Scalable techniques from nonparameteric statistics for real-time robot learning

Stefan Schaal, Chris Atkeson and Stefan Schaal

Abstract of paper published in Applied Intelligence.

Locally weighted learning (LWL) is a class of techniques from nonparametric statistics that provides useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of robotic systems. This paper introduces several LWL algorithms that have been tested successfully in real-time learning of complex robot tasks. We discuss two major classes of LWL, memory-based LWL and purely incremental LWL that does not need to remember any data explicitly. In contrast to the traditional belief that LWL methods cannot work well in high-dimensional spaces, we provide new algorithms that have been tested on up to 90 dimensional learning problems. The applicability of our LWL algorithms is demonstrated in various robot learning examples, including the learning of devil-sticking, pole-balancing by a humanoid robot arm, and inverse-dynamics learning for a seven and a 30 degree-of-freedom robot. In all these examples, the application of our statistical neural networks techniques allowed either faster or more accurate acquisition of motor control than classical control engineering.
Click here to download an gzip-ed version of the paper. Click here for a pdf version.
/DR 458 0 R >> endobj 457 0 obj << /Type /Font /Name /Helv /BaseFont /Helvetica /Subtype /Type1 /Encoding 460 0 R >> endobj 458 0 obj << /Encoding 459 0 R /Font 461 0 R >> endobj 459 0 obj << /PDFDocEncoding 460 0 R >> endobj 460 0 obj << /Type /Encoding /Differences [ 24 /breve /caron /circumflex /dotaccent /hungarumlaut /ogonek /ring /tilde 39 /quotesingle 96 /grave 128 /bullet /dagger /daggerdbl /ellipsis /emdash /endash /florin /fraction /guilsinglleft /guilsinglright /minus /perthousand /quotedblbase /quotedblleft /quotedblright /quoteleft /quoteright /quotesinglbase /trademark /fi /fl /Lslash /OE /Scaron /Ydieresis /Zcaron /dotlessi /lslash /oe /scaron /zcaron 160 /Euro 164 /currency 166 /brokenbar 168 /dieresis /copyright /ordfeminine 172 /logicalnot /.notdef /registered /macron /degree /plusminus /twosuperior /threesuperior /acute /mu 183 /periodcentered /cedilla /onesuperior /ordmasculine 188 /onequarter /onehalf /threequarters 192 /Agrave /Aacute /Acircumflex /Atilde /Adieresis /Aring /AE /Ccedilla /Egrave /Eacute /Ecircumflex /Edieresis /Igrave /Iacute /Icircumflex /Idieresis /Eth /Ntilde /Ograve /Oacute /Ocircumflex /Otilde /Odieresis /multiply /Oslash /Ugrave /Uacute /Ucircumflex /Udieresis /Yacute /Thorn /germandbls /agrave /aacute /acircumflex /atilde /adieresis /aring /ae /ccedilla /egrave /eacute /ecircumflex /edieresis /igrave /iacute /icircumflex /idieresis /eth /ntilde /ograve /oacute /ocircumflex /otilde /odieresis /divide /oslash /ugrave /uacute /ucircumflex /udieresis /yacute /thorn /ydieresis ] >> endobj 461 0 obj << /Helv 457 0 R >> endobj 462 0 obj << /N 455 0 R >> endobj 463 0 obj << /Type /Annot /Subtype /FreeText /Rect [ 243.8125 737.71362 443.81494 753.9043 ] /C [ ] /DA ([0 0 1] r /Helv 10 Tf) /BS << /W 0 >> /T (Sethu Vijayakumar) /F 4 /Contents ( ) /M (D:20010925143054-08'00') /AP 465 0 R /Open false >> endobj 464 0 obj << /Length 31 /Subtype /Form /BBox [ 0 0 200.00244 16.19067 ] /Resources << /ProcSet [ /PDF ] >> >> stream