Hiwonder JetAuto Pro AI Robot Car with 6DOF Vision Robotic Arm, Support ROS1 ROS2, with Large AI Model (ChatGPT), SLAM Mapping/Navigation, AI Voice Interaction, Intelligent Sorting

Specifications (automatically extracted)

Description

For Hiwonder JetAuto Pro tutorials you can check: https://docs.hiwonder.com/projects/JetAuto/en/jetauto-orin-nano/. Product Description JetAuto Pro is a composite ROS robot developed by Hiwonder for ROS education scenarios. It is equipped with an NVIDIA Jetson or Raspberry Pi, the high-performance magnetic encoding motors, and a 6DOF robotic arm. High-performance hardware configurations such as LiDAR, 3D depth camera, 7-inch LCD screen, and far-field microphone array can realize robot motion control, mapping navigation, path planning, tracking and obstacle avoidance, autonomous driving, 3D grabbing, navigation and handling, somatosensory interaction, far-field voice interaction, group control formation, and other applications.To power advanced embodied AI applications, JetAuto Pro also deploys a multimodal large AI model that supports both online and local deployment. Deep integration with the OpenClaw agent framework establishes a complete closed loop spanning from perception to physical execution, facilitating high-level capabilities including natural language interaction, scene understanding, cross-platform collaboration, proactive response, dynamic calling, and spatial memory. To help you unlock its full potential, we offer open-source code and learning resources to inspire and support your AI projects. Integrated with the OpenClaw Agent Deeply integrated with the OpenClaw agent, JetAuto Pro can be controlled through a PC or app, breaking device and scenario limitations. With built-in remote text and voice control, it supports multimodal command input, accurately perceives complex environments, makes real-time intelligent decisions, and autonomously plans and completes refined task workflows. Multimodal Large AI Models Deployed JetAuto Pro deploys language, speech, and vision multimodal large AI models supporting both online and local deployment. Integrating these models with AI vision significantly enhances environmental perception and instruction comprehension