Uncalibrated Path Planning in the Image Space for the Fixed Camera Configuration

Image-based visual servoing can be used to efficiently control the motion of robot manipulators. When the initial and the desired configurations are distant, however, as pointed out by many researchers, such a control approach can suffer from the convergence and stability problems due to its local properties. By specifying adequate image feature trajectories to be followed in the image, we can take advantage of the local convergence and stability of image-based visual servoing to avoid these problems. Hence, path planning in the image space has been an active research topic in robotics in recent years. However, almost all of the related results are established for the case of camera-in-hand configuration. In this paper, we propose an uncalibrated visual path planning algorithm for the case of fixed-camera configuration. This algorithm computes the trajectories of image features directly in the projective space such that they are compatible with rigid body motion. By decomposing the projective representations of the rotation and the translation into their respective canonical forms, we can easily interpolate their paths in the projective space. Then, the trajectories of image features in the image plane can be generated via projective paths. In this way, the knowledge of feature point structures and camera intrinsic parameters are not required. To validate the feasibility and performance of the proposed algorithm, simulation results based on the puma560 robot manipulator are given in this paper.