Filters








378 Hits in 2.8 sec

RESAMPL: A Region-Sensitive Adaptive Motion Planner [chapter]

Samuel Rodriguez, Shawna Thomas, Roger Pearce, Nancy M. Amato
Springer Tracts in Advanced Robotics  
In this work, we present resampl, a motion planning strategy that uses local region information to make intelligent decisions about how and where to sample, which samples to connect together, and to find  ...  Our Contribution: In this work, we propose resampl, a motion planning strategy that uses local region information to make intelligent decisions about how and where to sample, which samples to connect together  ...  Finally, [19] is a complete, deterministic planner that partitions the free space into star-shaped regions such that a single sample can see every point in the region.  ... 
doi:10.1007/978-3-540-68405-3_18 fatcat:ltty3ywjmzaitkm7pwqfrhgcju

An unsupervised adaptive strategy for constructing probabilistic roadmaps

L. Tapia, S. Thomas, B. Boyd, N.M. Amato
2009 2009 IEEE International Conference on Robotics and Automation  
For example, adaptive solutions such as setting learning rates, hand-classifying spaces, and defining parameters for a library of planners have all been proposed.  ...  Through a series of experiments, we demonstrate that in a wide variety of environments, the regions automatically identified by our technique represent the planning space well both in number and placement  ...  In this paper, we explore a combination of two previously introduced adaptive methods, a feature-sensitive motion planning framework [16] and temporal adaptation (provided by the Hybrid PRM planner  ... 
doi:10.1109/robot.2009.5152544 dblp:conf/icra/TapiaTBA09 fatcat:e5ldnd6fgvgbvhg5oqfuftpe5u

AUTONOMOUS NAVIGATION OF A 5 GRAM CRAWLING MILLIROBOT IN A COMPLEX ENVIRONMENT [chapter]

Allison Mathis, Jared Russell, Tom Moore, Jason Cohen, Brian Satterfield, NicHolas Kohut, Xiao-Yu Fu, ronald S. Fearing
2012 Adaptive Mobile Robotics  
Due to payload constraints, all sensing is performed by a single lowresolution camera and processing is split between an onboard unit and a base station.  ...  We present an integrated object detector, localizer, and planner that have been successfully demonstrated to enable the millirobot to determine its position within the environment, plan and navigate the  ...  Replacing the current camera with a newer model would significantly increase the performance of the perception system by providing higher-resolution and improved light sensitivity.  ... 
doi:10.1142/9789814415958_0019 fatcat:dwuznuvbj5bdxk3vcy2dxvg5oq

A scalable method for parallelizing sampling-based motion planning algorithms

Sam Ade Jacobs, Kasra Manavi, Juan Burgos, Jory Denny, Shawna Thomas, Nancy M. Amato
2012 2012 IEEE International Conference on Robotics and Automation  
This paper describes a scalable method for parallelizing sampling-based motion planning algorithms.  ...  It subdivides configuration space (C-space) into (possibly overlapping) regions and independently, in parallel, uses standard (sequential) sampling-based planners to construct roadmaps in each region.  ...  Algorithm 1 Parallel Sampling-based Motion Planning Input: An environment E, A set of motion planners S, number of regions N R Output: A roadmap graph G 1: Decompose E into N regions 2: Make a region graph  ... 
doi:10.1109/icra.2012.6225334 dblp:conf/icra/JacobsMBDTA12 fatcat:ghmp6mqygzdmrejf3pfe5fkluu

Toggle PRM: Simultaneous mapping of C-free and C-obstacle - A study in 2D -

Jory Denny, Nancy M. Amato
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Motion planning is known to be difficult. Probabilistic planners have made great advances, but still have difficulty for problems that require planning in narrow passages or on surfaces in Cspace.  ...  This work proposes Toggle PRM, a new methodology for PRMs that simultaneously maps both free and obstacle space.  ...  Region-Sensitive Adaptive Motion Planner (RESAMPL) [21] is a feature sensitive motion planning aid designed to help both multi-query and single-query planning methods.  ... 
doi:10.1109/iros.2011.6095102 dblp:conf/iros/DennyA11 fatcat:f4tgsgz4w5eevmk4dx5rk3ii3a

Toggle PRM: Simultaneous mapping of C-free and C-obstacle - a study in 2D -

J. Denny, N. M. Amato
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Motion planning is known to be difficult. Probabilistic planners have made great advances, but still have difficulty for problems that require planning in narrow passages or on surfaces in Cspace.  ...  This work proposes Toggle PRM, a new methodology for PRMs that simultaneously maps both free and obstacle space.  ...  Region-Sensitive Adaptive Motion Planner (RESAMPL) [21] is a feature sensitive motion planning aid designed to help both multi-query and single-query planning methods.  ... 
doi:10.1109/iros.2011.6048865 fatcat:waiovqxjdvfgnnrc57itybrzim

Reachability-guided sampling for planning under differential constraints

A. Shkolnik, M. Walter, R. Tedrake
2009 2009 IEEE International Conference on Robotics and Automation  
We demonstrate the algorithm with a detailed look at the expansion of an RRT in a swingup task, and on path planning for a nonholonomic car.  ...  Here we present a new sampling strategy for the RRT algorithm, based on an estimated feasibility set, which affords a dramatic improvement in performance in these severely constrained systems.  ...  The RG-RRT takes advantage of the fact that sampling is cheap compared to the process of expanding a node and, therefore, is willing to resample until a point is drawn from a region that yields better  ... 
doi:10.1109/robot.2009.5152874 dblp:conf/icra/ShkolnikWT09 fatcat:dasdlzzzfnephfvyvcb7p57yve

Adaptive local learning in sampling based motion planning for protein folding

Chinwe Ekenna, Shawna Thomas, Nancy M. Amato
2015 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)  
It is sensitive not only to different types of landscapes but also to differing regions in the landscape itself, removing the need to explicitly partition the landscape.  ...  Simulating protein folding motions is an important problem in computational biology.  ...  RESAMPL [12] is similar in spirit to Feature Sensitive Motion Planning, but it dynamically generates local regions to plan in.  ... 
doi:10.1109/bibm.2015.7359656 dblp:conf/bibm/EkennaTA15 fatcat:fw4p75yrvredffwinzgwkoweca

Adaptive local learning in sampling based motion planning for protein folding

Chinwe Ekenna, Shawna Thomas, Nancy M. Amato
2016 BMC Systems Biology  
It is sensitive not only to different types of landscapes but also to differing regions in the landscape itself, removing the need to explicitly partition the landscape.  ...  Simulating protein folding motions is an important problem in computational biology.  ...  RESAMPL [12] is similar in spirit to Feature Sensitive Motion Planning, but it dynamically generates local regions to plan in.  ... 
doi:10.1186/s12918-016-0297-9 pmid:27490494 pmcid:PMC4977477 fatcat:qzr5pq3m6vbkhen6m2sjucwyvi

Review of mobile robots obstacle avoidance, localization, motion planning, and wheels

Mustafa A. Mhawesh, Zaid H. Al-Tameemi, Omar Muhammed Neda
2020 Indonesian Journal of Electrical Engineering and Computer Science  
<span>The main objective of this research is to study the obstacle avoidance, Monte Carlo Localization (MCL) method, motion planning in dynamic networks for mobile robots, and mobile robots wheels depending  ...  The obstacles that are sensed in the region surrounded the robot are considered, so this region is called "sensitivity bubble".the researchers of [4] proposed an idea making the mobile robots discover  ...  The planner is a single-query probabilistic-roadmap (PRM) planner [22] . Test-platform 4.2.1.  ... 
doi:10.11591/ijeecs.v20.i2.pp768-776 fatcat:k5cw2vzaezgzfgfqyj6oriydce

Autonomous human–robot proxemics: socially aware navigation based on interaction potential

Ross Mead, Maja J Matarić
2016 Autonomous Robots  
distance and orientation parameters, (2) a reactive proxemic controller for goal state realization, and (3) a cost-based trajectory planner for maximizing automated robot speech and gesture recognition  ...  rates along a path to the goal state.  ...  2. a speech output level, SO L H R -How loudly will H speak? a gesture output level, G O L H R -In what region of space will H gesture?  ... 
doi:10.1007/s10514-016-9572-2 fatcat:3u6ta3ru6rbote4zrarabhkoum

A scalable distributed RRT for motion planning

Sam Ade Jacobs, Nicholas Stradford, Cesar Rodriguez, Shawna Thomas, Nancy M. Amato
2013 2013 IEEE International Conference on Robotics and Automation  
The second algorithm radially subdivides the configuration space into regions, constructs a portion of the tree in each region in parallel, and connects the subtrees, removing cycles if they exist.  ...  Rapidly-exploring Random Tree (RRT), like other sampling-based motion planning methods, has been very successful in solving motion planning problems.  ...  A similar algorithm of interest is Region-Sensitive Adaptive Motion Planning (RESAMPL) [23] . RESAMPL subdivides C space into local regions using an initial set of samples.  ... 
doi:10.1109/icra.2013.6631304 dblp:conf/icra/JacobsSRTA13 fatcat:pfyvw6n6bbbrxkv26o2za46viu

Efficient Estimation of Dynamic Density Functions with Applications in Data Streams [chapter]

Abdulhakim Qahtan, Suojin Wang, Xiangliang Zhang
2018 Studies in Big Data  
KDE-Track summarizes the distribution of a data stream by estimating the Probability Density Function (PDF) of the stream at a set of resampling points.  ...  A typical solution to tackle the problems of mining data streams is to learn a model that fits in the computer memory.  ...  Fig. 2 : 2 Example of adaptive resampling: more resampling points are used in regions with high curvature of the function. 11: end for 12: while a new sample x x xt arrives in the stream do 13: 2 it  ... 
doi:10.1007/978-3-319-89803-2_11 fatcat:nfuip3y55nb7hdsilr47c6pbki

Guided Learning of Control Graphs for Physics-Based Characters

Libin Liu, Michiel Van De Panne, Kangkang Yin
2016 ACM Transactions on Graphics  
The difficulty of developing control strategies has been a primary bottleneck in the adoption of physics-based simulations of human motion.  ...  We present a method for learning robust feedback strategies around given motion capture clips as well as the transition paths between clips.  ...  The guided sample selection and resampling implicitly focuses the exploration on regions of the state space that are both relevant to the current policy as well as regions of the action space that are  ... 
doi:10.1145/2893476 fatcat:vshdaunjbrdxvgraskhdaum3uu

Localization and navigation of the CoBots over long-term deployments

Joydeep Biswas, Manuela M. Veloso
2013 The international journal of robotics research  
motion model of the robot, and either the observed odometry or command actions, followed by a observation based weighting function and a resample step.  ...  For navigation, we present a hierarchical planner, which computes a topological policy using a graph representation of the environment, computes motion commands based on the topological policy, and then  ... 
doi:10.1177/0278364913503892 fatcat:l5yzzzl6yvfilmt7pzvn6jdnia
« Previous Showing results 1 — 15 out of 378 results