NTRS - NASA Technical Reports Server

Back to Results
Upper Torso Control for HOAP-2 Using Neural NetworksHumanoid robots have similar physical builds and motion patterns as humans. Not only does this provide a suitable operating environment for the humanoid but it also opens up many research doors on how humans function. The overall objective is replacing humans operating in unsafe environments. A first target application is assembly of structures for future lunar-planetary bases. The initial development platform is a Fujitsu HOAP-2 humanoid robot. The goal for the project is to demonstrate the capability of a HOAP-2 to autonomously construct a cubic frame using provided tubes and joints. This task will require the robot to identify several items, pick them up, transport them to the build location, then properly assemble the structure. The ability to grasp and assemble the pieces will require improved motor control and the addition of tactile feedback sensors. In recent years, learning-based control is becoming more and more popular; for implementing this method we will be using the Adaptive Neural Fuzzy Inference System (ANFIS). When using neural networks for control, no complex models of the system must be constructed in advance-only input/output relationships are required to model the system.
Document ID
Acquisition Source
Jet Propulsion Laboratory
Document Type
Sandoval, Steven P.
(New Mexico State Univ. NM, United States)
Date Acquired
August 23, 2013
Publication Date
August 1, 2005
Publication Information
Publication: Summer Student Research Presentations
Subject Category
Cybernetics, Artificial Intelligence And Robotics
Distribution Limits
Work of the US Gov. Public Use Permitted.

Available Downloads

There are no available downloads for this record.
No Preview Available