Hiwonder ROSOrin Pro ROS2 Smart Car with Jetson/Raspberry Pi, Multimodal Large AI Models & OpenClaw, 3D Vision, SLAM Mapping & Navigation, Robotic Arm

The Hiwonder ROSOrin Pro is an advanced ROS2 robotic platform designed for students, educators, and researchers looking to master autonomous driving, physical manipulation, and artificial intelligence. Combining a high-performance controller with a 3D depth camera, a 6DOF robotic arm, and a TOF LiDAR, this smart car bridges the gap between digital perception and physical execution. It is the ideal tool for exploring advanced SLAM mapping, navigation, and multimodal large AI model integration.

Multimodal large AI model deployment

The ROSOrin Pro supports both online and local deployment of multimodal large AI models, including ChatGPT, Gemini, Grok, and Llama. This allows for fully offline AI interaction and control without requiring an active internet connection.

Integrated OpenClaw agent framework

Deep integration with the OpenClaw agent enables control via PC or app, bypassing device and scenario limitations. It supports multimodal command input, remote text and voice control, and real-time intelligent decision-making to autonomously plan and execute complex workflows.

Advanced hand-eye coordination

By combining a 3D depth camera with a 6DOF robotic arm and built-in inverse kinematics, the platform simplifies 3D object recognition, positioning, and tracking. This allows the robot to easily perform complex physical tasks such as precise grasping, sorting, and transport.

High-precision TOF LiDAR navigation

Equipped with a high-precision TOF LiDAR, the smart car fuses encoder and IMU data to perceive its surroundings in real time. It supports multiple mapping algorithms to ensure reliable navigation and path planning in complex environments.

Multipurpose 3D depth camera

The onboard 3D depth camera enables advanced computer vision tasks, including YOLO26 object detection and human pose estimation. It also supports KCF object tracking, line following, and face tracking for diverse interactive applications.

COIN-D6 LiDAR obstacle avoidance

The integrated COIN-D6 LiDAR provides robust obstacle avoidance, target following, and fixed-point or multi-point navigation. It works alongside OpenClaw for efficient path planning and global task navigation.

Intelligent AI voice module

An AI voice interaction module supports custom wake words and command words for both online and offline voice control. It leverages OpenClaw to perform fuzzy intent inference and task completion.