Mobile and ROS robots

JetAcker

An Ackermann-steering ROS robot car for autonomous driving lessons, on NVIDIA Jetson or Raspberry Pi 5.

Raspberry Pi
NVIDIA Jetson
Suggested for university

JetAcker is an autonomous driving robot car that Hiwonder designed for ROS education. Its chassis steers like a road car, with Ackermann geometry, a pendulum suspension and a full-metal CNC steering system, and it runs on an NVIDIA Jetson or a Raspberry Pi 5. Every kit has a lidar for SLAM mapping, path planning and obstacle avoidance. The Standard Kit adds a 3D depth camera for 3D vision, and the Advanced and Ultimate kits add a 7-inch screen and a circular 6-microphone array for voice control and, with a Jetson Orin Nano or Orin NX, large AI model applications through ChatGPT. Hiwonder supplies tutorials, schematics, source code and videos.

Zeta42 is an authorised Hiwonder partner in the Middle East.

Configurations

Choose how it ships.

Model: Starter Kit · Standard Kit · Advanced Kit · Ultimate Kit
Controller: Without Controller · With Raspberry Pi 5(8GB) · With Jetson Nano(4GB) · With Jetson Orin Nano Super(4GB) · With Jetson Orin Nano Super(8GB) · With Jetson Orin NX Super(8GB) · With Jetson Orin NX Super(16GB)

What it does

Built for.

Car-like steering
With Ackermann steering, the inner front wheel turns further than the outer one, as on a road car. A pendulum suspension keeps the wheels on uneven ground, and high-density solid wheels resist deformation and wear.
Lidar SLAM
The lidar maps a space with Gmapping, Hector, Karto or Cartographer and supports path planning, fixed-point navigation and dynamic obstacle avoidance. The Ultimate Kit uses an EAI G4 lidar, the other kits a SLAMTEC A1.
3D vision
From the Standard Kit up, a depth camera on a 240° pan-tilt adds RTAB-VSLAM 3D mapping and point clouds, KCF target tracking, line following, colour and AprilTag recognition, YOLO object recognition and MediaPipe body, fingertip and face detection.
Voice and large AI models
In the Advanced and Ultimate kits, the circular 6-microphone array locates sound and takes voice commands. With ChatGPT and a vision language model, JetAcker navigates to spoken destinations and describes what it finds there. Hiwonder notes that the large AI model features need a Jetson Orin Nano or Orin NX.
Simulation
JetAcker supports Gazebo simulation, and its URDF model can be viewed in RViz to check mapping and navigation while debugging.
Choice of controller
It is sold with a Jetson Nano, Jetson Orin Nano Super, Jetson Orin NX Super or Raspberry Pi 5, or without a controller. ROS2 runs on all of them, and ROS1 on the Jetson Nano.

Where it is used

Applications.

Teaching autonomous driving on car-like Ackermann steering
University ROS courses covering SLAM, navigation and path planning
Embodied AI with voice commands and vision language models (Advanced and Ultimate kits with a Jetson Orin Nano or Orin NX)
Multi-robot navigation and formation

Videos

See it run.

Specifications

The full sheet.

Size: 316 × 259 × 242 mm
Weight: 4.8kg
Material: Full-metal hard aluminum alloy bracket
Battery: 11.1V 6000mAh LiPo battery
Continuous working time: 90 min
Drive motor: 520 Hall encoder geared motor, 1:90 ratio, 15kg.cm torque
Servo: HTS-20H serial bus servo
ROS controller: Jetson Nano / Jetson Orin Nano Super / Jetson Orin NX Super / Raspberry Pi 5
Operating system: ROS1: Ubuntu 18.04 (Jetson Nano); ROS2: Ubuntu 22.04 (all controllers)
Lidar: SLAMTEC A1 (Starter, Standard and Advanced Kit); EAI G4 (Ultimate Kit)
3D depth camera: Standard, Advanced and Ultimate Kit
Screen: 7-inch LCD (Advanced and Ultimate Kit)
Microphone: Circular 6-microphone array (Advanced and Ultimate Kit)
Software: iOS / Android app
Communication: USB / WiFi / Ethernet
Programming language: Python / C / C++ / JavaScript
Control method: Phone / wireless handle
Package size (Advanced Kit): 38 × 31 × 23 cm
Package weight (Advanced Kit): About 5kg