · Systems and methods for animal deterrence using multi-modal sensing and reinforcement-learning-based acoustic actuation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0305600 A1
- Document ID: US20260305600A1
- Status: Published application
- Kind: A1
- Application number: 19/635,968
- Filed: 2026-04-01
- Published: 2026-10-08
- Earliest claimed: 2025-04-02
- Assignees: University of Maryland, Baltimore County
- Applicants: University of Maryland, Baltimore County
- Inventors: Bipendra BASNYAT; Nirmalya ROY
- Web page: https://patentgrep.com/patent/US20260305600A1

## CPC

- A01M 29/18: using ultrasonic signals
- A01M 29/10: using light sources, e.g. lasers or flashing lights
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- A01M: CATCHING, TRAPPING OR SCARING OF ANIMALS (appliances for catching swarms or drone-catching A01K57/00; fishing A01K69/00 - {A01K99/00}; biocides, pest repellants or attractants A01N); APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Systems and methods for animal deterrence using multi-modal sensing and reinforcement-learning-based acoustic actuation are disclosed. According to an aspect, a system includes one or more activity sensors configured to detect activity in a monitored area. The system also includes one or more imaging sensors configured to acquire image data of an animal in the monitored area in response to detection of activity by the at least one activity sensor. Further, the system includes an animal deterrence manager that determines a species of the animal based on the acquired image data. The animal deterrence manager is also configured to determine a deterrent profile based on the determined species. Further, the animal deterrence manager determines a deterrent command based on the deterrent profile. The animal deterrence manager is also configured to communicate the deterrent command to a stimulus device for implementing a deterrent action.

## Claims

### Claim 1

A system comprising:
at least one activity sensor configured to detect activity in a monitored area;
at least one imaging sensor configured to acquire image data of an animal in the monitored area in response to detection of activity by the at least one activity sensor;
an animal deterrence manager configured to:
determine a species of the animal based on the acquired image data;
determine a deterrent profile based on the determined species;
determine a deterrent command based on the deterrent profile;
communicate the deterrent command to a stimulus device for implementing a deterrent action;
observe a behavioral response of the animal to the deterrent action using the at least one imaging sensor; and
update a learned policy based on the observed behavioral response of the animal.

### Claim 2 (depends on 1)

The system of claim 1, wherein the at least one activity sensor comprises a passive infrared motion sensor configured to generate a trigger signal in response to detection of a thermal motion signature in the monitored area.

### Claim 3 (depends on 1)

The system of claim 1, wherein the at least one imaging sensor comprises a camera configured to capture image data of the monitored area in response to detection of activity by the at least one activity sensor.

### Claim 4 (depends on 3)

The system of claim 3, wherein the camera comprises a dual-spectral imaging configuration including an RGB image sensor and a near-infrared image sensor configured to capture image data.

### Claim 5 (depends on 1)

The system of claim 1, wherein the animal deterrence manager is configured to determine the species of the animal by executing a machine-learned classification model by use of the acquired image data.

### Claim 6 (depends on 5)

The system of claim 5, wherein the machine-learned classification model comprises an object detection model configured to output a bounding box and a species label for the animal within a field of view of the at least one imaging sensor.

### Claim 7 (depends on 6)

The system of claim 6, wherein the object detection model is based on a You Only Look Once (YOLO) architecture or a MobileNet-SSD architecture optimized for edge deployment.

### Claim 8 (depends on 1)

The system of claim 1, wherein the animal deterrence manager is configured to retrieve deterrent parameters associated with the determined species from a deterrent profile database for determining the deterrent profile based on the determined species.

### Claim 9 (depends on 8)

The system of claim 8, wherein the deterrent profile specifies at least one of: a frequency range, an amplitude envelope, a modulation pattern, a temporal duration, and an intensity level for a deterrent stimulus.

### Claim 10 (depends on 9)

The system of claim 9, wherein the deterrent profile is selected from a plurality of species-specific deterrent profiles each derived from an audiogram corresponding to a respective animal species.

### Claim 11 (depends on 1)

The system of claim 1, wherein the stimulus device comprises at least one acoustic emitter configured to emit an acoustic deterrent signal in response to the deterrent command.

### Claim 12 (depends on 11)

The system of claim 11, wherein the acoustic emitter is configured to emit signals in a predetermined ultrasonic frequency range and a predetermined audible frequency range.

### Claim 13 (depends on 12)

The system of claim 12, wherein the stimulus device comprises an array of speakers including a piezoelectric ultrasonic transducer and a dynamic cone speaker.

### Claim 14 (depends on 1)

The system of claim 1, wherein the stimulus device comprises at least one additional deterrent actuator including a light emitter, a mechanical actuator, and/or a combined audio-visual deterrent device.

### Claim 15 (depends on 1)

The system of claim 1, wherein the learned policy maps system states to deterrent actions and is updated using a reinforcement learning algorithm.

### Claim 16 (depends on 15)

The system of claim 15, wherein a system state used by the learned policy comprises at least the determined species, a time of day, an ambient light level, and a measure of prior responsiveness of the determined species to deterrent actions.

### Claim 17 (depends on 15)

The system of claim 15, wherein the animal deterrence manager is configured to compute a reward signal indicative of an effectiveness of the deterrent action and adjusting the learned policy based on the reward signal for updating the learned policy based on the observed behavioral response of the animal.

### Claim 18 (depends on 17)

The system of claim 17, wherein the reward signal is based at least in part on whether the animal exits a protected zone within a specified observation period after execution of the deterrent action.

### Claim 19 (depends on 1)

The system of claim 1, wherein the animal deterrence manager is configured to maintain, for each of a plurality of species, a habituation score indicative of a temporal trend in behavioral responsiveness of the respective species to deterrent actions.

### Claim 20 (depends on 19)

The system of claim 19, wherein the animal deterrence manager is configured to increase an exploration parameter used by the learned policy when the habituation score for the determined species exceeds a first threshold.

### Claim 21 (depends on 19)

The system of claim 19, wherein the animal deterrence manager is configured to trigger an escalation protocol that modifies at least one deterrent parameter when the habituation score for the determined species exceeds a second, higher threshold.

### Claim 22 (depends on 1)

The system of claim 1, wherein the animal deterrence manager is configured to track at least one of a trajectory, a velocity, and a heading change of the animal over an observation interval following execution of the deterrent action for observing the behavioral response of the animal to the deterrent action.

### Claim 23 (depends on 22)

The system of claim 22, wherein the animal deterrence manager is configured to classify the behavioral response into one of a plurality of behavioral states including at least approaching, stationary, alert, and retreating, and to use the behavioral state as input to the learned policy.

### Claim 24 (depends on 1)

The system of claim 1, further comprising a communication interface configured to transmit the deterrent command from the animal deterrence manager to the stimulus device over a wireless communication link.

### Claim 25 (depends on 1)

The system of claim 1, further comprising a plurality of stimulus devices distributed across the monitored area, wherein the animal deterrence manager is configured to select a subset of the plurality of stimulus devices to receive the deterrent command based at least on a location of the animal within the monitored area.

### Claim 26 (depends on 1)

The system of claim 1, wherein the animal deterrence manager comprises an edge processor configured to perform animal species determination, deterrent profile determination, deterrent command generation, observation of behavioral response, and update the learned policy.

### Claim 27

A system comprising:
at least one activity sensor configured to detect activity in a monitored area;
at least one imaging sensor configured to acquire image data of an animal in the monitored area in response to detection of activity by the at least one activity sensor; and
an animal deterrence manager configured to:
classify a detected animal by species by use of a machine-learned model based on the image data;
determine a system state based on the classified species, a time-of-day indicator, an environmental condition indicator, and/or a habituation metric associated with the classified species;
determine deterrent control data based at least on the system state;
cause at least one stimulus device to implement a deterrent action according to the deterrent control data;
analyze subsequent sensor data to determine a behavioral response of the animal to the deterrent action; and
update a learned policy that governs selection of deterrent actions and the habituation metric based at least on the determined behavioral response.

### Claim 28 (depends on 27)

The system of claim 27, wherein the at least one activity sensor comprises a passive infrared motion sensor configured to generate a trigger signal in response to detection of a thermal motion signature in the monitored area.

### Claim 29 (depends on 27)

The system of claim 27, wherein the at least one imaging sensor comprises a camera configured to capture video of the monitored area, and the machine-learned model is configured to process the video to classify the detected animal by species.

### Claim 30 (depends on 27)

The system of claim 27, wherein the animal deterrence manager is configured to maintain the learned policy using a reinforcement learning algorithm that updates an action-value function or a policy function based on the determined behavioral response.

### Claim 31 (depends on 27)

The system of claim 27, wherein the animal deterrence manager is configured to form a state vector including at least the classified species, the time-of-day indicator, the environmental condition indicator, and the habituation metric associated with the classified species for determining the system state.

### Claim 32 (depends on 27)

The system of claim 27, wherein the animal deterrence manager is configured to select a deterrent action from among a plurality of candidate deterrent actions stored in a deterrent profile database based at least on the system state for determining deterrent control data.

### Claim 33 (depends on 27)

The system of claim 27, wherein the animal deterrence manager is configured to track at least one of a trajectory, a velocity, and a heading change of the animal after implementation of the deterrent action for analyzing subsequent sensor data.

### Claim 34 (depends on 27)

The system of claim 27, wherein the animal deterrence manager is configured to compute the habituation metric as a function of behavioral responses observed over a plurality of deterrent encounters with animals of the classified species.

### Claim 35 (depends on 27)

The system of claim 27, wherein the animal deterrence manager is configured to:
update the learned policy based the determined behavioral response comprises computing a reward signal indicative of an effectiveness of the deterrent action; and
adjust the learned policy based on the reward signal.

### Claim 36 (depends on 27)

The system of claim 27, wherein the at least one stimulus device comprises a plurality of stimulus devices distributed across the monitored area, and
wherein the animal deterrence manager is configured to select a subset of the plurality of stimulus devices to implement the deterrent action based at least on a location of the detected animal within the monitored area.

### Claim 37

A system comprising:
an animal deterrence manager configured to:
maintain, for each of a plurality of wildlife species, a habituation score quantifying a temporal trend in behavioral responsiveness of the respective species to deterrent stimuli implemented by the system;
for each deterrent encounter with an animal of a given species, compute a response quality metric from sensor data indicative of a behavioral response of the animal to a deterrent action;
update the habituation score for the given species based on the computed response quality metric;
modify one or more control parameters governing selection of deterrent actions so as to adjust at least one of a diversity, intensity, or timing of deterrent stimuli applied to the given species in response to the habituation score meeting at least one escalation condition; and
transmit an alert to an operator via a remote management interface in response to the habituation score meeting an alert condition.

### Claim 38 (depends on 37)

The system of claim 37, wherein the deterrent stimuli implemented by the system comprise acoustic deterrent signals emitted by at least one acoustic emitter in at least one of an ultrasonic frequency range and an audible frequency range.

### Claim 39 (depends on 37)

The system of claim 37, wherein the sensor data indicative of the behavioral response comprises image data captured by an imaging sensor, and
wherein the animal deterrence manager is configured to analyze at least one of a trajectory, a velocity, and a heading change of the animal after the deterrent action for computing the response quality metric.

### Claim 40 (depends on 37)

The system of claim 37, wherein the escalation condition comprises the habituation score for the given species exceeding a first threshold and a second, higher threshold, and
wherein the animal deterrence manager is configured to, for the first threshold, increase a degree of variation in selected deterrent actions and, for the second threshold, increasing at least one of an intensity or duration of the deterrent stimuli for modifying the one or more control parameters.

### Claim 41 (depends on 37)

The system of claim 37, wherein the one or more control parameters comprise at least one randomization parameter of a reinforcement learning controller that maintains a learned policy for deterrent action selection, and
wherein the animal deterrence manager is configured to adjust the randomization parameter based on the habituation score for the given species modifying the one or more control parameters.
