Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning

By Helen Oleynikova, Zachary Taylor, Marius Fehr, Roland Yves Siegwart, Juan I. Nieto. IEEE/RJS International Conference on Intelligent RObots and Systems, 2016

786 citations recorded by the source corpus.

Micro Aerial Vehicles (MAVs) that operate in unstructured, unexplored environments require fast and flexible local planning, which can replan when new parts of the map are explored. Trajectory optimization methods fulfill these needs, but require obstacle distance information, which can be given by Euclidean Signed Distance Fields (ESDFs). We propose a method to incrementally build ESDFs from Truncated Signed Distance Fields (TSDFs), a common implicit surface representation used in computer graphics and vision. TSDFs are fast to build and smooth out sensor noise over many observations, and are designed to produce surface meshes. We show that we can build TSDFs faster than Octomaps, and that it is more accurate to build ESDFs out of TSDFs than occupancy maps. Our complete system, called voxblox, is available as open source and runs in real-time on a single CPU core. We validate our approach on-board an MAV, by using our system with a trajectory optimization local planner, entirely on-board and in real-time.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bae5d50b59282140648224274af73931f2c58711

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 Computer Vision and Pattern Recognition

Citations in the corpus

Where Should I Walk? Predicting Terrain Properties From Images Via Self-Supervised Learning (2019, background): “a geometric representation of the environment, like 2D heightmaps [1], [2], point clouds [3], and signed distance fields [7].”
EGO-Planner: An ESDF-Free Gradient-Based Local Planner for Quadrotors (2020, neutral): “[13] H. Oleynikova, Z. Taylor, M. Fehr, R. Siegwart, and J. Nieto, “Voxblox: Incremental 3d euclidean signed distance fields for on-board mav planning,” in Proc.”
ANYmal parkour: Learning agile navigation for quadrupedal robots (2023, methodology): “For navigation, signed distance fields [39] are commonly used since they can easily be integrated into the problem formulation to avoid elements in the scene.”
An Efficient Sampling-Based Method for Online Informative Path Planning in Unknown Environments (2019, methodology): “We use voxblox [20] as a map representation, the control hierarchy presented in [24] for trajectory tracking, and the Gazebo-based RotorS simulator [25] to accurately model the MAV’s physics.”
Continual Learning of Semantic Segmentation using Complementary 2D-3D Data Representations (2021, methodology): “The TSDF is calculated following [22].”
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (2023, methodology): “On similar lines, iSDF [28] used implicit representations to efficiently compute signed-distances, compared to [25, 27].”
Maplab: An Open Framework for Research in Visual-Inertial Mapping and Localization (2017, methodology): “To that end, maplab employs voxblox [38], a volumetric mapping library, for TSDFbased depth fusion and surface reconstruction.”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, methodology): “3) builds a global 3D mesh using a volumetric approach (Oleynikova et al., 2017), and semantically annotates the 3D mesh using 2D pixel-wise segmentation and 3D Bayesian updates.”
Vision-Only Robot Navigation in a Neural Radiance World (2021, methodology): “Works such as [23] and [24] present methods for incrementally constructing SDF-like map representations and using them for online motion planning.”
Learning high-speed flight in the wild (2021, background): “Please watch Movie 1 to get a better sense of the speed and agility of our approach. algorithms have been proposed to achieve autonomous ﬂight in previously unknown environments [14–22].”
Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization (2022, positive): “Kimera [50] uses Voxblox [43] to integrate semantically-labeled point clouds into a Truncated Signed Distance Field (TSDF) and an ESDF of the environment, while also performing Bayesian inference over the semantic label of each voxel.”
A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers (2022, background): “Examples of dense metric-semantic maps include Voxblox++ [95] and Kimera [96] (which build upon an SDF), and Fusion++ [97] and [98] (based on voxel maps).”