Conference paper Restricted Access

Incremental Policy Refinement by Recursive Regression and Kinesthetic Guidance

Bojan Nemec; Mihael Simonč; Tadej Petrič; Aleš Ude


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3632342", 
  "author": [
    {
      "family": "Bojan Nemec"
    }, 
    {
      "family": "Mihael Simon\u010d"
    }, 
    {
      "family": "Tadej Petri\u010d"
    }, 
    {
      "family": "Ale\u0161 Ude"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2020, 
        1, 
        31
      ]
    ]
  }, 
  "abstract": "<p>Fast deployment of robot tasks requires appropriate<br>\ntools that enable efficient reuse of existing robot control<br>\npolicies. Learning from Demonstration (LfD) is a popular tool<br>\nfor the intuitive generation of robot policies, but the issue of<br>\nhow to address the adaptation of existing policies has not been<br>\nproperly addressed yet. In this work, we propose an incremental<br>\nLfD framework that efficiently solves the above-mentioned<br>\nissue. It has been implemented and tested on a number of<br>\npopular collaborative robots, including Franka Emika Panda,<br>\nUniversal Robot UR10, and KUKA LWR 4.</p>", 
  "title": "Incremental Policy Refinement by Recursive Regression and Kinesthetic Guidance", 
  "type": "paper-conference", 
  "id": "3632342"
}
23
1
views
downloads
All versions This version
Views 2323
Downloads 11
Data volume 610.9 kB610.9 kB
Unique views 2222
Unique downloads 11

Share

Cite as