Benchmarking the Sim-to-Real Gap in Cloth Manipulation
This work addresses the problem of evaluating simulation accuracy for deformable object manipulation, which is crucial for researchers in robotics and simulation, but it is incremental as it builds on existing simulators without introducing new methods.
The authors tackled the lack of evaluation for the sim-to-real gap in cloth manipulation by creating a benchmark dataset from dynamic and quasi-static tasks, and used it to assess four popular simulators (MuJoCo, Bullet, Flex, SOFA) in terms of reality gap, computational time, and stability.
Realistic physics engines play a crucial role for learning to manipulate deformable objects such as garments in simulation. By doing so, researchers can circumvent challenges such as sensing the deformation of the object in the realworld. In spite of the extensive use of simulations for this task, few works have evaluated the reality gap between deformable object simulators and real-world data. We present a benchmark dataset to evaluate the sim-to-real gap in cloth manipulation. The dataset is collected by performing a dynamic as well as a quasi-static cloth manipulation task involving contact with a rigid table. We use the dataset to evaluate the reality gap, computational time, and simulation stability of four popular deformable object simulators: MuJoCo, Bullet, Flex, and SOFA. Additionally, we discuss the benefits and drawbacks of each simulator. The benchmark dataset is open-source. Supplementary material, videos, and code, can be found at https://sites.google.com/view/cloth-sim2real-benchmark.