Low-Latency Mapless ESDF Queries for MAV Reactive Collision Avoidance
Low-Latency Mapless ESDF Queries for MAV Reactive Collision Avoidance
This research proposes a GPU-accelerated, mapless ESDF query method for reactive collision avoidance in MAVs, achieving lower latency and higher accuracy than voxel-grid approaches. The method processes depth images directly, avoiding pre-processing, and is integrated into an MPC for real-world deployment in forest environments.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
maximum speed
≤9
View original evidence
neously more accurate and lower in total latency than every voxel-grid configuration we measured between 2 cm and 20 cm, at one to two orders of magnitude less memory at matched resolution. With our query integrated into a Model Predictive Controller (MPC), simulated runs in laser-scanned forests at up to 9 m/s collide in 0.4 % through dense branches, against 5.9 % with the best voxel grid and 5.5 % with the best map
Open source S4maximum speed
≤4
View original evidence
less baseline at our resolution, whose failures we attribute to voxel resolution and total latency respectively. We deploy the system onboard at two forest sites and fly at commanded speeds of up to 4 m/s.
Open source S5
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
neously more accurate and lower in total latency than every voxel-grid configuration we measured between 2 cm and 20 cm, at one to two orders of magnitude less memory at matched resolution. With our query integrated into a Model Predictive Controller (MPC), simulated runs in laser-scanned forests at up to 9 m/s collide in 0.4 % through dense branches, against 5.9 % with the best voxel grid and 5.5 % with the best map
Open source S4
less baseline at our resolution, whose failures we attribute to voxel resolution and total latency respectively. We deploy the system onboard at two forest sites and fly at commanded speeds of up to 4 m/s.
Open source S5
near-field, short-horizon problem with potentially only hundreds of queries per measurement, where building a map may not pay off. We propose a mapless, Graphics Processing Unit (GPU)-accelerated Euclidean Signed Distance Field (ESDF) query with negligible pre-processing that operates directly on posed depth images, with resolution set by pooling the image rather than by a voxel size. On an embedded GPU it is simulta
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org