Multi-Objective Evolutionary Optimisation for Inverse Kinematics on Highly Articulated and Humanoid Robots

Sebastian Starke, Norman Hendrich, Dennis Krupke, Jianwei Zhang
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017) (accepted) - sep 2017
While solving inverse kinematics on serial kinematic chains is well researched, many methods still seem rather limited in jointly handling more complex geometries, including dexterous multi-finger hands or humanoid robots. Additionally, object manipulation and motion tasks would benefit from the ability to define intermediate goals along the kinematic chains, such as an elbow position or wrist orientation. In this paper, we propose a fast hybrid evolutionary approach that is capable of solving inverse kinematics for multiple end effectors and objectives simultaneously, leaving high flexibility for specifyin full-body postures. Accurate solutions can be found in real-time and suboptimal extrema are robustly avoided. Our experimental results on the NASA Valkyrie and Shadow Dexterous Hand demonstrate that the algorithm can be efficiently applied for different robotic tasks which require flexible control of fullyconstrained geometries.

Images and movies

 

BibTex references

@InProceedings\{SHKZ17,
  author       = "Starke, Sebastian and Hendrich, Norman and Krupke, Dennis and Zhang, Jianwei",
  title        = "Multi-Objective Evolutionary Optimisation for Inverse Kinematics on  Highly Articulated and Humanoid Robots",
  booktitle    = "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017) (accepted)",
  month        = "sep",
  year         = "2017",
  url          = "http://basilic.informatik.uni-hamburg.de/Publications/2017/SHKZ17"
}

Other publications in the database

» Sebastian Starke
» Norman Hendrich
» Dennis Krupke
» Jianwei Zhang