Invited Speaker

Yunfeng Zhang

National University of Singapore (NUS)

Update time:2023-12-06 10:30

Y F Zhang received his B.Eng. in Mechanical Engineering from Shanghai Jiao Tong University, China in 1985 and Ph.D. from the University of Bath, UK in 1991. He is currently an Associate Professor at the Department of Mechanical Engineering, National University of Singapore. His research interests include (1) computational intelligence in design and manufacturing; (2) hybrid manufacturing (3D printing and 5-axis machining) technology; (3) Machine/deep learning for automation. He has authored more than 200 publications and received various international awards including the Kayamori Best Paper Award in ICRA 1999 and the IMechE Thatcher Bros Prize in 2011.

Topic title: Additive Manufacturing with Dual Robot Manipulators: the Path Planning Issues and Solutions


Robot-assisted additive manufacturing (AM) has been gaining popularity benefiting from its great multi-axis reachability. Moreover, an AM system with dual deposition-heads held by manipulators would significantly shorten the building time, especially for large-scale parts. However, few works have been reported on the path planning for the dual manipulators AM which is highly challengeable due to various constraints, e.g. posture of deposition head, constant travelling speed, and collision-free. In this talk, an integrated path planning solution is presented for the AM with dual robot manipulators, including individual layer partition, printing task assignment, robot manipulator motion planning, and collision check modules, respectively.

Firstly, an evolutional algorithm is developed for automatically segmenting a 2D layer into a set of well-shaped sub-regions and then filling each sub-region with minimum short infill tool-paths. Secondly, a practical approach is proposed for printing task assignment for the dual manipulators based on the filled toolpaths, using a simulated annealing (SA) algorithm to keep a moderate distance for two manipulators and minimize dry run span. Thirdly, an initial trajectory solution is generated for each manipulator, i.e. the specified deposition-head pose and travelling speed at each time sample waypoint. Fourthly, a check-and-correction process at each waypoint, of which the collision among the links of two manipulators, is identified and corrected. A novel pivot-move (PM) strategy is further proposed to avoid the collision and maintain the traveling speed un-changed at the same time. Trajectory simulation and physical implementation on lab developed dual-manipulator AM platform were conducted to validate the effective-ness and high-quality deposition achieved by the developed solution.

Congress has ended
Important Dates
Conference Dates
March 29-31, 2024
Deadline for Submission of Abstract

December 31, 2023

Still open for submission

Notification of Abstract Acceptance

January 15, 2024

January 25, 2024