Incremental Local Gaussian Regression

Authors: Franziska Meier, Philipp Hennig, Stefan Schaal

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical evaluations are performed on several synthetic and real robot datasets of increasing complexity and (big) data scale, and demonstrate that we consistently achieve on par or superior performance compared to current state-of-art methods while retaining a principled approach to fast incremental regression with minimal manual tuning parameters. 5 Experiments We evaluate our LGR on inverse dynamics learning tasks, using data from two robotic platforms: a SARCOS anthropomorphic arm and a KUKA lightweight arm.
Researcher Affiliation Academia 1University of Southern California Los Angeles, CA 90089, USA 2Max Planck Institute for Intelligent Systems Spemannstraße 38, T ubingen, Germany
Pseudocode Yes Algorithm 1 Incremental LGR
Open Source Code No The paper refers to third-party code used for comparison (LWPR and I-SSGPR) but does not provide a statement or link for the open-source code of their proposed LGR method.
Open Datasets No Sarcos [2], KUKA1, KUKA2, KUKAsim. The paper mentions these datasets but does not provide specific links, DOIs, repository names, or formal citations for public access to these datasets.
Dataset Splits Yes Table 1: Datasets for inverse dynamics tasks: KUKA1, KUKA2 are different splits of the same data. Rightmost column indicates the overlap in input space coverage between offline (ISoffline) and online training (ISonline) sets. Dataset freq Motion Noffline train Nonline train Ntest ISoffline ISonline
Hardware Specification Yes Finally, it is noteworthy that LGR processes both of these data sets at 500Hz (C++ code, on a 3.4GHz Intel Core i7), making it a realistic alternative for real-time inverse dynamics learning tasks.
Software Dependencies No The paper mentions 'C++ code' and references third-party software like 'SL simulation software package [30]' and 'Robot Cub framework', but does not provide specific version numbers for any software dependencies required to replicate the experiment.
Experiment Setup Yes For all experiments we initialized the length scales to λ = 0.3, and used wgen = 0.3 for both LWPR and LGR.