Robust Monte Carlo localization for mobile robots

By Sebastian Thrun, Dieter Fox, Wolfram Burgard, Frank Dellaert. Artificial Intelligence, 2001

2,054 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/d209d62ddcd90afb8d5ea8d259ec851a48235dc7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

The Player/Stage Project: Tools for Multi-Robot and Distributed Sensor Systems (2003, methodology): “By minimizing constraints on the control program, Player and Stage offer a uniquely ¤exible robot development environment compared to others such as Saphira [16], Mission Lab [17], TeamBots [2], Ayllu [32], DCA [21], ARIA [1], and CARMEN [26].”
Localization for mobile sensor networks (2004, methodology): “Our work adapts the Monte Carlo localization (MCL) method [10, 42] developed for use in robotics localization for use in mobile sensor network applications.”
Socially compliant mobile robot navigation via inverse reinforcement learning (2016, methodology): “We localize the robot in a static map using laser-based Monte Carlo Localization (Thrun et al., 2000).”
Active localization with dynamic obstacles (2016, methodology): “We employ a particle ﬁlter [18], [19], [20] to solve the passive global localization problem.”
A Statistical Modeling Approach to Location Estimation (2002, methodology): “There are several empirical methods for location estimation, such as RADAR [2], Nibble [8], RadioCamera [15], and the ones developed in the robotics community (see [ 28 ] and the references therein).”
Multi-robot Simultaneous Localization and Mapping using Particle Filters (2005, methodology): “It is also very easy to implement: the sensor model S and action model A are identical to those used in the standard MonteCarlo localization algorithm (Thrun et al. 2001), and the map generator M is a simple ray-tracing algorithm.”
A Generalized Extended Kalman Filter Implementation for the Robot Operating System (2014, methodology): “We plan to add new nodes in the future, such as an unscented Kalman filter [13] node and a particle filter [14] node.”
Adapting the Sample Size in Particle Filters Through KLD-Sampling (2003, methodology): “Furthermore, our approach can be combined with any other method for improving the efficiency of particle filters (Gilks and Berzuini 2001; Pitt and Shephard 1999; Godsill and Clapp 2001; Thrun et al. 2001).”
Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal (2018, background): “Traditional approaches have consisted of localisation techniques, often in conjunction with mapping, in order to form as complete a picture as possible of the joint conﬁguration of the world and the robot [1, 2].”
Biips: Software for Bayesian Inference with Interacting Particle Systems (2014, background): “They have found numerous applications in signal ﬁltering and robotics (Thrun et al. 2001; Gustafsson et al. 2002; Vermaak et al. 2002; Vo et al. 2003; Ristic et al. 2004; Caron et al. 2007), systems biology (Golightly and Wilkinson 2006, 2011; Bouchard-Côté et al. 2012), economics and…”
Finding Approximate POMDP solutions Through Belief Compression (2011, neutral): “Such state estimators as the Kalman lter (Leonard & Durrant-Whyte, 1991) or Markov localization (Fox, Burgard, & Thrun, 1999; Thrun, Fox, Burgard, & Dellaert, 2000 ) provide a (possibly factored, Boyen & Koller, 1998) distribution over possible states of the world instead of a single (possibly inco”
Perspectives on standardization in mobile robot programming: the Carnegie Mellon Navigation (CARMEN) Toolkit (2003, methodology): “Previous implementations [12] of mobile robot control software favoured a multi-level support, with coarse strategic planning providing intermediate goals to a lower-level collision avoidance module [2].”
Anytime Point-Based Approximations for Large POMDPs (2006, background): “While this may seem like a generous (or optimistic) assumption, substantial experience with domains of this size and maps of this quality have demonstrated robust localization abilities (Thrun et al., 2000).”
The spherical simplex unscented transformation (2003, methodology): “Although the method is potentially extremely powerful, it requires a large number of sample points for reliable estimates (Thrun [ 6 ] reports several thousand for a 3 dimensional navigation system).”
Autonomous discovery of temporal abstractions from interaction with an environment (2002, background): “With the ability to use GPS outdoors or the ability to estimate position indoors (Thrun et al., 2000), this is not an unrealistic assumption.”