Self-driving Training Lab
Introduction
Self-driving Training Lab is based on the visual perception of the autonomous driving scene of the unmanned vehicle, using the sand table and the unmanned car, combined with artificial intelligence algorithm and LiDAR SLAM technology to achieve decision control and path planning, to realize the autonomous driving of the unmanned vehicle in the sand table. The sand table can simulate a variety of common road conditions, such as single lane, dual lane, intersection, T-intersection, roundabout, crosswalk and other road scenes, including left turn, right turn, parking, bus stop, construction signs and other common traffic signs. Driverless intelligent vehicles can independently identify the road environment, actively perceive traffic signs, and realize autonomous driving in the sand table according to the preset logic. The training room covers the entire workflow of data acquisition and annotation, model training, model verification, model reasoning and deployment. Create "artificial intelligence + transportation" action.
Applicable Majors: Artificial Intelligence/Intelligent Science and Technology/Computer related majors
Course Products: robot programming, computer vision application, deep learning application development
Project Products: Application practice of the underlying hardware of unmanned intelligent vehicle, application practice of unmanned intelligent vehicle, vision-based environment perception and motion control of unmanned vehicle, radar-based environment perception and autonomous navigation, autonomous driving of unmanned vehicle in sand table scene based on AI
Intelligent Hardwares: intelligent car, teaching toolbox, simple sand table, customized sand table
Application Scenarios: professional teaching, comprehensive practical training, competition training
Feature
Derived from Real Industry Projects
• The project relies on Neusoft characteristic industry projects, derived from real industry projects and real business scenarios
Self-driving Training Lab is based on the visual perception of the autonomous driving scene of the unmanned vehicle, using the sand table and the unmanned car, combined with artificial intelligence algorithm and LiDAR SLAM technology to achieve decision control and path planning, to realize the autonomous driving of the unmanned vehicle in the sand table. The sand table can simulate a variety of common road conditions, such as single lane, dual lane, intersection, T-intersection, roundabout, crosswalk and other road scenes, including left turn, right turn, parking, bus stop, construction signs and other common traffic signs. Driverless intelligent vehicles can independently identify the road environment, actively perceive traffic signs, and realize autonomous driving in the sand table according to the preset logic. The training room covers the entire workflow of data acquisition and annotation, model training, model verification, model reasoning and deployment. Create "artificial intelligence + transportation" action.
Applicable Majors: Artificial Intelligence/Intelligent Science and Technology/Computer related majors
Course Products: robot programming, computer vision application, deep learning application development
Project Products: Application practice of the underlying hardware of unmanned intelligent vehicle, application practice of unmanned intelligent vehicle, vision-based environment perception and motion control of unmanned vehicle, radar-based environment perception and autonomous navigation, autonomous driving of unmanned vehicle in sand table scene based on AI
Intelligent Hardwares: intelligent car, teaching toolbox, simple sand table, customized sand table
Application Scenarios: professional teaching, comprehensive practical training, competition training
Feature
Derived from Real Industry Projects
• The project relies on Neusoft characteristic industry projects, derived from real industry projects and real business scenarios
• Through project training, students learn project development under real business scenarios, avoiding the gap between simulated projects and real projects
• Training process software and hardware organic combination to achieve the effect of real feedback and increase the interest in the practice process
• Keep up with the technological development of the unmanned driving industry and practical teaching methodology, and integrate elements such as new theories, new technologies, new tools, new products and new applications into the project and project supporting resources
