Systematic quantification and analysis of multi-joint robotic arms based on deep learning

In the modern intelligent environment, there is an increasing demand for unmanned and autonomous operations. Intelligent equipment operations replace manual labour, solving the problems caused by repetitive, complex and high-risk operating environments, saving manpower and material resources while improving productivity and reducing accident rates. The operation of many intelligent devices requires constant switching of workplaces, so many industries have invested in a large number of mobile robots. The chassis of robots are divided into many categories depending on their function. Four-wheeled Ackermann models are generally used more often in unmanned vehicles, differential models used more often in AGVs, four-wheeled omnidirectional wheel chassis used in competitions and four-wheeled skid steer chassis. The chassis used for the mobile robotic arm covered in this thesis is a four-wheeled McNamee wheel chassis, and this chassis model is presented.