Goal-Conditioned Action Space Reduction for Deformable Object Manipulation

Planning for deformable object manipulation has been a challenge for a long time in robotics due to its high computational cost. In this work, we propose to reduce this cost by reducing the number of pick points on a deformable object in the action space. We do this by identifying a small number of key particles that are sufficient as pick points to reach a given goal state. We find these key particles through a geometric model simplification process, which finds the minimal geometric model that still enables a good approximation of the original model at the goal state. We present an implementation of this general approach for 1-D linear deformable objects (e. g. , ropes) that uses a piece-wise line fitted model, and for 2-D flat deformable objects (e. g. , cloth) that uses a mesh simplified model. We conducted simulation experiments on ropes and cloths, which demonstrate the effectiveness of the proposed method. Finally, the planned paths are executed in a real-world setting for two cloth folding tasks.

Authors

• Shengyin Wang
• Rafael Papallas
• Matteo Leonetti
• Mehmet Remzi Dogar

Keywords

• Deformable models
• Costs
• Automation
• Computational modeling
• Geometric modeling
• Dynamics
• Planning
• Deformable Objects
• Simple Model
• Model Estimates
• Simulation Experiments
• Simple Process
• Geometric Model
• Goal State
• Conduct Simulation Experiments
• 3D Space
• Line Segment
• Path Planning
• Model Configuration
• 2D Model
• Manipulation Tasks
• Quadratic Programming
• Particle Position
• Piece Of Cloth
• Planning Framework
• Hausdorff Distance
• Real Robot
• Intermediate Goals
• Rapidly-exploring Random Tree
• Impedance Control
• Mass-spring System
• Cost Curve