Design of experimental teaching platform based on multifunctional autonomous mobile grasping robots
[Objective]In an effort to meet the growing demand for hands-on experience in the training of robotics engineering talents,we have developed a multifunctional teaching platform featuring an autonomous mobile grasping robot.This platform introduces novel approaches and solutions for practical experiments,catering to courses in robotics engineering,artificial intelligence,and other emerging disciplines.[Methods]Central to the platform are two main components:a wheeled robot motion chassis equipped with lidar and a six-axis servo manipulator fitted with a depth camera and flexible grippers.The wheeled chassis provides exceptional mobility and stability,enabling precise navigation in diverse environments.The vision-guided mechanical arm allows the robot to identify,locate,and grasp objects.Integrating the autonomous motion chassis with the mechanical arm results in a system that accomplishes mapping and autonomous navigation,thereby expanding the working space of the mechanical arm.This enhances the functionality of the robot and widens its range of applications.The platform incorporates several key features,such as scene mapping using the Gmapping algorithm,which is based on particle filtering.This allows for precise map construction in complex environments.We have also integrated the A*algorithm and the TEB algorithm for path planning and navigation,enabling precise map construction in complex environments.The object recognition system,based on the Aruco_detect algorithm,rapidly and accurately identifies target objects,laying the foundation for subsequent grasping operations.To facilitate understanding and operation by students by students,the experimental platform provides two control modes:master-slave control and mobile web control via smartphones.Through the master-slave mode,students can control the mobile robot and experience its robust capabilities first-hand.Simultaneously,they can control the robot and observe mapping and navigation effects through the mobile web interface,gaining a more intuitive understanding of the robot's actual operational performance.To further optimize and enhance the platform performance,we have set up real-world experimental scenarios and conducted simulation scenario construction and data simulation work in a virtual environment based on the robot operating system(ROS).This approach enhances the platform's completeness and reliability while reducing experimental costs and providing students with more practical opportunities.[Results]Experimental tests have demonstrated that our platform can meet the diverse requirements of various experimental teaching scenarios.It supports secondary development,which encourages students to explore exploration different methods and contributes to the development of their comprehensive application skills,as well as their analytical and problem-solving abilities.Moreover,the platform encompasses cutting-edge technology applications such as ROS,simultaneous localization and mapping,autonomous navigation,object recognition,and grasping.This enables students to deeply comprehend the practical operation mechanism of robots and master the development process of robotic systems.[Conclusions]In summary,our platform represents a highly multifunctional teaching tool that offers significant research and educational benefits.By harmoniously blending simulations with real-world applications,we have not only managed to reduce the costs associated with traditional experimental teaching platforms,but we have also created a richer,more immersive learning environment where students can delve into the intricacies of robotics knowledge and technology.The use of the platform aids in understanding the operational mechanisms of robots,thereby enhancing students;learning outcomes and their practical application capabilities.Furthermore,exposure to this comprehensive teaching platform fosters innovative thinking and teamwork skills among students,laying a solid foundation for their future career development in the field of robotics engineering.
NETL
NSTL
万方数据
