Clustering-Based Robot Navigation and Control

Loading...
Thumbnail Image
Penn collection
Departmental Papers (ESE)
General Robotics, Automation, Sensing and Perception Laboratory
Kod*lab
Degree type
Discipline
Subject
GRASP
Kodlab
Motion planning
Clustering
Configuration spaces
Topology
Sampling-based motion planning
Controls and Control Theory
Dynamical Systems
Electrical and Computer Engineering
Engineering
Geometry and Topology
Robotics
Systems Engineering
Funder
This work was supported in part by AFOSR under the CHASE MURI FA9550–10–1−0567.
Grant number
License
Copyright date
Distributor
Contributor
Abstract

In robotics, it is essential to model and understand the topologies of configuration spaces in order to design provably correct motion planners. The common practice in motion planning for modelling configuration spaces requires either a global, explicit representation of a configuration space in terms of standard geometric and topological models, or an asymptotically dense collection of sample configurations connected by simple paths. In this short note, we present an overview of our recent results that utilize clustering for closing the gap between these two complementary approaches. Traditionally an unsupervised learning method, clustering offers automated tools to discover hidden intrinsic structures in generally complex-shaped and high-dimensional configuration spaces of robotic systems. We demonstrate some potential applications of such clustering tools to the problem of feedback motion planning and control. In particular, we briefly present our use of hierarchical clustering for provably correct, computationally efficient coordinated multirobot motion design, and we briefly describe how robot-centric Voronoi diagrams can be used for provably correct safe robot navigation in forest-like cluttered environments, and for provably correct collision-free coverage and congestion control of heterogeneous disk-shaped robots. For more information: Kod*lab

Advisor
Date of presentation
2016-05-16
Conference name
Departmental Papers (ESE)
Conference dates
2023-05-17T15:52:19.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
@Misc{arslan_guralnik_kod_ICRA2016TopologyWorkshop, Title = {Clustering-Based Robot Navigation and Control}, Author = {Omur Arslan and Dan P. Guralnik and Daniel E. Koditschek}, Booktitle = {Robotics and Automation, 2016 IEEE International Conference on, Workshop on Emerging Topological Techniques in Robotics}, Year = {2016} }
Collection