Download a PDF with the full list of our publications: Robot-Intelligence-Lab-Publications-2021.pdf

A comprehensive list can also be found at Google Scholar, or by searching for the publications of author Kormushev, Petar.

Citation

BibTex format

@article{Rakicevic:2019:10.1007/s10514-019-09842-7,
author = {Rakicevic, N and Kormushev, P},
doi = {10.1007/s10514-019-09842-7},
journal = {Autonomous Robots},
pages = {1917--1935},
title = {Active learning via informed search in movement parameter space for efficient robot task learning and transfer},
url = {http://dx.doi.org/10.1007/s10514-019-09842-7},
volume = {43},
year = {2019}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Learning complex physical tasks via trial-and-error is still challenging for high-degree-of-freedom robots. Greatest challenges are devising a suitable objective function that defines the task, and the high sample complexity of learning the task. We propose a novel active learning framework, consisting of decoupled task model and exploration components, which does not require an objective function. The task model is specific to a task and maps the parameter space, defining a trial, to the trial outcome space. The exploration component enables efficient search in the trial-parameter space to generate the subsequent most informative trials, by simultaneously exploiting all the information gained from previous trials and reducing the task model’s overall uncertainty. We analyse the performance of our framework in a simulation environment and further validate it on a challenging bimanual-robot puck-passing task. Results show that the robot successfully acquires the necessary skills after only 100 trials without any prior information about the task or target positions. Decoupling the framework’s components also enables efficient skill transfer to new environments which is validated experimentally.
AU - Rakicevic,N
AU - Kormushev,P
DO - 10.1007/s10514-019-09842-7
EP - 1935
PY - 2019///
SN - 0929-5593
SP - 1917
TI - Active learning via informed search in movement parameter space for efficient robot task learning and transfer
T2 - Autonomous Robots
UR - http://dx.doi.org/10.1007/s10514-019-09842-7
UR - http://hdl.handle.net/10044/1/67445
VL - 43
ER -

Contact us

Senior Lecturer (Associate Professor)
Dyson School of Design Engineering
Address: 25 Exhibition Road, South Kensington, London, SW7 2DB
LinkedIn of Petar Kormushev