Pawvlov NLT Labs NLT Labs

For Investors

Engineering

Edge-first embedded system: an ESP32-S3-WROOM-1 runs a MobileNetV3-Small INT8 dog-pose classifier and an 80Hz storm-audio classifier on-device at 5fps, driving a single-flight damped auger through a DRV8833. A companion mobile app pairs over BLE for setup and reads training progress; a thin cloud control plane handles OTA model/firmware, anonymized session telemetry, and Stripe subscription. Safety-critical inference never gates on the cloud, and no raw frames or audio ever leave the unit — the on-device-only design is the deliberate BIPA / two-party-consent mitigation.

Front-to-back section through the center axis of the tower showing the gravity-fed treat path from the top-loading hopper, down the damped Delrin auger, through the acoustic-foam chamber, out an external chute into the floor-reachable silicone tray. Electronics stack low-front (camera, mic array, IR LEDs) and low-rear (main PCB, USB-C power board), with the steel weighted plate at the very base for tip resistance.

Internal cross-section (SVG)
Pawvlov — Internal cross-section (SVG)Labeled engineering cross-section of Pawvlov showing internal components, dimensions, and wiring.Section A–A · front-to-back center-axis cutawayH 165 mmW 130 mmD 190 mm incl. trayTreat hopper (ABS)~120-treat capacity, top-loading snap lidDelrin (POM) helical augersingle-flight fixed-rotation screwN20 damped gear motor6V, drives auger 1 flight/dispenseAcoustic chamberBasotect open-cell foam + MLV barrier, wraps motor/auger, <40dB targetMain PCB — ESP32-S3-WROOM-1 + DRV88334L proto (RF isolation) → 2L+jumper at scaleOV5640 5MP camera120° FOV, 14mm bore, angled 15° down4x ICS-40180 MEMS mic array50mm diamond span, beamformed 80Hz storm detect8x 940nm IR LEDnight-vision assist, invisible to canine visionUSB-C power board + AP63203 buck5V/3A mains in, isolated flyback-protected motor railWS2812B status LED (amber-only)rear-upper, diffused, out of dog's forward gazeSteel weighted base plate~200g, bonded into base shell for tip resistanceExternal silicone dispense trayFDA 21 CFR 177.2600, 45mm forward extension, 6° tilt, floor-reachableLegendStructure / chassisMotor / actuatorAcoustic foamMain PCBSensorPower inputSilicone / trayPawvlov · Rev A

Dispense tray is drawn external to the sealed shell, below the base outline — the dog reaches into open air, never into the housing.

Chip selection

ESP32-S3-WROOM-1-N16R8 chosen as a single-chip compute + radio that runs the classifier on-device without an external NPU or a second radio/cert path.

Sensor & camera architecture

A low-forward camera reads body language at the dog's own height, a beamformed MEMS mic array detects storms independently, and IR assist handles dark 3am storms — none of it a startle source.

  • OV5640 5MP camera
  • ICS-40180 PDM MEMS mic x4
  • 940nm IR LED x8

ML inference pipeline

All safety-critical inference is on-device; the device ships dispense-DISABLED (log-only) until the classifier is validated, and the cloud never gates a dispense decision.

Power & battery

USB-C mains, deliberately no battery in the dispense path — a dead battery at 3am during the exact event the product exists for is an unacceptable failure mode.

Firmware architecture

FreeRTOS with the safety-critical inference loop isolated from network jitter; the single most important property is that the calm-confidence floor cannot be lowered from the app.

Manufacturing process

  • Single-cavity injection mold for the tower + base shells ($35K, replaces a $105K three-SKU tool)
  • SMT PCBA line + AOI (4-layer proto -> 2-layer + jumper at scale after RF validation)
  • Auger + acoustic-chamber sub-assembly (Delrin flight + Basotect/MLV)
  • Functional end-of-line test: <40 dB dispense, jam-recovery, fail-closed gate

Architecture summary

Edge-first embedded system: an ESP32-S3-WROOM-1 runs a MobileNetV3-Small INT8 dog-pose classifier and an 80Hz storm-audio classifier on-device at 5fps, driving a single-flight damped auger through a DRV8833. A companion mobile app pairs over BLE for setup and reads training progress; a thin cloud control plane handles OTA model/firmware, anonymized session telemetry, and Stripe subscription. Safety-critical inference never gates on the cloud, and no raw frames or audio ever leave the unit — the on-device-only design is the deliberate BIPA / two-party-consent mitigation.

Risk register

Risk register

RiskSeverityLikelihoodMitigationConfidence
On-device classifier misclassifies during an anxiety event and rewards a fear state (iatrogenic)CriticalMediumShip dispense-DISABLED (log-only) until >95% calm/anxious accuracy + <2% false-positive fear-reward on held-out data; 0.95 fail-closed floor is firmware-locked; documented audio-only pivot if unmet Modeled
OV5640 camera module goes EOL mid-production or ESP32-S3 allocation slipsMediumMediumQualify a pin-compatible second camera source before the 1K run; order ESP32-S3 ahead with buffer stock Sourced
<40 dB auger noise target not met across variable treat sizesHighMediumBasotect+MLV acoustic chamber, single-flight fixed-rotation auger, current-sense stall recovery; validated in EOL test BEFORE tooling commit Modeled
FCC intentional-radiator + UL cert slips past the launch windowMediumLowFCC pre-scan at design freeze; cert runs parallel to the mold lead time; budget reserved in the capital ask Modeled

Dimensions (to scale)

Overall dimensions by model

ModelHeight (mm)Width (mm)Depth (mm)Weight (g)Note
Medium1651301901050Depth includes 45mm tray extension; below shoulder height for 20-60lb dogs; weighted base ~200g of the 1050g total

Component dimensions (to scale)

ComponentValue (mm)ToleranceNote
Camera bore14±0.15mmOV5640 module seat, low-forward face
Mic array span50±0.5mm4-mic diamond beamforming geometry
Tray recess depth8±0.3mmprevents treat roll-off, 6° forward tilt
Tray external extension45±1mmforward of base shell, floor-reachable
Hopper capacity height130±1mm≈120 standard 12-15mm training treats
Acoustic chamber wall12±0.5mmBasotect + MLV, drives <40dB target
Base weighted plate mass200±5gsteel insert, tip resistance (value in grams, not mm)