Table of Contents
Fetching ...

Integrative Wrapping System for a Dual-Arm Humanoid Robot

Yukina Iwata, Shun Hasegawa, Kento Kawaharazuka, Kei Okada, Masayuki Inaba

Abstract

Flexible object manipulation of paper and cloth is a major research challenge in robot manipulation. Although there have been efforts to develop hardware that enables specific actions and to realize a single action of paper folding using sim-to-real and learning, there have been few proposals for humanoid robots and systems that enable continuous, multi-step actions of flexible materials. Wrapping an object with paper and tape is more complex and diverse than traditional manipulation research due to the increased number of objects that need to be handled, as well as the three-dimensionality of the operation. In this research, necessary information is organized and coded based on the characteristics of each object handled in wrapping. We also generalize the hardware configuration, manipulation method, and recognition system that enable humanoid wrapping operations. The system will include manipulation with admittance control focusing on paper tension and state evaluation using point clouds to handle three-dimensional flexible objects. Finally, wrapping objects with different shapes is experimented with to show the generality and effectiveness of the proposed system.

Integrative Wrapping System for a Dual-Arm Humanoid Robot

Abstract

Flexible object manipulation of paper and cloth is a major research challenge in robot manipulation. Although there have been efforts to develop hardware that enables specific actions and to realize a single action of paper folding using sim-to-real and learning, there have been few proposals for humanoid robots and systems that enable continuous, multi-step actions of flexible materials. Wrapping an object with paper and tape is more complex and diverse than traditional manipulation research due to the increased number of objects that need to be handled, as well as the three-dimensionality of the operation. In this research, necessary information is organized and coded based on the characteristics of each object handled in wrapping. We also generalize the hardware configuration, manipulation method, and recognition system that enable humanoid wrapping operations. The system will include manipulation with admittance control focusing on paper tension and state evaluation using point clouds to handle three-dimensional flexible objects. Finally, wrapping objects with different shapes is experimented with to show the generality and effectiveness of the proposed system.

Paper Structure

This paper contains 23 sections, 2 equations, 15 figures, 1 table.

Figures (15)

  • Figure 1: Wrapping with a dual-armed humanoid robot. The wrapping operation deals with three things: the object to be wrapped, the object that wraps the object, and the object that seals the object. In this paper, these three are represented as Target, Wrapper, and Seal, respectively.
  • Figure 2: Representation of Target, Wrapper, Seal, and the overall system. The basic information of Target, Wrapper, and Seal is stored as $T_{bbox}$, $W_{cbbox}$, and $S_{cmp}$, respectively. As a whole system, $f^{recog}$ recognizes the current object using $img$ and $pc$ and reflects this in Target, Wrapper, and Seal information. Based on this, $f^{ctrl}$ provides trajectory commands to the real robot, and $f^{s/f}$ judges whether the operation succeeded or failed. If the result is a success, the process proceeds to the next step, repeating the cycle. If it fails, the process restarts from the initial state. At the end of all operations, $r$ is calculated by $f^{eval}$ to evaluate the final wrapping state.
  • Figure 3: (a) realizes the thin, hard, nail-shaped part required in step B. (b) realizes the three-dimensionality and elasticity required in steps C and E by means of rubber molding.
  • Figure 4: Lifting Wrapper from the plane; after grasping Wrapper, the hand is tilted and moved in the direction of Wrapper's center to secure enough $T_{seal}$ area (red arrow).
  • Figure 5: The success or failure of each operation is determined by the presence or absence of the extracted points ($W_{pc}$ or $S_{pc}$) in the $ROI$ ($f^{s/f}$). A blue box represents the $ROI$.
  • ...and 10 more figures