Waveshare ESP32 robotic arm kit with 5+1 DoF supports ROS2, LeRobot, and Jetson Orin NX integration

Waveshare has recently released the RoArm-M3-Pro and RoArm-M3-S, a 5+1 DOF high-torque ESP32 robotic arm kit. The main difference between the two is that the RoArm-M3-Pro features all-metal ST3235 bus servos for durability and longevity, on the other hand, the RoArm-M3-S uses standard servo motors which are less durable for long-term use.

These robotic arms feature a lightweight structure, a 360° omnidirectional base, and five flexible joints, which together create a 1m workspace with a 200 grams @ 0.5m payload. A 2-DOF wrist joint enables multi-dimensional clamping and precise force control. It integrates an ESP32 MCU, supporting multiple wireless control modes via a web app, it also supports inverse kinematics for accurate positioning, curve velocity control for smooth motion, and adaptive force control. The design is open source and with ROS2 compatibility, it allows secondary development via JSON commands and ESP-NOW for multi-device communication. Compatible with the LeRobot AI framework, it supports AI research with pre-trained models, imitation learning, and reinforcement learning, making it suitable for robotics, automation, and human-machine interaction projects.

RoArm-M3-Pro and RoArm-M3-S specifications:

Degrees of Freedom (DOF) – 5 + 1
Payload – 200 grams @ 0.5m
Workspace – 1120mm (Max, 360° omnidirectional), Vertical: 798mm (Max)
Operating range – Base-360°, Shoulder-180°, Elbow-180°, Hand-135°/270°
Servos
- Total servo – 7
  - All-metal ST3235 bus servos, direct-drive (RoArm-M3-Pro)
  - Standard servos for RoArm-M3-S
- Servo speed – 40rpm (no-load, no torque limit)
- Servo torque – 30 kg.CM @12V
Joint feedback – 12-bit 360° magnetic encoder (0.088° precision)
Host Operation – UART/USB/ESP-NOW/HTTP communication via JSON data format commands
Display – 0.91-inch OLED
Control board
- MCU module – Espressif ESP32-WROOM-32U with WiFi and Bluetooth
- Storage – microSD card slot
- Interfaces
  - I2C for OLED screens and I2C sensors
  - SPI
  - LiDAR Interface (supported sensor not specified)
  - ST3215 Serial Bus Servo Interface
  - 2x Motor Interface PH2.0 6P for motors with encoders (Group A and Group B).
  - 2x Motor Interface PH2.0 2P for motors without encoders (Group A and Group B).
  - 40-pin expansion header for connection to a Raspberry Pi or other host boards
  - 40-pin GPIO header
- Sensors and ICs
  - AK09918C 3-axis electronic compass
  - QMI8658C 6-axis motion sensor
  - TB6612FNG motor control chip
  - ST3215/ST3235 serial bus servo control circuit
  - INA219 voltage and current monitoring chip.
- USB
  - USB Type-C Port for power and programming the board
  - USB Type-C Port for LIDAR data transmission
- Misc
  - Reset button
  - Download button
  - Power ON/OFF button
- Power – XH2.54 power port with DC 5V voltage regulator for host computers (Raspberry Pi, Jetson Nano).
Expansion
- EoAT customization (gripper, etc.)
- Camera mount
- Peripheral mounting rails
Operating voltage
- 12V, 5A power supply with 2-channel supply switch
- Supports 3S Lithium batteries (NOT included)
Dimensions
- Horizontal reach – 316.15 mm (depending on arm configuration)
- Vertical height – 236.8 mm (from the base to the top of the arm)
- Base width – 87.35 mm to 91.45 mm (including clamp mechanism)
- End-Effector Length – 13.29 mm
- Additional Horizontal Extension – 30.00 mm
- Base Height – 126.06 mm
- Rotational Base Section Height – 123.06 mm
- Arm Section Above Base – 53.46 mm
Weight
- RoArm-M3-S – 973.5 ± 15g
- RoArm-M3-Pro – 1020.8g ± 15g
- Table Edge Fixing Clamp – 290g ±10g

The End-of-Arm Tool (EoAT) clamp on the RoArm-M3 series consists of a two-degree-of-freedom (2-DOF) wrist joint, enabling pitch and horizontal rotation. It utilizes a direct-drive mechanism for precise force control, ensuring accurate object handling. The clamp supports modular attachments, such as mechanical grippers and vacuum-based suction tools, allowing customization based on application requirements. With LeRobot AI framework integration it can do inverse kinematics and deep learning-based control, optimizing motion planning and object manipulation in automated systems.

The RoArm-M3 series supports various tools, software, libraries, and web applications for integration and control. It is compatible with the LeRobot AI framework for motion control using inverse kinematics and deep learning. It supports Python, C++, and ROS2 support for programming, with APIs for motion planning, sensor input, and control. The system also includes a web-based and standalone GUI for operation, calibration, and diagnostics. It integrates with OpenCV for vision-based tasks and TensorFlow/PyTorch for AI-based object recognition. Communication interfaces include MQTT, WebSocket, and REST APIs for industrial automation and cloud-based monitoring. You can generally find more information about the product on their wiki page, but at the time of writing the page is empty, but they have various other information available on their products page.

Previously we have written about the previous generation Waveshare RoArm-M2 robotic arm, another ESP32-based robotic arm, but with four degrees of freedom (4 DoF) and built using carbon fiber and aluminum alloy. The main difference between the RoArm-M2 and RoArm-M3 is that the new model has 5+1 degrees of freedom, which means the arm includes all 5 DOF movements (base, shoulder, elbow, wrist pitch, and gripper) plus an additional wrist rotation (1 DOF), which allows the end effector (gripper) to rotate horizontally. This provides better maneuverability, making it more suitable for complex tasks like precision gripping, manipulation, and AI-based applications. We have also written about SO-ARM100 open-source AI robotic arm kit with LeRobot framework and NVIDIA Jetson integration.

The RoArm-M3-xx series ESP32-based 5+1 DOF robotic arm is available on AliExpress for $331.39 (RoArm-M2-S) or $455.99 (RoArm-M2-Pro).

Debashis Das

Debashis Das is a technical content writer and embedded engineer with over five years of experience in the industry. With expertise in Embedded C, PCB Design, and SEO optimization, he effectively blends difficult technical topics with clear communication