UFOMap: An Efficient Probabilistic 3D Mapping Framework That Embraces the Unknown

Duberg, Daniel

doi:10.48550/arxiv.2003.04749

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At their cores, mapping an outdoor off-road terrain and an urban one are functionally similar processes. OctoMap [1] and UFOMap [2] are popular, robust and freely available tools that can produce occupancy maps of various environments. However, they do not have the capability of inferring whether a node in an unknown occupancy state between other occupied nodes is occupied or free.…”

Section: Methodsmentioning

confidence: 99%

“…OctoMap [1] and a recent variant, UFOMap [2], offer such a LiDAR-based mapping approach suitable for use by mobile robots and their immediate surroundings. As LiDAR data are received, these systems organise them into an octree [10] structure, which is a highly scalable and optimised data structure for 3D geometric modelling and is very well-suited for high resolution mapping.…”

Section: Related Workmentioning

confidence: 99%

“…A popular approach to the terrain mapping problem uses point clouds captured from a LiDAR sensor and merges them together over time using methods such as OctoMap [1] and UFOMap [2] to form a complete map of the environment. However, these methods become less robust the further away data captured by the LiDAR are from the actual sensor -significant gaps in the terrain estimate are introduced as the gaps between LiDAR hits become larger.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

EMap: Real-Time Terrain Estimation

Lock

Camara

Fox

2022

Towards Autonomous Robotic Systems

View full text Add to dashboard Cite

Terrain mapping has a many use cases in both land surveyance and autonomous vehicles. Popular methods generate occupancy maps over 3D space, which are sub-optimal in outdoor scenarios with large, clear spaces where gaps in LiDAR readings are common. A terrain can instead be modelled as a height map over 2D space which can iteratively be updated with incoming LiDAR data, which simplifies computation and allows missing points to be estimated based on the current terrain estimate. The latter point is of particular interest, since it can reduce the data collection effort required (and its associated costs) and current options are not suitable to real-time operation. In this work, we introduce a new method that is capable of performing such terrain mapping and inferencing tasks in real-time. We evaluate it with a set of mapping scenarios and show it is capable of generating maps with higher accuracy than an OctoMap-based method.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

EMap: Real-Time Terrain Estimation

Lock

Camara

Fox

2022

Towards Autonomous Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Numerous 3D space representations exist such as signed distance fields [7] [8], octrees [9] [10], and voxel grids [1].…”

Section: A Related Workmentioning

confidence: 99%

GPU Accelerated Voxel Grid Generation for Fast MAV Exploration

Toumieh¹,

Lambert²

2021

Preprint

View full text Add to dashboard Cite

Voxel grids are a minimal and efficient environment representation that is used for robot motion planning in numerous tasks. Many state-of-the-art planning algorithms use voxel grids composed of free, occupied and unknown voxels. In this paper we propose a new GPU accelerated algorithm for partitioning the space into a voxel grid with occupied, free and unknown voxels. The proposed approach is low latency and suitable for high speed navigation.

show abstract

UFOMap: An Efficient Probabilistic 3D Mapping Framework That Embraces the Unknown

Cited by 2 publications

References 0 publications

EMap: Real-Time Terrain Estimation

EMap: Real-Time Terrain Estimation

GPU Accelerated Voxel Grid Generation for Fast MAV Exploration

Contact Info

Product

Resources

About