Deformable Object Manipulation @ KAIST

Deformable Object Manipulation

Code

We utilize simulated environments in IsaacSim or employ teleoperation to guide and teach the robots, such as deformable object manipulation. (Ahn et al., 2022)

My development partially contributed to this paper.

DetactGym: Deformable Object Manipulation Gym that specialized rubber band manipulation. We prepared real-world experiments.

Literature Survey: Simulated Based Grasping of Deformable Object

References

Project

DEFTACTGYM: A Reinforcement Learning Testbed for Deformable Object Manipulation Using Visuotactile Sensory Data

Chanyoung Ahn, Bonggyeong Park, Jaehwi Jang, Minwoo Cho, Jeongho Ha, Daehyung Park

RIRO Lab @ KAIST Dec 2022

Abs PDF Code Blog

We aim to create a simulated testbed for training and assessing deformable object manipulation skills. This testbed requires tactile data to detect occluded deformation to acquire skills. In this work, we introduce a tactile testbed, DetactGym, with custom-built tactile sensors. We implement tactile sensors as a combination of a rigid trigger and a force-reading part to address the IsaacSim simulator’s inability to read contact forces in deformable. The trigger transmits the contact force to the sensor upon interaction with the target deformable. We highlight the effectiveness of tactile information over visual cues in handling deformable objects while minimizing deformation.