This paper proposes a set of techniques for predictive collision avoidance, which ensure robust operation of robot applications. Implementation issues for applying the techniques to state-of-art robots are presented, including integration with manual and automatic operation modes.
The paper presents a method and related algorithm for visual robot guidance in tracking objects moving on conveyor belts; the instantaneous location of the moving object is evaluated by a vision system consisting from a stationary, down looking monochrome video camera, a controller-integrated image processor and a vision extension of the structured V+ robot programming environment. The algorithm for visual tracking of the conveyor belt for "on-the-fly" object grasping is partitioned in two stages: (i) visual planning of the instantaneous destination of the robot, (ii) dynamic re-planning of the robot's destination while tracking the object moving on the conveyor belt. The control method uses in addition the concept of Conveyor Belt Window -CBW. The paper discusses in detail the motion control algorithm for visually tracking the conveyor belt on which objects are detected, recognised and located by the vision part of the system. Experiments are finally reported in what concerns the statistics of object locating errors and motion planning errors function of the size of the objects and of the belt speed. These tests have been carried out on a 4-d.o.f. SCARA robot with artificial vision and the AVI AdeptVision software extension of the V+ high-level, structured programming environment.
I. MODELLING CONVEYOR BELTS BY MEANS OF BELT VARIABLESThe principal mechanism which allows specifying robot motions relative to a conveyor belt consists into modelling the belt by a special type of location data, defined as belt variables. A belt variable is considered as a relative transformation (having a component variable in time) which defines the location of a reference frame attached to the moving belt conveyor [1].Using such a belt variable, it becomes possible to describe in time the relationship between a belt encoder and the location and speed of a reference frame which maintains a fixed position and orientation relative to the belt. The definition of a belt variable is given by:DEFBELT %belt_variable = nominal_trans, scale_factor where: (i) %belt_variable is the name of the belt variable to be defined, (ii) nominal_trans represents the value in 6 R of the (simple or composed) relative transformation which defines the position and the orientation of the conveyor belt, and (iii) scale_factor is a calibrating constant specifying the ratio between the elementary displacement of the belt and one pulse of the encoder. The X axis of nominal_trans indicates the direction of motion of the belt, the XY plane defined by this transformation is parallel to the conveyor's belt surface, and the position (X,Y,Z) specified by the nominal transformation points to the approximate centre of the belt relative to the base frame of the robot. It has been decided that the origin of nominal_trans be always chosen in the middle of the robot's working displacement over the conveyor.The current orientation in a belt variable is invariant in time, equal to that expressed by nominal_trans. In order to evaluate the current location updated by the same be...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.