Hiwonder JetRover JETSON Robot Car with AI Vision Robotic Arm, Supports ROS1 & ROS2, with AI Large Model (ChatGPT), SLAM Mapping/Navigation, AI Voice Interaction, Intelligent Sorting

The Hiwonder JetRover is an advanced composite ROS robot designed for robotics education, research, and advanced maker projects. Equipped with a 6-degree-of-freedom robotic arm, multimodal AI capabilities, and LiDAR navigation, it provides students, educators, and hobbyists with a powerful platform for exploring autonomous driving, SLAM, and embodied AI. Open-source codes and learning resources are provided to help you unlock the full potential of your AI projects.

Versatile ROS education platform

Built for ROS1 and ROS2 scenarios, the JetRover features a high-performance magnetic encoding motor and supports Mecanum wheel, Ackerman, and Tank chassis. The system is equipped with an NVIDIA Jetson or Raspberry Pi controller, a 7-inch LCD screen, and a 6-degree-of-freedom robotic arm to handle complex physical tasks.

Six-axis arm with bus servos

The integrated 6-degree-of-freedom robotic arm is powered by high-torque, high-voltage bus servos that improve operating efficiency and extend the robot's endurance. This allows for precise physical manipulation, 3D grabbing, and automated sorting tasks.

LiDAR SLAM mapping and navigation

Equipped with high-precision LiDAR, the JetRover performs real-time SLAM mapping, path planning, and fixed-point navigation. The system also supports dynamic obstacle avoidance to safely navigate complex environments.

Depth vision and target tracking

A high-performance 3D depth camera is mounted at the end of the 6DOF robotic arm, providing first-person view vision. This setup enables the robot to perform target recognition, visual tracking, and precise 3D grabbing.

Far-field voice interaction array

A 6-channel far-field microphone array and integrated speakers enable sound source positioning, voice recognition control, and voice-guided navigation. This hardware allows the robot to respond accurately to natural language commands.

Dual-controller collaboration architecture

The JetRover utilizes a dual-controller design to distribute processing tasks efficiently between the primary processor and sub-controllers. This architecture ensures smooth coordination between high-level AI algorithms and low-level motor control.

Multimodal generative AI integration

By combining multimodal AI large language models with SLAM navigation, the JetRover can interpret voice commands to execute multi-point navigation. Once at its destination, the robot employs a vision language model to analyse surrounding objects and events.

Semantic and environmental scene understanding

The robot leverages large language models to interpret the natural language intent behind user voice commands. Supported by an AI vision language model, it deeply analyses environmental information, identifying objects and events within its field of view.