IMAGINE aims to develop methods that enable robots to gain a better understanding of how they interact with their environment and how they change. This should improve the autonomy, flexibility and robustness of robots' manipulation capabilities in the face of unforeseen changes. The approach is based on the development of a low-cost gripper for the dismantling and recycling of electromechanical devices, such as hard disks. The structural understanding of electromechanical devices and the functional understanding of robot actions will be extended to disassemble categories of electromechanical devices and appliances, to monitor the success of actions and to propose corrective strategies if necessary.

KIT is responsible for the development of a multifunctional reconfigurable gripper for disassembling electromechanical devices. KIT also manages the tasks of learning disassembly actions from human observation and the integration of components of object and affordance perception, planning, simulation, and action execution into a holistic system architecture that is evaluated on several functional demonstrators.