Bimanual compliant tactile exploration for grasping unknown objects

Abstract

Abstract-Humans have an incredible capacity to learn properties of objects by pure tactile exploration with their two hands. With robots moving into human-centred environment, tactile exploration becomes more and more important as vision may be occluded easily by obstacles or fail because of different illumination conditions. In this paper, we present our first results on bimanual compliant tactile exploration, with the goal to identify objects and grasp them. An exploration strategy is proposed to guide the motion of the two arms and fingers along the object. From this tactile exploration, a point cloud is obtained for each object. As the point cloud is intrinsically noisy and un-uniformly distributed, a filter based on Gaussian Processes is proposed to smooth the data. This data is used at runtime for object identification. Experiments on an iCub humanoid robot have been conducted to validate our approach.

Dexterous grasping under shape uncertainty

“…4(e)-(h), when the training data points are sampled from the whole object point cloud, the variance or shape uncertainty is generally very small on the whole surface except the parts with sparse or with even no data points, such as the bottom of the jug. In robotic grasping tasks, due to the occlusion [48,49] or non-reachability from tactile exploration [21], it is usually the case that some parts of the object are not perceivable and point-clouds exhibit holes. To evaluate our method under missing data points, we use MeshLab 3 to simulate partial view of point clouds with a fixed camera view, and then obtain object point cloud from that virtual camera.…”

“…The object point clouds are obtained from laser scanner and 1000 data points are randomly sampled from the original point cloud. To speed up the object shape modeling procedure, we further adopt a GP-based filter to select the most informative data points [21] for representing the GP. The filtered data points for GP are shown as spheres on the object surface, Fig.…”

“…Few works have considered object shape uncertainty by integrating planning and control. However, in real robotic grasping tasks due to the, for example, occlusion problems [48,49,22] or non-reachability from tactile exploration [21], object shape uncertainty is inevitable. In this work, we thus integrate object uncertainty in grasp planning and control.…”

“…For instance, the concept of independent contact regions (ICRs) is introduced to provide robustness to finger placement error [24] where any grasp with fingertip's positions inside the ICR will achieve a force-closure grasp. The uncertainty information can also be updated online using vision [23,47] or tactile exploration [20,21,22]. However, these approaches usually use a set of predefined grasps and require several rounds of grasp trials.…”

Multi-contact haptic exploration and grasping with tactile sensors

“…We also developed an algorithm for bi-manual haptic exploration of objects [13], using multiple phalanxes per finger, covered with tactile sensors, for the 3-d reconstruction of the objects' shapes. However, these approaches were limited in the range of object's shapes that could be explored.…”