TASK/MOTION PLANNING

Consider the problem of automatically planning the necessary actions for a robot to perform a task. The following information must be determined by considering the nature of the task and the mechanical characteristics of the robot:

  • Grasping posture for the hand
  • (For the assembly task) Assembly Sequence
  • Strategies for changing hands
  • Position/posture of the object on the table
  • Robot motion trajectory

Here, the figure in the left shows the graph structure used to determine the assembly sequence. Taking the above points into account, by attributing them to the graph search problem, we can automatically determine the necessary actions the robot needs to perform.


Research Topics


Research on Planning Robotic Cooking Task

Publications

  1. Hoshito Nagahama, Ixchel Georgina Ramirez-Alpizar, Kensuke Harada, “Food Arrangement Framework for Cooking Robots,” Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics, pp. 1179-1184, 2022.(Proceeding)
  2. Kota Takata, Takuya Kiyokawa, Ixchel G. Ramirez-Alpizar, Natsuki Yamanobe, Weiwei Wan, and Kensuke Harada, “Efficient Task/Motion Planning for a Dual-arm Robot from Language Instructions and Cooking Images,” Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. 2022 (Preprint)
  3. Kota Takata, Takuya Kiyokawa, Ntsuki Yamanobe, Ixchel G.
    Ramirez-Alpizar, Weiwei Wan, Kensuke Harada, “Graph Based Framework on Bimanual Manipulation Planning from Cooking Recipe, ” Robotics, vol. 11, no. 6, 2022. (Download link)

Robotic Motion Planning from Cooking Recipe

slide

ダウンロード
Slide
Presentation slide of IROS 2022(long version)
slide.pdf
PDFファイル 1.7 MB

Youtube

Supplementary video on "Efficient Task/Motion Planning for a Dual-arm Robot from Language Instructions and Cooking Images" presented at IROS 2022.

 

Youtube

Supplementary video on "Efficient Task/Motion Planning for a Dual-arm Robot from Language Instructions and Cooking Images" presented at IROS 2022.

 


Youtube

Supplementary video on "Graph Based Framework on Bimanual Manipulation Planning from Cooking Recipe" submitted for MDPI Robotics.


Planning Food Arrangement

Youtube

Supplementary video on "Food Arrangement Framework for Cooking Robots" presented at IEEE/ASME AIM 2022.



Research on Assembly Sequence Planning

Publications

1.  Assembly Sequence Planning for Motion Planning, Weiwei Wan, Kensuke Harada, and Kazuyuki Nagata, Assembly Automatoin (AA), 2017.

2. Planning to Build Block Structures with Unstable Intermediate States Using two Manipulators, Hao Chen, Weiwei Wan, Keisuke Koyama, and Kensuke Harada, IEEE Transactions on Automation Science and Engineering (TASE), 2021. Video (Reported by IEEE Spectrum Video Friday)

Combined Assembly Task planning and motion planning

Youtube



Bimanual Object Picking from the Pile with COllapse Prediction


Youtube

Youtube



Publications

  1. Motoda, T.; Petit, D.; Nishi, T.; Nagata, K.; Wan, W.; Harada, K.; Shelf Replenishment Based on Object Arrangement Detection and Collapse Prediction for Bimanual Manipulation. Robotics 2022, 11, 104. https://doi.org/10.3390/robotics11050104. 
  2. Shusei Nagato, Tomohiro Motoda, Keisuke Koyama, Weiwei Wan and Kensuke Harada, “Motion Planning to Retrieve an Object from Random File,” Proceedings of the 2022 International Conference on Artificial Life and Robotics, pp. 328-334, 2022.
  3. Tomohiro Motoda, Damien Petit, Weiwei Wan, and Kensuke Harada, "Bimanual Shelf Picking Planner Based on Collapse Prediction," Proceedings of IEEE International Conference on Automation, Science and Engineering, pp. 510-515, 2021. 

Robotic bin picking

Learning Based Industrial Bin-picking Trained with Approximate Physics Simulator

Ryo Matsumura, Kensuke Harada, Yukiyasu Domae, and Weiwei Wan

International Conference on Intelligent Autonomous Systems (IAS) 2018

Paper


Learning Based Robotic Bin-picking for Potentially Tangled Objects

Ryo Matsumura, Yukiyasu Domae, Weiwei Wan, and Kensuke Harada

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2019

Paper / Video


A Topological Solution of Entanglement for Complex-shaped Parts in Robotic Bin-picking

Xinyi Zhang, Keisuke Koyama, Yukiyasu Domae, Weiwei Wan, Kensuke Harada

IEEE International Conference on Automation, Science and Engineering (CASE) 2021

Paper / Video Code


Learning Efficient Policies for Picking Entangled Wire Harnesses: An Approach to Industrial Bin Picking

Xinyi Zhang, Yukiyasu Domae, Weiwei Wan, Kensuke Harada

IEEE Robotics and Automation Letter (RA-L) 2022 (Accepted)

Paper / Video / Code


Bin-Picking for Potentially Entangled Object by Linearing Image of the Pile

Mizuki Takasu, Xinyi Zhang, Yukiyasu Domae, Weiwei Wan, Kensuke Harada

Video



Research on craft assembly task

Publications

  1. Vitor Hideyo Isume, Kensuke Harada, Weiwei Wan, Yukiyasu Domae, "Using affordances for assembly: Towards a complete Craft Assembly System," Proceedings of the 21st International Conference on Control, Automation and Systems (ICCAS), 2021, pp. 2010-2014, doi: 10.23919/ICCAS52745.2021.9649936.

affordance-based selection for craft components

video

Slides

ダウンロード
Presentation Slides for ICCAS2021
ICCAS2021_slides.pdf
PDFファイル 2.3 MB