526 Hits in 6.7 sec

A Deep Reinforcement Learning Approach for Active SLAM

Julio A. Placed, José A. Castellanos
2020 Applied Sciences  
In this paper, we formulate the active SLAM paradigm in terms of model-free Deep Reinforcement Learning, embedding the traditional utility functions based on the Theory of Optimal Experimental Design in  ...  in robotic exploration.  ...  In this way, one of the main drawbacks of traditional active SLAM methods is relaxed by transferring the intensive computations to the DNN training phase, requiring only feed-forward propagation during  ... 
doi:10.3390/app10238386 fatcat:sk5plhifsbckvckown3u4gneyu

A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers [article]

Julio A. Placed, Jared Strader, Henry Carrillo, Nikolay Atanasov, Vadim Indelman, Luca Carlone, José A. Castellanos
2022 arXiv   pre-print
In this work, we survey the state-of-the-art in active SLAM and take an in-depth look at the open challenges that still require attention to meet the needs of modern applications. % in order to achieve  ...  Active Simultaneous Localization and Mapping (SLAM) is the problem of planning and controlling the motion of a robot to build the most accurate and complete model of the surrounding environment.  ...  Monotonicity. One of the most important assumptions in active SLAM is that uncertainty increases as exploration takes place.  ... 
arXiv:2207.00254v1 fatcat:ksyanwtftje3xkx7tbql6hry54

Fast Uncertainty Quantification for Active Graph SLAM [article]

Julio A. Placed, José A. Castellanos
2022 arXiv   pre-print
Based on the former, we present an online Active graph SLAM system capable of selecting D-optimal actions and that outperforms other state-of-the-art methods that rely on slower computations.  ...  Therefore, the optimal set of actions can be estimated by maximizing optimality criteria of the weighted Laplacian instead of that of the FIM.  ...  Our system performs D-optimal Active SLAM in complex simulation environments, achieving behaviors akin to other state-of-the-art Active SLAM methods based on traditional utility computations in a reduced  ... 
arXiv:2110.01289v2 fatcat:jstep3nf2nb2hin6fk6kkjqjmu

A high-efficiency, information-based exploration path planning method for active simultaneous localization and mapping

Peng Li, Cai-yun Yang, Rui Wang, Shuo Wang
2020 International Journal of Advanced Robotic Systems  
The efficiency of exploration in an unknown scene and full coverage of the scene are essential for a robot to complete simultaneous localization and mapping actively.  ...  The dead-reckoning algorithm is used to predict the uncertainty of the robot's pose along each candidate path. The exploration path is selected based on exploration efficiency and/or high coverage.  ...  The active SLAM can be separated into two subproblems, SLAM and the active exploration path planning.  ... 
doi:10.1177/1729881420903207 fatcat:ltuxt6fgxvehhltkxxu6yzkd7a

Good Graph to Optimize: Cost-Effective, Budget-Aware Bundle Adjustment in Visual SLAM [article]

Yipu Zhao, Justin S. Smith, Patricio A. Vela
2020 arXiv   pre-print
The cost-efficiency of visual(-inertial) SLAM (VSLAM) is a critical characteristic of resource-limited applications.  ...  An efficient algorithm, called Good Graph, is developed to select size-reduced graphs optimized in local BA with condition preservation.  ...  In doing so, it was one of the first active matching approaches to save time, in the sense that the combined time cost of the active matching and the reduced size pose optimization was lower than that  ... 
arXiv:2008.10123v1 fatcat:dlilgtwbw5b77jmfa4ppczjsam

Planning for robotic exploration based on forward simulation

Mikko Lauri, Risto Ritala
2016 Robotics and Autonomous Systems  
Experimental results in simulated and real environments show that, depending on the environment, applying POMDP based planning for exploration can improve performance over frontier exploration.  ...  We address the problem of controlling a mobile robot to explore a partially known environment. The robot's objective is the maximization of the amount of information collected about the environment.  ...  Acknowledgements The authors thank Mr. Olli Suominen for helpful discussions and comments on the manuscript, and Mr. Joonas Melin for assistance in carrying out the experimental work.  ... 
doi:10.1016/j.robot.2016.06.008 fatcat:t3ewax4shndudk2hsv2ygrvjay

Where am I? Creating spatial awareness in unmanned ground robots using SLAM: A survey

2015 Sadhana (Bangalore)  
SLAM is the process of creating a map of the environment, sometimes unknown apriori, while at the same time localizing the robot in the same map.  ...  SLAM algorithms for both static and dynamic environments have been surveyed. The algorithms in each class are further divided based on the techniques used.  ...  In some approaches, each node in the topological map is a distinct place in the environment. The robot acts as the local observer during the exploration of the envorinment.  ... 
doi:10.1007/s12046-015-0402-6 fatcat:33hu7lxwsja2fdjepsdxjczd54

Fast minimum uncertainty search on a graph map representation

Henry Carrillo, Yasir Latif, Jose Neira, Jose A. Castellanos
2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
in the computation time with respect to the state of the art. • A-optimality criterion (A-opt) [18]: This criterion targets the minimization of the variance and it is defined as  ...  This paper addresses the problem of path planning considering uncertainty criteria over the belief space.  ...  According to the TOED [16] [17] D-opt gives the most accurate approximation of the uncertainty enclosed in the covariance matrix, but in the context of active SLAM or planning under uncertainty [10]  ... 
doi:10.1109/iros.2012.6385927 dblp:conf/iros/CarrilloLNC12 fatcat:lfkdawdh3fghzk3bpgpgfxhbrm

Active learning in robotics: A review of control principles

Annalisa T. Taylor, Thomas A. Berrueta, Todd D. Murphey
2021 Mechatronics (Oxford)  
This is a review of active learning in robotics, focusing on methods amenable to the demands of embodied learning systems.  ...  In this work, we survey the fundamental components of robotic active learning systems.  ...  Acknowledgments We would like to thank Muchen Sun, Ana Pervan, Kyra Rudy, Frank Park, and the anonymous reviewers of the first draft for their many helpful comments on this manuscript.  ... 
doi:10.1016/j.mechatronics.2021.102576 fatcat:qt47bncznzdtdc7ntpmis5dqw4

A Review of Visual-LiDAR Fusion based Simultaneous Localization and Mapping

César Debeunne, Damien Vivet
2020 Sensors  
After a summary of the basic idea of SLAM and its implementation, we give a complete review of the state-of-the-art of SLAM research, focusing on solutions using vision, LiDAR, and a sensor fusion of both  ...  Indeed, hybridized solutions offer improvements in the performance of SLAM, especially with respect to aggressive motion, lack of light, or lack of visual features.  ...  The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; nor in the decision to publish the results.  ... 
doi:10.3390/s20072068 pmid:32272649 fatcat:rxpcwm666vfypphxtcuzk3rxdu

A frontier based multi-robot approach for coverage of unknown environments

Raja Sankar Dileep Muddu, Dan Wu, Libing Wu
2015 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)  
I also appreciate the financial aid and computing resources he provided during my thesis.  ...  Current research in robotics is focused on multi robot exploration to assist humans in dangerous and monotonous tasks.  ...  And it is always handy to have a social robot assisting in monotonous house hold activities like floor cleaning [4] .  ... 
doi:10.1109/robio.2015.7414626 dblp:conf/robio/MudduWW15 fatcat:jjafbru2snfl3i5t524sn57px4

Anytime Planning for Decentralized Multirobot Active Information Gathering

Brent Schlotfeldt, Dinesh Thakur, Nikolay Atanasov, Vijay Kumar, George J. Pappas
2018 IEEE Robotics and Automation Letters  
This active information gathering problem has applications in environmental monitoring, search and rescue, and security and surveillance.  ...  The novelty of this letter is to demonstrate the practical feasibility of these algorithms in a target tracking scenario featuring three collaborating UAVs and five mobile targets.  ...  In line 9 of Algorithm 2, ( , δ) decrease monotonically in runtime, which implies that the solution cost decreases monotonically in runtime.  ... 
doi:10.1109/lra.2018.2794608 dblp:journals/ral/SchlotfeldtTAKP18 fatcat:qjzxwcf3ojgwngwravn4cayg5i

Enhanced hyperpolarized chemical shift imaging based on a priori segmented information

Gil Farkash, Stefan Markovic, Mihajlo Novakovic, Lucio Frydman
2019 Magnetic Resonance in Medicine  
The purpose of the study was to develop an approach for improving the resolution and sensitivity of hyperpolarized 13 C MRSI based on a priori anatomical information derived from featured, water-based  ...  Additional information can be found in the Supporting Information section available in the on-line version of this article.  ...  This research was supported by Minerva Project 712277, NIH Grant R01HD086323, the Kimmel Institute for Magnetic Resonance (WIS), and the generosity of the Perlman Family Foundation.  ... 
doi:10.1002/mrm.27631 pmid:30652358 fatcat:zt675qsxk5g7dkn634v3gai5vu

A Primer on Autonomous Aerial Vehicle Design

Hugo Coppejans, Herman Myburgh
2015 Sensors  
This allows the platform to freely explore without a constraint on the area in which it can operate.  ...  The ability to create a working autonomous MAV depends mainly on integrating a simultaneous localization and mapping (SLAM) solution with the rest of the system.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s151229785 pmid:26633410 pmcid:PMC4721706 fatcat:72tcgljxrzbzdeiviv5q5vgcz4

Stochastic State Estimation for Simultaneous Localization and Map Building in Mobile Robotics [chapter]

Juan Andrade, Teresa A. Vidal Calleja, Alberto Sanfeliu
2005 Cutting Edge Robotics  
The Problem of Coupled Stochastic State Estimation 1 The study of stochastic models for Simultaneous Localization and Map Building (SLAM) in mobile robotics has been an active research topic for over  ...  For the two-landmark case, the landmark variance estimate is greater than the optimal solution shown in the third column in Figure 5 since the covariance has been inflated during decorrelation.  ...  Different mechatronic systems oriented on robotics are explored in the last chapter of the book.  ... 
doi:10.5772/4651 fatcat:urd57di5ljbntehi4ql7k4jsai
« Previous Showing results 1 — 15 out of 526 results