No abstract

Abstract-The choice of an adequate object shape representation is critical for efficient grasping and robot manipulation. A good representation has to account for two requirements: it should allow uncertain sensory fusion in a probabilistic way and it should serve as a basis for efficient grasp and motion generation. We consider Gaussian process implicit surface potentials as object shape representations. Sensory observations condition the Gaussian process such that its posterior mean defines an implicit surface which becomes an estimate of the object shape. Uncertain visual, haptic and laser data can equally be fused in the same Gaussian process shape estimate. The resulting implicit surface potential can then be used directly as a basis for a reach and grasp controller, serving as an attractor for the grasp end-effectors and steering the orientation of contact points. Our proposed controller results in a smooth reach and grasp trajectory without strict separation of phases. We validate the shape estimation using Gaussian processes in a simulation on randomly sampled shapes and the grasp controller on a real robot with 7DoF arm and 7DoF hand.

We present a model of online Goal Babbling for the bootstrapping of sensorimotor coordination. By modeling infants' early goal-directed movements we show that inverse models can be bootstrapped within a few hundred movements even in very high-dimensional sensorimotor spaces. Our model thereby explains how infants might initially acquire reaching skills without the need for exhaustive exploration, and how robots can do so in a feasible way. We show that online learning in a closed loop with exploration allows substantial speed-ups and, in high-dimensional systems, outperforms previously published methods by orders of magnitude.

No abstract

No abstract