With the innovative and modular software rc_reason, image data interpretation becomes easy. rc_reason components can be easily activated on-board any rc_visard, and intuitively operated through the sensor’s standard user interface.
The rc_reason SilhouetteMatch Module detects position and orientation of comparatively flat objects that are positioned on a planar surface in unmixed scenes. By matching the scene at hand to a previously taught template, the 3D position and orientation is determined for each object, and grasp points can be defined.
Typical applications include machine tending or emptying load carriers of several (separated) layers of objects.
The rc_reason BoxPick Module provides a solution for robotic pick-and-place applications such as de-/palletizing and sorting of packets.
Equipped with the BoxPick Module, the rc_visard detects rectangular surfaces over pre-defined size ranges and optionally computes potential grasp points. It allows the detection of the position, the orientation and the size of the objects and enables the robot to place the objects in a defined position.
NEW! You want to run the ItemPick Module on a Universal Robot?
Not a problem with our URCap: Designed specifically for this purpose,
and now available as a plug-and-play bundle solution…
The rc_reason ItemPick Module is a solution for robotic pick-and-place applications using suction grippers: It computes surface grasp poses for a suction device on a given object.
ItemPick applications, in particular for difficult objects or workspaces, can be optimized by equipping the rc_visard with a projector and corresponding IO Control Module.
The RandomDot Projector is a specifically tailored projector that can be used as an enhancement to the rc_visard when the perception of particularly difficult scenes with little or no natural texture is required.
It increases the scene density and hence improves the quality of stereo matching when the natural scene texture is insufficient.
SLAM (Simultaneous Localization and Mapping) allows rc_visard to create a map of its environment, while simultaneously estimating its current location. This is an important part of the GPS-free navigation on unknown terrain. The SLAM module runs onboard the rc_visard, no external hardware is required.
The TagDetect component enables a robust out-of-the-box detection of QR codes and AprilTags. In addition, it calculates the 3D position and orientation of each tag relative to the sensor. It can be used e.g. for localizing the sensor or for the identification and localization of objects. Its detection time of less than 1s enables highly efficient applications.
Objects can be identified and manipulated through our advanced algorithms. The exact distance to the object is determined from the depth data provided by rc_visard. As a result, novel application fields can be addressed in all domains of robotics.
Object data, such as geometry, features and associated handles, is stored in an object data database. All modules of rc_reason have access to this data base so that modules do not need to store object data themselves. The database can be updated and extended by the customer at any time.