RI | Research | Projects | Dynamic Biped

Text only version of this site

Dynamic Biped Head: Garth Zeglin Contact: Garth Zeglin (garthz@cs.cmu.edu) Mailing address: Carnegie Mellon University Robotics Institute 5000 Forbes Avenue Pittsburgh, PA 15213 For more information, see this project's homepage.

This page last updated - January 1999.

Project Description

We are developing a new series of bipedal walking robots that use passive-dynamic principles.

In January 2002 the planar biped achieved several runs in which it walked more than ten steps. This can be seen in the data plots (PDF) or in the video (MPEG, 6.5M).

Personnel [Past Members]

	Name	Title	Email Address
	Chris Atkeson	Professor, RI/HCII	cga@cs.cmu.edu
	Garth Zeglin	Project Scientist	garthz@cs.cmu.edu

Publications

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Powered bipeds based on passive dynamic principles
  S. Anderson, M. Wisse, C. Atkeson, J.K. Hodgins, G. Zeglin, and B. Moyer
  5th IEEE-RAS International Conference on Humanoid Robots, December, 2005, pp. 110 - 116. [Abstract]
  Download: pdf [505 KB] copyrighted

• Dynamic Programming in Reduced Dimensional Spaces: Dynamic Planning For Robust Biped Locomotion
  M. Stilman, C. Atkeson, J. Kuffner, and G. Zeglin
  Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'05), April, 2005, pp. 2399 - 2404. [Abstract]
  Download: pdf [854 KB] copyrighted

• Poincare-Map-Based Reinforcement Learning for Biped Walking
  J. Morimoto, J. Nakanishi, G. Endo, G. Cheng, C. Atkeson, and G. Zeglin
  Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'05), April, 2005. [Abstract]
  Download: pdf [452 KB] copyrighted

• Acquisition of a Biped Walking Pattern Using an Approximate Poincare Map
  J. Morimoto, J. Nakanishi, G. Endo, G. Cheng, C. Atkeson, and G. Zeglin
  Proceedings of the IEEE-RAS/RSJ Int. Conf. on Humanoid Robots (Humanoids 2004), November, 2004, pp. 912 - 924. [Abstract]
  Download: pdf [1034 KB] copyrighted

• A Simple Reinforcement Learning Algorithm For Biped Walking
  J. Morimoto, G. Cheng, C. Atkeson, and G. Zeglin
  Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'04), April, 2004, pp. 3030 - 3035. [Abstract]
  Download: pdf [838 KB] copyrighted

• Minimax Differential Dynamic Programming: Application to a Biped Walking Robot
  J. Morimoto, G. Zeglin, and C. Atkeson
  Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2003. [Abstract]
  Download: pdf [608 KB] copyrighted

• Robust Low Torque Biped Walking Using Differential Dynamic Programming with a Minimax Criterion
  J. Morimoto and C. Atkeson
  Proceedings of the Fifth International Conference on Climbing an Walking Robots and their Supporting Technologies (CLAWAR 2002), September, 2002. [Abstract]
  Download: pdf [178 KB] copyrighted

• Minimax Differential Dynamic Programming: An Application to Robust Biped Walking
  J. Morimoto and C. Atkeson
  Neural Information Processing Systems 2002, 2002. [Abstract]
  Download: pdf [235 KB] copyrighted

• Nonparametric Representation of Policies and Value Functions: A Trajectory-Based Approach
  C. Atkeson and J. Morimoto
  Neural Information Processing Systems 2002, 2002. [Abstract]
  Download: pdf [265 KB] copyrighted