A Convex-Combinatorial Model for Planar Caging

by   Bernardo Aceituno-Cabezas, et al.
Toyota Research Institute

Caging is a promising tool which allows a robot to manipulate an object without directly reasoning about the contact dynamics involved. Furthermore, caging also provides useful guarantees in terms of robustness to uncertainty, and often serves as a way-point to a grasp. Unfortunately, previous work on caging is often based on computational geometry or discrete topology tools, causing restriction on gripper geometry, and difficulty on integration into larger manipulation frameworks. In this paper, we develop a convex-combinatorial model to characterize caging from an optimization perspective. More specifically, we study the configuration space of the object, where the fingers act as obstacles that enclose the configuration of the object. The convex-combinatorial nature of this approach provides guarantees on optimality, convergence and scalability, and its optimization nature makes it adaptable for further applications on robot manipulation tasks.


Manipulation of unknown objects via contact configuration regulation

We present an approach to robotic manipulation of unknown objects throug...

Building 3D Object Models during Manipulation by Reconstruction-Aware Trajectory Optimization

Object shape provides important information for robotic manipulation; fo...

Certified Grasping

This paper studies robustness in planar grasping from a geometric perspe...

Manipulation with Shared Grasping

A shared grasp is a grasp formed by contacts between the manipulated obj...

Reactive Planar Manipulation with Convex Hybrid MPC

This paper presents a reactive controller for planar manipulation tasks ...

Pneumatic Shape-shifting Fingers to Reorient and Grasp

We present pneumatic shape-shifting fingers to enable a simple parallel-...

Please sign up or login with your details

Forgot password? Click here to reset