Development and Learning

Developing the K1 robot for learning and testing purposes, facilitating developers in familiarizing themselves with the ROS system while also testing AI-related functionalities.

Development and Learning

K1 is South Newport’s flagship product aimed at the ROS education entry-level scene, integrating NavBot chassis technology and accumulated ROS tutorial expertise to achieve an ideal balance of educational performance, cost-effectiveness, and quality. Offering multiple chassis options and source-level tutorials(not just demonstrations),K1 comes equipped with high-value radar and depth camera accessories,catering to learning in mapping navigation,deep learning,3D vision,robot formation,and other areas. With technical support provided, it meets the needs of both beginners and those seeking to advance their skills.

Key Features Overview 01

RTAB-Map Visual And Lidar 3D Mapping Navigation

Support For RTAB-Map Pure Visual Mapping Navigation, Support For Fusion MappingNavigation Of Lidar And Visual Perception

Classic 2D Lidar Mapping, Navigation, And Obstacle Avoidance

Support For Gmapping, Hector, Karto, And Cartographer Mapping AlgorithmsSupport For Point-To-Point Navigation, Multi-Point Navigation, And Obstacle Avoidance DuringNavigation

Key Features Overview 02

ORB Visual Mapping Function

ORB-SLAM2 Is An Open-Source SLAM Framework That Supports Monocular, Stereo, And RGB-DCameras. lt Can Calculate The Camera's Pose In Real-Time And Simultaneously Perform Sparse3D Reconstruction Of The Surrounding Environment. Additionally, In Stereo And RGB-D Modes, ltCan Provide True-Scale Information.

ROS OT (ROS Operation Tool) Functionality With Graphical Usernterface

Deploying ROS OT Graphical User Interface To Facilitate One-Click Activation Of ROSFunctionalities, Providing Intuitive Feedback On Vehicle Speed, Battery Level, And OtherInformation.

Key Features Overview 03

Three-Dimensional Reconstruction In Real Autonomous Driving

For RayShen Multiline Lidar Enables Outdoor 3D Mapping, Bringing Us Closer To RealAutonomous Driving.

Autonomous Parking Feature

Implementing Full-Automatic Parking AndGarage Entry For Robots Through ProprietaryPatented Algorithms Combined With DeepLearning Represents A Core Functionality InThe Autonomous Driving Industry.

Lane Keeping Functionality InAutonomous Driving Lane Keeping By Lane

Lane Keeping By Lane Recognition Using CoreAlgorithms, A Core Functionality In TheAutonomous Driving ndustry

Key Features Overview 04

Steering Decision Functionalityn Autonomous Driving

Integrated Decision Making Using ProprietaryAlgorithms And Deep Learning-Based Lane AndTraffc Sign Recognition, A Core Functionality InThe Autonomous Driving industry

Yolo Traffc Sign Recognition

Step-By-Step Guide To Train Your Own Deepearning Model Library, lmplementing BasicAutonomous Driving Functionality Using AnRGB Camera

Yolo Obiect And GestureRecognition

GestureRecognition Using Common Deep Learning Model LibrariesFor Everyday Obiect Recognition

ROS Tensorflow Obiect Detection

Based On TensorFlow, You Can lmplement TheRecognition Of Common Objects AndHandwritten Diait Recoanition.

Key Features Overview 05

Deep Visual Tracking

Implementing Robot Following Using DepthCamera To Recognize Obiect Distance AndOrientation

KCF Object Tracking

Implementing Robot Following By RecognizingFixed Feature Objects Using Depth Camera

AR Tag Recognition And Following

Implementing Robot FollowinlmplementingRobot Following By Recognizing And TrackingAR Tag Pose Using Depth Camera, With TheAbility To Extend AR Tag Localizationg ByRecognizing Fixed Feature Obiects Using Depth Camera

Rapidly-Exploring Random Tree(RRT)Autonomous ExplorationMapping

Autonomous Exploration Mapping, MapSaving, And Returning To The Starting PointUsing RRT Algorithm Without Human ntervention

Welcome to contact us.

We look forward to connecting with you and providing our services!

Solution