RT Conference Proceedings
T1 Evaluation of neural euclidean signed distance fields for distance-aware local path planning
A1 Gil García, Guillermo
A1 Cobano-Suárez, José-Antonio
A1 Caballero, Fernando
A1 Merino, Luis
K1 Three-dimensional displays
K1 Path planning
K1 Space exploration
K1 Planning
K1 Indoor environment
K1 Robot
K1 Aerial systems
K1 Neural Distance Fields
K1 Perception
AB This paper presents a 3D local path planner based on Neural Euclidean Signed Distance Fields (ESDFs). There are approaches in the literature that make use of ESDFs as representation of the environment for planning, but not on the use of neural ESDF for distance-aware local path planning. This paper evaluates the proposed approach and analyses the quality of the paths generated by planners based on online Neural ESDF. The distance field is based on the HIO-SDF network, and the planner exploits the analytical properties of the ESDFs. The experimental validation shows promising results on the applications of HIO-SDF networks for 3D local path planning.
PB IEEE
YR 2024
FD 2024-12-23
LK https://hdl.handle.net/10433/23348
UL https://hdl.handle.net/10433/23348
LA en
NO Service Robotics Lab
DS RIO
RD May 8, 2026