Online Learning of Part Deformation Models in Robotic Cleaning of Compliant Objects

Abstract

We present an approach to automatically learn a bimanual robotic cleaning task on compliant objects. One robot grasps the object, while the other robot cleans it. Given a part with unknown deformation characteristics, the system visually detects the regions to be cleaned, and generates plans for both the grasping and cleaning arms. As the system performs cleaning attempts and gains experience with multiple new parts, it learns models of the part deformation depending on the cleaning force and grasping parameters. A planner iteratively generates tool paths for both robots using the available knowledge to optimize the cleaning time, including (1) delays from regrasping a part to minimize deflection and (2) time taken for repeated cleaning attempts over regions that remained dirty. A nonparametric deflection model is learned separately for each part, with minimal assumptions of the material behavior. We demonstrate the approach on a system of two KUKA LWR iiwa robots and a set of thin planar parts. Results indicate that the system is effective at rapidly learning part deformation models to enable effective iterative cleaning performance.

Three-Dimensional Deformable Object Manipulation Using Fast Online Gaussian Process Regression

“…Navarro-Alarcon et al [15], [16] used an adaptive and model-free linear controller to servo-control soft objects, where the object's deformation is modeled using a spring model [26]. [17] learned the models of the part deformation depending on the end-effector force and grasping parameters in an online manner to accomplish high-quality cleaning task. A more complete survey about deformable object manipulation in industry is available in [18].…”

“…These methods focus on high-level policies but lack the capability to achieve accurate operation -actually most of them are open-loop methods. Other approaches require a model about the object's deformation properties in terms of stiffness, Young' modules, or FEM coefficients, to design a control policy [5], [13]- [17]. However, such deformation parameters are difficult to be estimated accurately and may even change during the manipulation process, especially for objects made by nonlinear elastic or plastic materials.…”

Manipulating Highly Deformable Materials Using a Visual Feedback Dictionary

“…Navarro-Alarcon et al [8], [9] use an adaptive and model-free linear controller to servo-control soft objects, where the object's deformation is modeled using a spring model [25]. Langsfeld et al [26] perform online learning of part deformation models for robot cleaning of compliant objects. Our goal is to extend these visual servoing methods to perform complex tasks on highly deformable materials.…”

Addressing perception uncertainty induced failure modes in robotic bin-picking

“…In our previous work, we have developed other modules including an ontology for task partitioning in human-robot collaboration for kitting operations [70], resolving occlusions in robotic bin-picking [71], sequence planning for complex assemblies [72], instruction generation for human operations [73], bimanual robotic cleaning [74,75], and ensuring human safety [76]. Future work consists of investigating how to integrate these modules to develop hybrid work cells, where humans and robots collaborate to carry out non-repetitive industrial tasks.…”