ABSTRACT
Visual feedback can play a crucial role in a dynamic robotic task such as the interception of a moving target To utilize the feedback effectively, there is a need to de velop robot motion planning techniques that also take into account properties of the sensed data. We pro pose a motion planning framework that achieves this with the help of a space called the Perceptual Control Manifold or PCM defined on the product of the robot configuration space and an image-based feature space. We show how the task of intercepting a moving target can be mapped to the PCM, using image feature trajec tories of the robot end-effector and the moving target This leads to the generation of motion plans that sat isfy various constraints and optimality criteria derived from the robot kinematics, the control system, and the sensing mechanism. Specific interception tasks are an alyzed to illustrate this vision-based planning technique.
Sensor feedback is important in the flexible operation of a robot. The feedback could be critical in a dynamic manipulation task such as grasping a moving target, since the robot motion goal could be changing with time. Further, because of the temporal element in the definition of such tasks, effective motion planning is needed to drive the robot toward the moving goal. Such interception tasks would be involved, for example, in an assembly robot that picks a randomly placed object on a conveyor belt or in a space robot that acquires a moving target.
