Next Article in Journal
Exploiting Impact of Hardware Impairments in NOMA: Adaptive Transmission Mode in FD/HD and Application in Internet-of-Things
Previous Article in Journal
Effect of Uneven Electrostatic Forces on the Dynamic Characteristics of Capacitive Hemispherical Resonator Gyroscopes
Previous Article in Special Issue
Assistive Grasping Based on Laser-point Detection with Application to Wheelchair-mounted Robotic Arms
Article Menu

Export Article

Open AccessArticle
Sensors 2019, 19(6), 1292;

Learning the Cost Function for Foothold Selection in a Quadruped Robot

College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China
State Key Laboratory of Robotics and System (HIT), Harbin 150080, China
Shenzhen Academy of Aerospace Technology, Shenzhen 518057, China
Authors to whom correspondence should be addressed.
This paper is an extended version of our paper published in “Li, X.; Li, J.; Guo, Y. Foothold selection for quadruped robot based on learning from expert. In Proceedings of the IEEE International Conference on Advanced Robotics and Mechatronics, Hefei, China, 27–31 August 2017; pp. 223–228”.
Received: 13 February 2019 / Revised: 8 March 2019 / Accepted: 8 March 2019 / Published: 14 March 2019
(This article belongs to the Special Issue Semantic Representations for Behavior Analysis in Robotic system)
Full-Text   |   PDF [24475 KB, uploaded 14 March 2019]   |  


This paper is focused on designing a cost function of selecting a foothold for a physical quadruped robot walking on rough terrain. The quadruped robot is modeled with Denavit–Hartenberg (DH) parameters, and then a default foothold is defined based on the model. Time of Flight (TOF) camera is used to perceive terrain information and construct a 2.5D elevation map, on which the terrain features are detected. The cost function is defined as the weighted sum of several elements including terrain features and some features on the relative pose between the default foothold and other candidates. It is nearly impossible to hand-code the weight vector of the function, so the weights are learned using Supporting Vector Machine (SVM) techniques, and the training data set is generated from the 2.5D elevation map of a real terrain under the guidance of experts. Four candidate footholds around the default foothold are randomly sampled, and the expert gives the order of such four candidates by rotating and scaling the view for seeing clearly. Lastly, the learned cost function is used to select a suitable foothold and drive the quadruped robot to walk autonomously across the rough terrain with wooden steps. Comparing to the approach with the original standard static gait, the proposed cost function shows better performance. View Full-Text
Keywords: quadruped robot; foothold selection; TOF camera; 2.5D elevation map; supporting vector machine quadruped robot; foothold selection; TOF camera; 2.5D elevation map; supporting vector machine

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Li, X.; Gao, H.; Zha, F.; Li, J.; Wang, Y.; Guo, Y.; Wang, X. Learning the Cost Function for Foothold Selection in a Quadruped Robot. Sensors 2019, 19, 1292.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top