Interaction with unstructured groups of objects allows a robot to discover and manipulate novel items in cluttered environments. We present a framework for interactive singulation of individual items from a pile. The proposed framework provides an overall approach for tasks involving operation on multiple objects, such as counting, arranging, or sorting items in a pile. A perception module combined with pushing actions accumulates evidence of singulated items over multiple pile interactions. A decision module scores the likelihood of a single-item pile to a multiple-item pile based on the magnitude of motion and matching determined from the perception module. Three variations of the singulation framework were evaluated on a physical robot for an arrangement task. The proposed interactive singulation method with adaptive pushing reduces the grasp errors on non-singulated piles compared to alternative methods without the perception and decision modules. This work contributes the general pile interaction framework, a specific method for integrating perception and action plans with grasp decisions, and an experimental evaluation of the cost trade-offs for different singulation methods.

Studies of human manipulation strategies suggest that pre-grasp object manipulation, such as rotation or sliding of the object to be grasped, can improve task performance by increasing both the task success rate and the quality of load-supporting postures. In previous demonstrations, pre-grasp object rotation by a robot manipulator was limited to manually-programmed actions. We present a method for automating the planning of pre-grasp rotation for object transport tasks. Our technique optimizes the grasp acquisition point by selecting a target object pose that can be grasped by high-payload manipulator configurations. Careful selection of the transition states leads to successful transport plans for tasks that are otherwise infeasible. In addition, optimization of the grasp acquisition posture also indirectly improves the transport plan quality, as measured by the safety margin of the manipulator payload limits.

Although the human hand is a complex biomechanical system, only a small set of features may be necessary for observation learning of functional grasp classes. We explore how to methodically select a minimal set of hand pose features from optical marker data for grasp recognition. Supervised feature selection is used to determine a reduced feature set of surface marker locations on the hand that is appropriate for grasp classification of individual hand poses. Classifiers trained on the reduced feature set of five markers retain at least 92% of the prediction accuracy of classifiers trained on a full feature set of thirty markers. The reduced model also generalizes better to new subjects. The dramatic reduction of the marker set size and the success of a linear classifier from local marker coordinates recommend optical marker techniques as a practical alternative to data glove methods for observation learning of grasping.

The thumb is essential to the hand's function in grasping and manipulating objects. Previous anthropomorphic robot hands have thumbs that are biologically-inspired but kinematically-simplified. In order to study the biomechanics and neuromuscular control of hand function, an anatomical robotic model of the human thumb is constructed for the anatomically-correct testbed (ACT) hand. This paper presents our ACT thumb kinematic model that unifies a number of studies from biomechanical literature. We also validate the functional consistency (i.e. the nonlinear moment arm values) between the cadaveric data and the ACT thumb. This functional consistency preserves the geometric relationship between muscle length and joint angles, which allows robotic actuators to imitate human muscle functionality