DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hwangbo, Jemin | ko |
dc.contributor.author | Gehring, Christian | ko |
dc.contributor.author | Bellicoso, Dario | ko |
dc.contributor.author | Fankhauser, Peter | ko |
dc.contributor.author | Siegwart, Roland | ko |
dc.contributor.author | Hutter, Marco | ko |
dc.date.accessioned | 2020-04-22T01:20:45Z | - |
dc.date.available | 2020-04-22T01:20:45Z | - |
dc.date.created | 2020-04-10 | - |
dc.date.created | 2020-04-10 | - |
dc.date.created | 2020-04-10 | - |
dc.date.created | 2020-04-10 | - |
dc.date.issued | 2015-10 | - |
dc.identifier.citation | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.2842 - 2847 | - |
dc.identifier.issn | 2153-0858 | - |
dc.identifier.uri | http://hdl.handle.net/10203/273969 | - |
dc.description.abstract | Methods of optimizing a single trajectory are mature enough for planning in many applications. Yet such optimization methods applied to high Degree-Of-Freedom robots either consume too much time to be real-time or approximate the dynamics such that they lack physical consistency. In this paper, we present a method of precomputing optimized trajectories and compressing the information to get a compact representation of the optimal policy function. By varying the initial configuration of a robot and optimizing multiple trajectories, the controller gains knowledge about the optimal policy function. Such computation can be performed on a powerful workstation or even supercomputers instead of an on-board computer of the robot. The precomputed optimal trajectories are stored in a Single-hidden Layer Feedforward neural Network (SLFN) using Optimally Pruned Extreme Learning Machine (OP-ELM). This ensures minimal representation of the model and fast evaluation of the SLFN. We first explain our method using a simple time-optimal control problem with an analytical solution. We then demonstrate how this method can work even for high dimensional state by optimizing a foothold strategy of a full quadruped robot in simulation. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Direct State-to-Action Mapping for High DOF Robots Using ELM | - |
dc.type | Conference | - |
dc.identifier.wosid | 000371885403002 | - |
dc.identifier.scopusid | 2-s2.0-84958151687 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 2842 | - |
dc.citation.endingpage | 2847 | - |
dc.citation.publicationname | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Hamburg, GERMANY | - |
dc.identifier.doi | 10.1109/IROS.2015.7353768 | - |
dc.contributor.localauthor | Hwangbo, Jemin | - |
dc.contributor.nonIdAuthor | Gehring, Christian | - |
dc.contributor.nonIdAuthor | Bellicoso, Dario | - |
dc.contributor.nonIdAuthor | Fankhauser, Peter | - |
dc.contributor.nonIdAuthor | Siegwart, Roland | - |
dc.contributor.nonIdAuthor | Hutter, Marco | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.