KLD-Sampling: Adaptive Particle Filters

By Dieter Fox. Neural Information Processing Systems, 2001

435 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/81a6c81e77931c4f8b75df8c9564c640a56e12bf

How researchers see this paper

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

Citations in the corpus

The Marathon 2: A Navigation System (2020, methodology): “AMCL : An implementation of an Adaptive Monte-Carlo Localization, which uses a particle ﬁlter to localize a robot in a given occupancy grid using omni-directional or differential motion models [18].”
The Office Marathon: Robust navigation in an indoor office environment (2010, methodology): “Cells that are less than one inscribed radius of the robot away from an obstacle (see Figure 6) are assigned a uniformly high cost, after which an exponential decay function is applied that will cause the cost to drop off out to the inflation radius used for the Costmap.”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, unknown): “[62], [63], people tracking [64], etc.”
Pedestrian localisation for indoor environments (2008, methodology): “Several schemes have been proposed for dynamically adapting the number of particles used to represent the distribution, such as likelihood-based adaptation [7], Kullback-Leibler divergence (KLD) sampling [5] and variants [17].”
Sigma-point kalman filters for probabilistic inference in dynamic state-space models (2004, background): “Recent work on adaptive particle filtersusing KLD sampling [8] attempts to address this by adapting t he number of particles used in real time.”
Design and use paradigms for Gazebo, an open-source multi-robot simulator (2004, methodology): “For example, it is possible to use Player’s VFH (Vector Field Histogram) [10] or AMCL (Adaptive Monte-Carlo Localization) [11] interchangeably between real and simulated environments.”
People Tracking with Mobile Robots Using Sample-Based Joint Probabilistic Data Association Filters (2003, methodology): “In this context, techniques to adaptively change the sample size according to the underlying uncertainty [19] might be attractive to improve the overall efficiency.”
Magicol: Indoor Localization Using Pervasive Magnetic Field and Opportunistic WiFi Sensing (2015, methodology): “We adopted KLD-sampling [30] to change the number of particles on-the-fly on the basis of their distribution.”
Deep Local Trajectory Replanning and Control for Robot Navigation (2019, methodology): “JackRabbot’s software stack uses the Robot Operating System (ROS) [62] for inter-process communication and logging, OpenSlam’s Gmapping for creating environment maps [63], ROS’s Adaptive Monte Carlo Localization algorithm for pose estimation [64], and YOLO [65] and DeepSort [66] for visually detecti”