Periodic inspection of weld seam quality is an important step in assessing equipment safety. But this task requires personnel to perform inspection rounds. To save labor costs and improve efficiency, autonomous navigation and autonomous weld inspection robot are developed. The development process involves the design of chassis damping, target detection mechanism, and control system and algorithms. In particular, when performing weld inspection in complex outdoor environments, the robot is required to avoid any obstacles. The problem of planning the inspection route is solved by improving a timed elastic band (TEB) algorithm. The robot is capable of conducting inspection tasks in complex and dangerous environments efficiently.