Manipulation for self-Identification, and self-Identification for better manipulation

The process of modeling a series of hand-object parameters is crucial for precise and controllable robotic in-hand manipulation because it enables the mapping from the hand's actuation input to the object's motion to be obtained. Without assuming that most of these model parameters are known a priori or can be easily estimated by sensors, we focus on equipping robots with the ability to actively self-identify necessary model parameters using minimal sensing. Here, we derive algorithms, on the basis of the concept of virtual linkage-based representations (VLRs), to self-identify the underlying mechanics of hand-object systems via exploratory manipulation actions and probabilistic reasoning and, in turn, show that the self-identified VLR can enable the control of precise in-hand manipulation. To validate our framework, we instantiated the proposed system on a Yale Model O hand without joint encoders or tactile sensors. The passive adaptability of the underactuated hand greatly facilitates the self-identification process, because they naturally secure stable hand-object interactions during random exploration. Relying solely on an in-hand camera, our system can effectively self-identify the VLRs, even when some fingers are replaced with novel designs. In addition, we show in-hand manipulation applications of handwriting, marble maze playing, and cup stacking to demonstrate the effectiveness of the VLR in precise in-hand manipulation control.

Integrated Motion Planning for Assembly Task with Part Manipulation Using Re-Grasping

This paper presents an integrated planner based on rapidly exploring random tree (RRT) for an assembly task with possible re-grasping. Given multiple grasp poses for the part to assemble, the planner chooses candidate grasp poses considering the environment (including the partially finished assembly) in addition to the initial and final poses of the part. Orientation graph search based re-grasping approach is proposed for part manipulation which is needed when there is no feasible grasp solution for a part between its initial and final poses. Orientation graph search helps finding a series of the intermediate poses of the part needed between its initial and final poses so that robot can grasp and assemble it without interfering the pre-assembled parts. Then while extending the tree, the algorithm tries to connect the tree to a robot configuration with a chosen candidate grasp pose. Also, since the task space undergoes changes at each step of the assembly task, a node or edge in the tree can become in collision during the assembly of later parts, making the node in collision and its descendant nodes disconnected from the whole tree. To handle this, Two stage extended RRT strategy is proposed. The disconnected parts of the main tree are put into forest, and attempts are made to re-connect the tree in the forest to main tree while extending the main tree, thus making it possible to use the disconnected part again. The algorithm is implemented in Linux based system using C++. The proposed algorithm is demonstrated experimentally using UR5e robot manipulator by assembling the soma puzzle pieces in different 3D formations.

Hand–object configuration estimation using particle filters for dexterous in-hand manipulation

We consider the problem of in-hand dexterous manipulation with a focus on unknown or uncertain hand–object parameters, such as hand configuration, object pose within hand, and contact positions. In particular, in this work we formulate a generic framework for hand–object configuration estimation using underactuated hands as an example. Owing to the passive reconfigurability and the lack of encoders in the hand’s joints, it is challenging to estimate, plan, and actively control underactuated manipulation. By modeling the grasp constraints, we present a particle filter-based framework to estimate the hand configuration. Specifically, given an arbitrary grasp, we start by sampling a set of hand configuration hypotheses and then randomly manipulate the object within the hand. While observing the object’s movements as evidence using an external camera, which is not necessarily calibrated with the hand frame, our estimator calculates the likelihood of each hypothesis to iteratively estimate the hand configuration. Once converged, the estimator is used to track the hand configuration in real time for future manipulations. Thereafter, we develop an algorithm to precisely plan and control the underactuated manipulation to move the grasped object to desired poses. In contrast to most other dexterous manipulation approaches, our framework does not require any tactile sensing or joint encoders, and can directly operate on any novel objects, without requiring a model of the object a priori. We implemented our framework on both the Yale Model O hand and the Yale T42 hand. The results show that the estimation is accurate for different objects, and that the framework can be easily adapted across different underactuated hand models. In the end, we evaluated our planning and control algorithm with handwriting tasks, and demonstrated the effectiveness of the proposed framework.