Skip to content
RobothecaBeta
Log in

Robot Pet v1 (ESP32-CAM Face Tracker)

A desktop robot pet built around an AI-Thinker ESP32-CAM that streams video, tracks faces or coloured objects with pan and tilt servos, and shows animated eyes on an OLED display.

  • Home
  • Open source
  • arduino

Suggested by Robotheca, created by @RKTheOneAndOnly (opens in a new tab), from github.com/RKTheOneAndOnly/Robot_Pet_V1 (opens in a new tab). Pinned to commit 73cf6e3 (opens in a new tab).

Fork on GitHub (opens in a new tab)Download the files at this commit (.zip)
Hardware license
GPL-3.0-only (opens in a new tab)
Software license
GPL-3.0-only (opens in a new tab)
Commercial use
Allowed

Photo and 3D model

Robot Pet v1 (ESP32-CAM Face Tracker), photo from its repository
Photo:@RKTheOneAndOnly (opens in a new tab)GPL-3.0-onlysource file (opens in a new tab)

3D preview converted from github.com/RKTheOneAndOnly/Robot_Pet_V1 at 73cf6e3, under GPL-3.0-only. View the original files from GitHub (13.0 MB) (opens in a new tab)

What it can do

Written by Robotheca from the project's documents.

  • Streams MJPEG video over WiFi from an ESP32-CAM to a laptop.
  • Tracks a face with a Haar cascade or a coloured object using an HSV blob.
  • Drives pan and tilt servos to keep the tracked target centred in frame.
  • Shows animated, mood-driven eyes on a 128x64 I2C OLED that blink and glance around.
  • Vision on the laptop only sends relative turn commands; the ESP32 owns servo angles and limits.
  • Colour mode lets the user click the video to sample and track a colour under the cursor.

Bill of materials

7 parts
Export parts list (CSV)

7 of 7 parts shown

Parts list
#ComponentQuantityEst. priceSupplier
2. Components Used
1AI-Thinker ESP32-CAM (OV2640)1––
2SG90 micro servo2––
31.3 " I²C OLED, 128×641––
4USB-to-TTL adapter (FTDI/CP2102)1––
55V power supply, ≥1A1––
63D printed parts5––
7Jumper wires, M2/M3 screws–––

7 of 7 needed parts have no price in the source, so there is no parts total. Read from README.md at the pinned commit.

Build guide

The creator's steps, each with its instructions.

  1. 1Add WiFi credentials to include/wifi_config.h
  2. 2Flash the firmware with PlatformIO
  3. 3Check the camera stream in a browser
  4. 4Run the servo bring-up test
  5. 5Centre both servos before assembly
  6. 6Install Python requirements and run the tracker

The guide appears here as you scroll.

Guide by @RKTheOneAndOnly (README.md), under GPL-3.0-only.

Wiring and electronics

Notes written by Robotheca from the project's documents.

Main parts

  • AI-Thinker ESP32-CAM (OV2640) as main controller and camera.
  • Two SG90 micro servos for pan and tilt.
  • 1.3 inch I2C OLED display, 128x64, blue, 4-pin.
  • USB-to-TTL adapter (FTDI/CP2102) used only for flashing.
  • 5V power supply of at least 1A, separate from the ESP32-CAM for the servos.

Connections

  • Pan servo signal on GPIO2, tilt servo signal on GPIO13.
  • OLED SDA on GPIO14 and SCL on GPIO15, since the camera occupies the default I2C pins 21 and 22.
  • Servos are powered from the separate 5V supply, not from the ESP32-CAM 5V or 3.3V pin.
  • Common ground must connect the servo supply, ESP32-CAM, and OLED grounds.

Cables and connectors

From the parts list.

  • Jumper wires, M2/M3 screws