Planning realistic interactions for bimanual grasping and manipulation

Abstract

This work presents a dual arm grasp planning architecture that includes two relevant aspects often neglected: differences in hand actuation, and realistic forces applicable by the end effectors. The introduction of an actuation matrix allows considering differences in contact forces that can be generated between, for instance, a fully actuated and an underactuated hand. The consideration of realistic forces allows the computation of real magnitudes of forces and torques that can be resisted by the grasped object. The manipulability workspace can also be computed based on the capability maps, thus providing all the possible motions that can be imparted on the grasped object while respecting the dual hand grasp constraints. The joint consideration of these factors allow the selection of a good grasp for a desired bimanual manipulation.

Planning Fail-Safe Trajectories for Space Robotic Arms

“…Two reachability maps can be merged as described in Sundaram et al (2016): each bin v i,p ∈ N of the resulting map FIGURE 3 | Capability maps for the KUKA iiwa robot when each joint is locked at its zero position while all the other joints are fully operational. The cross-section is displayed using the same scale and the same cutting plane (XZ), but the point of view is changed in some maps to provide a better 3D visualization.…”

“…It captures all poses reachable by the robot’s end-effector frame with respect to the robot base. These maps were initially introduced in Zacharias et al (2007) and Diankov (2010) , and have been used in multiple applications including workspace analysis and robot design in Porges et al (2015) , pre-filtering of inverse kinematics queries in Porges et al (2014) , robot base positioning as in Zacharias et al (2009b) ; Vahrenkamp et al (2013) , bi-manual manipulation planning in Sundaram et al (2016) ; Vahrenkamp et al (2009) , path generation or validation in Zacharias et al (2009a) and humanoid robot foot-step planning in Werner et al (2016) .…”

“…Two reachability maps can be merged as described in Sundaram et al (2016) : each bin v i,p ∈ N of the resulting map holds an integer value reflecting the number of maps from the set that identify this particular bin as reachable. A new interpreter function called failure index F ( V i ) is computed in an analogue manner to the reachability index, and defined as where is the p -th bin value of voxel i in reachability map k , and n m represents the number of maps generated, i.e.…”

Cálculo de fuerzas de contacto para prensiones bimanuales

“…El uso de métodos de optimización para calcular las fuerzas de contacto para sistemas bimanuales es unárea de investigación activa debido a la complejidad que los sistemas bimanuales imponen, sin embargo los trabajos desarrollados enésté ambito son escasos [12,18]. Por tal motivo, en este trabajo se presenta un método para calcular las fuerzas de contacto para prensiones bimanuales utilizando un método de optimización lineal considerando las limitaciones de torque de las articulaciones de los dedos de las manos.…”

Learning Singularity Avoidance

“…The MIE learnt from 50 trajectories is 0.002, therefore it is learnt successfully with errors below 10 −2 . 3 While it is shown that the manipulability index is learnt, it is important to establish whether the estimated manipulability is still suitable as a cost function to avoid singularity despite a greater error margin in comparison to the simulated 3DOF system. To this end, the RMSE is evaluated for 20 randomly generated trajectories of 100 points using the learnt model.…”