Multi-objective grasp pose optimisation for robotic 3D pipe assembly manipulation

Zebang Zhang*, Mozafar Saadat

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

50 Downloads (Pure)

Abstract

This paper considers the problem of grasp pose optimisation for manipulating 3D pipe assemblies during the manufacturing process. The method presented in this paper is specifically developed for manufacturing cryogenic pipe assemblies autonomously in a Factory-In-A-Box scenario (i.e., a compact factory built inside an industrial container). However, it also can be used for robotic manipulation of general frame structures. The problem is formulated as a constrained multi-objective optimisation problem. The optimisation algorithm searches for solutions that satisfy two constraints: (i) robot workspace reachability (i.e., feasible inverse kinematics solution for a given end-effector pose); and (ii) any possible collision when executing the post-grasp trajectory, and continuously improves them based on three objectives: (i) minimise robot joint motion for executing a specified pipe trajectory; (ii) minimise the sum of maximum deformation of pipe assembly along the trajectory; and (iii) minimise the sum of robot force manipulability along the trajectory. A special constraint handling method is used to decouple the constraint and objective evaluation process, allowing expensive objectives to be evaluated only when constraints are satisfied. The algorithm explicitly considers the possibility of multiple inverse kinematics solutions and uses a graph search algorithm (Dijkstra's Algorithm) to find the optimal trajectory amongst all feasible trajectories. The weighted sum approach is used to combine the three objectives with weights determined by the Analytical Hierarchy Process. The optimisation problem is solved using the Bees Algorithm with a proposed problem-specific local search strategy. Extensive benchmarks show that the proposed strategy achieves better overall results than the default strategy of the Bees Algorithm and other metaheuristics.
Original languageEnglish
Article number102326
Number of pages13
JournalRobotics and Computer-Integrated Manufacturing
Volume76
Early online date11 Feb 2022
DOIs
Publication statusPublished - Aug 2022

Bibliographical note

Funding Information:
The author would like to thank the Manufacturing Technology Centre (MTC), Coventry, UK, and Innovate UK for supporting this project through funding and case study.

Deploying a flexible robotic workcell is becoming an increasingly popular choice with the trends of mass customisation [21] , especially for small and mid-size enterprises. A good example of deploying such a flexible robotic workcell is the Factory-In-A-Box (FIAB) project. FIAB is a high-profile project funded by Innovate UK as part of the Thermal Energy Research Accelerator (T-ERA) carried out at the Manufacturing Technology Centre (MTC), UK, with the support of the University of Birmingham. A simulated FIAB environment is shown in Fig. 1 . FIAB is a successful demonstrator of a high technology, compact and autonomous factory inside a container to manufacture cryogenic pipe assemblies with the focus on flexibility (the factory can adapt quickly to manufacture pipes of different structures at different quantities according to customer needs) and mobility (the factory can be rapidly deployed anywhere) [22] . Cryogenic piping systems are used for applications which require extremely low temperature, typically lower than -150 °C. FIAB accepts orders from customers and performs simulations to check if the required dimensions of the pipes can be manufactured by the facility. The manufacturing process usually involves cutting, bending, brazing, and pressure testing. An industrial robot is mounted on an overhead rail to grasp and transfer pipes between different stations inside FIAB. Currently, the solution for grasping pipe assemblies is by designing a part-specific end-effector. While this solution provides a robust grasp and reduces excessive deformation during manipulation, it also increases the weight of the end-effector which makes the process less energy efficient. Besides, as the custom-designed end-effector is larger and more complex in terms of its geometry, the possibility of collision with the end-effector increases. Therefore, it may be infeasible for some pipes to be manufactured. More importantly, the custom-designed gripper is much more expensive than a general gripper.

Publisher Copyright:
© 2022 Elsevier Ltd

Keywords

  • 3D pipe assembly
  • Bees Algorithm
  • Deformable object
  • Grasp pose optimization
  • Multi-objective optimization
  • Robotic manipulation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Mathematics(all)
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Multi-objective grasp pose optimisation for robotic 3D pipe assembly manipulation'. Together they form a unique fingerprint.

Cite this