Filters








1,642 Hits in 3.4 sec

Motion planning under uncertainty for robotic tasks with long time horizons

Hanna Kurniawati, Yanzhu Du, David Hsu, Wee Sun Lee
2010 The international journal of robotics research  
By using probabilistic sampling, pointbased POMDP solvers have drastically improved the speed of POMDP planning, enabling POMDPs to handle moderately complex robotic tasks.  ...  We tested MiGS in simulation on several difficult POMDPs modeling distinct robotic tasks with long time horizons; they are impossible with the fastest point-based POMDP solvers today.  ...  This work is supported in part by AcRF grant R-252-000-327-112 from the Ministry of Education of Singapore.  ... 
doi:10.1177/0278364910386986 fatcat:wm2pkgpgcbewvc6gyjiycxo4tm

Identification of probabilistic approaches and map-based navigation in motion planning for mobile robots

B Madhevan, M Sreekumar
2018 Sadhana (Bangalore)  
Future research prospects in multi-robot path planning based on probabilistic approaches are also discussed.  ...  RMP is a complex task when it needs to be planned for a group of robots in a coordinated environment with leader-follower relationship.  ...  Secondarily, to evaluate PRM actions efficiently in the context of uncertainty and then generate motion plans with minimal error. Further, PRM is a probability-based planning method.  ... 
doi:10.1007/s12046-017-0776-8 fatcat:hnek2eu7w5gv7ky3sr3uz5glrm

Path planning in belief space with pose SLAM

Rafael Valencia, Juan Andrade-Cetto, Josep M. Porta
2011 2011 IEEE International Conference on Robotics and Automation  
We present a method that devises optimal navigation strategies by searching for the path in the pose graph with lowest accumulated robot pose uncertainty, independently of the map reference frame.  ...  In contrast, we argue in this paper that Pose SLAM graphs can be directly used as belief roadmaps.  ...  The most successful path planning methods are those based on randomized sampling such as the Probabilistic Roadmaps or the Rapidly-exploring Random Trees in which samples are stochastically drawn in the  ... 
doi:10.1109/icra.2011.5979742 dblp:conf/icra/ValenciaAP11 fatcat:2cce5pyryjbg7b6bbttawf4gle

Path Planning in Belief Space with Pose SLAM [chapter]

Rafael Valencia, Juan Andrade-Cetto
2017 Springer Tracts in Advanced Robotics  
We present a method that devises optimal navigation strategies by searching for the path in the pose graph with lowest accumulated robot pose uncertainty, independently of the map reference frame.  ...  In contrast, we argue in this paper that Pose SLAM graphs can be directly used as belief roadmaps.  ...  The most successful path planning methods are those based on randomized sampling such as the Probabilistic Roadmaps or the Rapidly-exploring Random Trees in which samples are stochastically drawn in the  ... 
doi:10.1007/978-3-319-60603-3_4 fatcat:lujqzbyftrd77inbxrdm3pcwju

Motion Planning Under Uncertainty: Application to an Unmanned Helicopter

Joshua D. Davis, Suman Chakravorty
2007 Journal of Guidance Control and Dynamics  
The motion planner involves a high-level planner which plans against the uncertainty in the environment and issues its commands as a series of waypoints for a lowerlevel controller to track.  ...  The optimal path for the unmanned helicopter is planned using a priori knowledge about the environment, and the sensor data received as the helicopter navigates the obstacles in the environment.  ...  Probabilistic roadmaps (PRM) are a recent development in motion planning and are an efficient method for determining an optimal path.  ... 
doi:10.2514/1.25077 fatcat:dxo3beumgnhlrb5xo7ehjj6mhm

Stein Variational Probabilistic Roadmaps [article]

Alexander Lambert, Brian Hou, Rosario Scalise, Siddhartha S. Srinivasa, Byron Boots
2022 arXiv   pre-print
We posit that such uncertainty in environment geometry can, in fact, help drive the sampling process in generating feasible, and probabilistically-safe planning graphs.  ...  Our approach, Stein Variational Probabilistic Roadmap (SV-PRM), results in sample-efficient generation of planning-graphs and large improvements over traditional sampling approaches.  ...  INTRODUCTION AND RELATED WORK Probabilistic roadmaps approximate a continuous configuration space with a discrete set of sampled configurations [1, 2] .  ... 
arXiv:2111.02972v2 fatcat:ojp6djjuxzdpbd27h2ifrbg2be

Task-Motion Planning for Navigation in Belief Space [article]

Antony Thomas, Fulvio Mastrogiovanni, Marco Baglietto
2019 arXiv   pre-print
We discuss a probabilistically complete approach that leverages this task-motion interaction for navigating in indoor domains, returning a plan that is optimal at the task-level.  ...  We present an integrated Task-Motion Planning (TMP) framework for navigation in large-scale environment.  ...  In contrast, we use a temporal task planner, POPF-TIF [9] with roadmap based sampling, incorporating robot state uncertainty. Srivastava et al.  ... 
arXiv:1910.11683v1 fatcat:krsoyt2ozvgajfdllagjekh4t4

Robust Belief Roadmap: Planning Under Intermittent Sensing [article]

Shaunak D. Bopardikar, Brendan J. Englot, Alberto Speranzon
2013 arXiv   pre-print
Computational results demonstrate the benefit of the approach and comparisons are made with the state of the art in path planning under state uncertainty.  ...  In this paper, we extend the recent body of work on planning under uncertainty to include the fact that sensors may not provide any measurement owing to misdetection.  ...  Some algorithms assume uncertainty in the map used for navigation.  ... 
arXiv:1304.7256v2 fatcat:lyjm35otnbeljf7wb7ott2342m

Bootstrapping navigation and path planning using human positional traces

Alen Alempijevic, Robert Fitch, Nathan Kirchner
2013 2013 IEEE International Conference on Robotics and Automation  
Navigating and path planning in environments with limited a priori knowledge is a fundamental challenge for mobile robots.  ...  as Probabilistic Roadmaps (PRM) can effectively utilise.  ...  as Probabilistic Roadmaps (PRM) can effectively utilise.  ... 
doi:10.1109/icra.2013.6630730 dblp:conf/icra/AlempijevicFK13 fatcat:skotfnf56vdorb4pl2iiv3qfya

Motion Planning under Uncertainty for Robotic Tasks with Long Time Horizons [chapter]

Hanna Kurniawati, Yanzhu Du, David Hsu, Wee Sun Lee
2011 Springer Tracts in Advanced Robotics  
Motion planning with imperfect state information is a crucial capability for autonomous robots to operate reliably in uncertain and dynamic environments.  ...  Partially observable Markov decision processes (POMDPs) provide a principled general framework for planning under uncertainty.  ...  We thank Sylvie Ong and Shao Wei Png for reading the first draft of this paper and helping with scripting a POMDP model.  ... 
doi:10.1007/978-3-642-19457-3_10 fatcat:3kyeqqx7yzhkpbkp5nppnh3aaa

An Overview of Planning Technology in Robotics [chapter]

Malik Ghallab
2004 Lecture Notes in Computer Science  
We present here an overview of several planning techniques in robotics.  ...  We will not be concerned with the synthesis of abstract mission and task plans, using well known classical and other domain-independent planning techniques.  ...  The algorithm Probabilistic-Roadmap ( Figure 2 ) starts initially with an empty roadmap.  ... 
doi:10.1007/978-3-540-30221-6_3 fatcat:6eyehtwszjaxjb2zenrygkitpi

Variational End-to-End Navigation and Localization [article]

Alexander Amini, Guy Rosman, Sertac Karaman, Daniela Rus
2019 arXiv   pre-print
In this paper, we extend end-to-end driving networks with the ability to perform point-to-point navigation as well as probabilistic localization using only noisy GPS data.  ...  We define a novel variational network capable of learning from raw camera data of the environment as well as higher level roadmaps to predict (1) a full probability distribution over the possible control  ...  and uncertainty about the longer-term plan.  ... 
arXiv:1811.10119v2 fatcat:bsfle3yp6rejbok7ewpg5mssva

Construction and use of roadmaps that incorporate workspace modeling errors

Nick Malone, Kasra Manavi, John Wood, Lydia Tapia
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In this paper, we present a method for roadmap construction that can be used in workspaces with uncertainty in the model.  ...  Probabilistic Roadmap Methods (PRMs) have been shown to work well at solving high Degree of Freedom (DoF) motion planning problems.  ...  Planning With Uncertainty The two main types of uncertainty are model uncertainty and motion uncertainty.  ... 
doi:10.1109/iros.2013.6696512 dblp:conf/iros/MaloneMWT13 fatcat:e7puc4fuwvadlfzseaqy6z4hjy

Generalized sampling based motion planners with application to nonholonomic systems

Suman Chakravorty, S. Kumar
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
as uncertainties in the robot map/ workspace.  ...  In this paper, generalized versions of the probabilistic sampling based planners, Probabilisitic Road Maps (PRM) and Rapidly exploring Random Tree (RRT), are presented.  ...  Generalized Probabilistic Roadmap (GPRM) In motion planning, the objective is to plan the path of a robot from a start state to an end state.  ... 
doi:10.1109/icsmc.2009.5346705 dblp:conf/smc/ChakravortyK09 fatcat:xt6jv3qy2zbplcgrpazeynnbve

Study of Wrinkling and Thinning Behavior in The Stamping Process of Top Outer Hatchback Part on The SCGA and SPCC Materials

Sri Wahyanti, Agus Dwi Anggono, Waluyo Adi Siswanto
2020 Advances in Science, Technology and Engineering Systems  
This yield to a lot of improvement and suggestions in many areas related to mobile robot such as path planning.  ...  , interact with objects and making quick decision.  ...  Local navigational approaches are more intelligence since they need to interact with the dynamic environment and execute plan autonomously. These methods are classified as in Figure 1 .  ... 
doi:10.25046/aj050330 fatcat:5gulgqyuonbqvfb3vgw4e73fke
« Previous Showing results 1 — 15 out of 1,642 results