Recognising Known Configurations of Garments For Dual-Arm Robotic Flattening
This work addresses the problem of efficient garment flattening for robotic systems in the industry, but it appears incremental as it builds on existing manipulation planning with known configurations.
The paper tackles the challenge of robotic deformable-object manipulation by learning known configurations of garments, enabling a robot to recognize garment states and select pre-designed plans for flattening, which addresses time-consuming and computationally expensive state prediction and planning.
Robotic deformable-object manipulation is a challenge in the robotic industry because deformable objects have complicated and various object states. Predicting those object states and updating manipulation planning is time-consuming and computationally expensive. In this paper, we propose learning known configurations of garments to allow a robot to recognise garment states and choose a pre-designed manipulation plan for garment flattening.