OctoMap : A Probabilistic , Flexible , and Compact 3 D Map Representation for Robotic Systems

By Kai M. Wurm, Armin Hornung, Maren Bennewitz, Cyrill Stachniss, Wolfram Burgard. 2010

511 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/f3fa1f32535a1725ca3074482aa8304bdd385064

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

Chisel: Real Time Large Scale 3D Reconstruction Onboard a Mobile Device using Spatially Hashed Signed Distance Fields (2015, methodology): “Occupancy grid mapping has already been shown to perform in real-time on Tango [1] devices using an Octree representation [24].”
Grounding spatial relations for human-robot interaction (2013, methodology): “For planning and executing a collision-free trajectories with the 7DOF arms [23], we used a compact 3D map [24].”
Object disappearance for object discovery (2012, methodology): “Octree-based techniques like OctoMap [20] can be used for this, but these dense techniques are extremely sensitive to small localization errors, particularly at the resolutions necessary to detect objects.”
State estimation for aggressive flight in GPS-denied environments using onboard sensing (2012, methodology): “We blur the a 3D occupancy map stored as an OctoMap [21] using a Gaussian kernel around occupied cells.”
Volumetric 3D mapping in real-time on a CPU (2014, background): “When the SDF is internally represented as an octree [20], the memory consumption can be greatly reduced by allocating only those cells that are located sufficently close to the surface.”
Integrated task and motion planning in belief space (2013, methodology): “Keeping an accurate probabilistic model of known-clear space is quite difficult: the typical approach in two-dimensional problems is an occupancy grid [Elfes, 1989], which was recently extended to three-dimensional problems [Wurm et al., 2010].”
Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot (2015, methodology): “This cloud is then converted into a probabilistic occupancy grid (OctoMap) [67] against which e cient localization comparisons later performed during locomotion.”
MoveIt! [ROS Topics] (2012, methodology): “The environment model was built upon the Octomap package [1], an octreebased probabilistic representation, allowing for efficient representation of large cluttered scenes.”
Detection, classification and tracking of moving objects in a 3D environment (2012, methodology): “For 3D mapping of the environment, we have used the octree based 3D occupancy grid approach presented in [15].”
FUEL: Fast UAV Exploration Using Incremental Frontier Structure and Hierarchical Planning (2020, background): “Similar to [35], which is widely applied in exploration, [34] builds an occupancy grid representation of the space.”
KinectFusion: Real-time dense surface mapping and tracking (2011, background): “More recently, SLAM work has focused on large scale reconstruction (mapping) including an impressive recent 3D version of the occupancy mapping approach, relying on 3D laser range-finder data and using octrees to enable scaling to large volumes is the Octomap algorithm [29].”