S
Surya P. N. Singh
Researcher at University of Queensland
Publications - 85
Citations - 2723
Surya P. N. Singh is an academic researcher from University of Queensland. The author has contributed to research in topics: Motion planning & Robotics. The author has an hindex of 21, co-authored 85 publications receiving 2311 citations. Previous affiliations of Surya P. N. Singh include Intuitive Surgical & University of Western Australia.
Papers
More filters
Proceedings ArticleDOI
V-REP: A versatile and scalable robot simulation framework
TL;DR: A versatile, scalable, yet powerful general-purpose robot simulation framework called V-REP, which allows for direct incorporation of various control techniques and renders simulations and simulation models more accessible to a general-public, by reducing the simulation model deployment complexity.
Book ChapterDOI
Virtual robot experimentation platform V-REP: a versatile 3D robot simulator
TL;DR: This paper introduces a modular and decentralized architecture for robotics simulation that balances functionality, provides more diversity, and simplifies connectivity between (independent) calculation modules.
Journal ArticleDOI
System Design of a Quadrupedal Galloping Machine
TL;DR: The system design of a machine that is constructed to study a quadrupedal gallop gait and two intelligent strategies have been developed for verification on a one-legged system, successful in operating one leg at speeds necessary for a dynamic gallop of amachine of this scale.
Proceedings ArticleDOI
An online and approximate solver for POMDPs with continuous action space
TL;DR: General Pattern Search in Adaptive Belief Tree (GPS-ABT), an approximate and online POMDP solver for problems with continuous action spaces and results on a box pushing and an extended Tag benchmark problem are promising.
Book ChapterDOI
A Pipeline for the Segmentation and Classification of 3D Point Clouds
Bertrand Douillard,James Underwood,Vsevolod Vlaskine,Alastair James Quadros,Surya P. N. Singh +4 more
TL;DR: The segmentation facilitates a novel approach to 3D classification that bypasses feature extraction and directly compares 3D shapes via the ICP algorithm, and is shown to achieve accuracy on par with the best feature based classifier while being significantly faster and allowing a clearer understanding of the classifier's behaviour.