Motion planning for robotic manipulation of deformable linear objects

By Mitul Saha, Pekka Isto, Jean-Claude Latombe. 2006

140 citations recorded by the source corpus.

Research on robotic manipulation has mainly focused on manipulating rigid objects so far. However, many important application domains require manipulating deformable objects, especially deformable linear objects (DLOs), such as ropes, cables, and sutures. Such objects are far more challenging to handle, as they can exhibit a much greater diversity of behaviors. This paper describes a new motion planner for manipulating DLOs and tying knots (self-knots and knots around simple static objects) using cooperating robot arms. The planner constructs a topologically-biased probabilistic roadmap in the DLO's configuration space. Unlike in traditional motion planning problems, the goal is a topological state of the world, rather than a geometric one. The implemented planner was tested in simulation to achieve various knots like bowline, neck-tie, bow (shoe-lace), and stun-sail

Subfields: Building and Construction, Control and Systems Engineering, Industrial and Manufacturing Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Control and Systems Engineering

In Industrial and Manufacturing Engineering

Citations in the corpus

Combining self-supervised learning and imitation for vision-based rope manipulation (2017, background): “[22] investigated the problem of knot tying and following works used motion planning [23], fixtures for open-loop execution [3] and robotic hands with tactile feedback [24].”
Continuous Backbone “ Continuum ” Robot Manipulators : A Review (2013, unknown): “The existence of practical, real-time, sensor-based motion planning algorithms will be important in moving the technology from the laboratory to numerous real applications [106].”
Flexible Object Manipulation (2010, background): “Saha, Isto, and Latombe developed a string model and motion planning algorithms for tying simulated knots [68, 70, 69].”
One-handed knotting of a flexible rope with a high-speed multifingered hand having tactile sensors (2007, background): “Mitul et al. proposed a topological motion planner for manipulating flexible linear objects and demonstrated the effectiveness of their proposed planner experimentally [6].”
Learning from Demonstrations Through the Use of Non-rigid Registration (2013, background): “Researchers have addressed the problemwithmotion planning [12, 13], learning from observation (using knot theoretic representations) [14], robotic hands with tactile feedback [15], and fixtures that enable robust open-loop”
Cable manipulation with a tactile-reactive gripper (2019, background): “Due to their high dimensional dynamics, manipulating deformable linear objects is usually simplified by constraining their motion with external features, for example against a table [1, 2, 3], with additional grippers [12], or pegs [11].”