All measurements are visualised in real-time, either in Windows or in Linux.

Provides the coordinates of all contacts. Different contact areas are separated, and the centre of each contact area is provided.

Obtain tactile measurements. Our software collects the measurements from all skin patches and prepares them for your application. Currently, we provide the measurements in Windows and Linux, as well as for ROS.

Detects the weight of an object by slightly lifting the object.

This can be used for quality control and/or for deciding the necessary grasping force.

Detects the roughness of an object. By slightly moving across the surface of an object, its texture can be detected.

This can be used, for example, for quality control and for appropriately grasping the object. 

Detects the adhesion of an object by slightly rubbing the object.
This provides valuable information for deciding how to grasp the object reliably.

Detect the stiffness of an object by slightly squeezing an object. This can be used, for example, to make sure not to grasp objects too hard to avoid breaking them. 

In addition to visual information, the local object shape can be obtained through tactile sensing. By repeatedly touching the object, the overall object shape can be obtained, and this information can be used to handle the object correctly. 

Detect the orientation of the object within the gripper. The correct orientation of the object is crucial for various tasks, for example, when inserting the object in a hole.

Localise objects in the hand. This function reveals the object’s relative position in relation to the gripper.

Recognise objects from a database of previously memorised objects. By slightly touching the object, its tactile features can be recognised, which can be used to recognise objects.

‍

This can be used, for example, to ensure that the grasped object is the correct one. It works in addition to vision, for example, when vision fails due to occlusions or poor light conditions. 

Provides various information about the contacts.
For each contact area, we will provide information about the curvature radius of an object and can recognise contact area properties such as edges, corners, and flat surfaces.

‍

Grasp objects with predefined force. Set the desired grasping force, and our software ensures that the object is grasped with this force.

Detect the onset of slip. We can detect slip within a few milliseconds, and the gripper can respond to it, for example, by grasping the object slightly stronger.

‍

Predict grasp success. Even before lifting the object, we can distinguish stable from unstable grasps. This allows the opportunity to re-grasp the object in advance and ensure that it will not be slipping out of the hand while transporting it.

‍

After detecting an unstable grasp, we provide suggestions for how to change the grasp so that it will be more stable. In particular, the object could be grasped stronger, if permissible, or the position of the grasp can be modified.

‍

If the grasp is too firm, the object is deforming. After detecting this, the grip strength can be reduced if so desired.

By collecting data about grasps, the algorithm automatically improves due to the additional training data.

‍