A Vision-Based Coordinated Motion Scheme for Dual-Arm Robots

With the rise of service robots, research on cooperation between two-arm robots has become increasingly important. In this paper, two NAO two-armed robots are used as the experimental platform and are combined with projective geometry, vision, robotics and other knowledge to carry out theoretical derivation and experiments on the coordinated movements of dual-arm robots. From the aspect of visual information processing, we analyse and solve the detailed target recognition process. Then, on this basis, we propose a set of complete coordinated motion control schemes. For object recognition, in this paper, we propose a highly adaptable linear stick recognition method. To solve the control flow of coordinated movement, we calculate the inverse kinematics of the unreachable pose of a single NAO manipulator by ignoring the degree of freedom of rotation around an end axis, and propose a trajectory planning method for the vertical constraint relationship between the tool and the workpiece plane in the coordinated manipulator movement. A comparison of the results of a simulation and a real experiment reveals that the trajectories of a workpiece clamped at the ends of the two robots’ mechanical arms are roughly the same; consequently, the coordinated control scheme proposed in this paper is feasible. Moreover, the scheme proposed in this paper is sufficiently accurate to meet service robot applications in daily life. Because the joint active clearance of the NAO robot arm is large and its sensor sensitivity is high, clearance change can be used in the future to replace the force sensor for hybrid control.