Force-prediction Scheme for Precise Grip-lifting Movements

In this work we present a novel Supervised Learning scheme for executing sensitive Force-based manipulation tasks. The proposed scheme, termed SLF, is formulated as a three-stage process: (a) supervised trial-execution in simulation to acquire sufficient training data; (b) training to facilitate grasp learning with suitable robot-arm pose and lifting force; (c) grasp execution in simulation. Consequently, following sim-to-real transfer, operation in real environments is achieved in addition to simulated ones, generalizing also for objects not included in the trial sessions. The proposed learning scheme is demonstrated in object lifting tasks where the applied force varies for different objects with similar contact friction coefficients, and likewise the grasping pose. Experimental results on the manipulator YuMi show that the robot is able to effectively reproduce demanding lifting and manipulation tasks after learning is accomplished.