Download PDFOpen PDF in browser

Optimizing Kick Trajectory: A Comparative Study

7 pagesPublished: October 19, 2017

Abstract

Incorporating a dynamic kick engine that is both fast and effective is pivotal to be competitive in one of the world’s biggest AI and robotics initiatives: RoboCup. Using the NAO robot as a testbed, we developed a dynamic kick engine that can generate a kick trajectory with an arbitrary direction without prior input or knowledge of the parameters of the kick. The trajectories are generated using cubic splines (two degree three polynomials with a via-point), cubic Hermite splines or sextics (one six degree polynomial). The trajectories are executed while the robot is dynamically balancing on one foot. Although a variety of kick engines have been implemented by others, there are only a few papers that demonstrate how kick engine parameters have been optimized to give an effective kick or even a kick that minimizes energy consumption and time. Parameters such as kick configuration, limits of the robot, or shape of the polynomial can be optimized. We propose an optimization framework based on the Webots simulator to optimize these parameters. Experiments on different joint interpolators for kick motions have been observed to compare results.

Keyphrases: covariance matrix adaptation evolutionary strategy, dynamic kick, kick trajectory, robot kick

In: Christoph Benzmüller, Christine Lisetti and Martin Theobald (editors). GCAI 2017. 3rd Global Conference on Artificial Intelligence, vol 50, pages 239-245.

BibTeX entry
@inproceedings{GCAI2017:Optimizing_Kick_Trajectory_Comparative,
  author    = {Pedro Pena and Joseph Masterjohn and Ubbo Visser},
  title     = {Optimizing Kick Trajectory: A Comparative Study},
  booktitle = {GCAI 2017. 3rd Global Conference on Artificial Intelligence},
  editor    = {Christoph Benzmüller and Christine Lisetti and Martin Theobald},
  series    = {EPiC Series in Computing},
  volume    = {50},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/Xw6m},
  doi       = {10.29007/3f7v},
  pages     = {239-245},
  year      = {2017}}
Download PDFOpen PDF in browser