SOFT‐SLAM: Computationally efficient stereo visual simultaneous localization and mapping for autonomous unmanned aerial vehicles

Abstract

Autonomous navigation of unmanned aerial vehicles (UAVs) in GPS‐denied environments is a challenging problem, especially for small‐scale UAVs characterized by a small payload and limited battery autonomy. A possible solution to the aforementioned problem is vision‐based simultaneous localization and mapping (SLAM), since cameras, due to their dimensions, low weight, availability, and large information bandwidth, circumvent all the constraints of UAVs. In this paper, we propose a stereo vision SLAM yielding very accurate localization and a dense map of the environment developed with the aim to compete in the European Robotics Challenges (EuRoC) targeting airborne inspection of industrial facilities with small‐scale UAVs. The proposed approach consists of a novel stereo odometry algorithm relying on feature tracking (SOFT), which currently ranks first among all stereo methods on the KITTI dataset. Relying on SOFT for pose estimation, we build a feature‐based pose graph SLAM solution, which we dub SOFT‐SLAM. SOFT‐SLAM has a completely separate odometry and mapping threads supporting large loop‐closing and global consistency. It also achieves a constant‐time execution rate of 20 Hz with deterministic results using only two threads of an onboard computer used in the challenge. The UAV running our SLAM algorithm obtained the highest localization score in the EuRoC Challenge 3, Stage IIa–Benchmarking, Task 2. Furthermore, we also present an exhaustive evaluation of SOFT‐SLAM on two popular public datasets, and we compare it to other state‐of‐the‐art approaches, namely ORB‐SLAM2 and LSD‐SLAM. The results show that SOFT‐SLAM obtains better localization accuracy on the majority of datasets sequences, while also having a lower runtime.

RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation

“…When comparing the trajectories at that scale, there is not so much difference between visual and lidar approaches and both follow well the ground truth. Table summarizes trajectory accuracy in terms of ATE for all odometry configurations available in RTAB‐Map, along with performance reported for ORB‐SLAM2 (Mur‐Artal & Tardós, ), LSD‐SLAM (Engel et al, ) and stereo odometry algorithm relying on feature tracking (SOFT)‐SLAM (Cvišić, Ćesić, Marković & Petrović, ). is the average odometry time across all sequences when limiting the approach to a single CPU Core.…”

Sparse Depth Enhanced Direct Thermal-Infrared SLAM Beyond the Visible Spectrum

“…During the last decade, vision-based motion estimation using consecutive images has matured into two main streams. One of them is a 6-DOF motion estimation method that utilizes visual feature correspondence [2], [11]. The other approach, called a direct method, estimates the ego-motion by minimizing the intensity difference of reprojected pixels from depth [1], [9], [10], [12].…”

Multi-Sensor 6-DoF Localization For Aerial Robots In Complex GNSS-Denied Environments

“…AMCL filters have high computational burden that is often addressed by using simple likelihood functions that do not always fully exploit the information contained in the features. Several SLAM schemes, such as [2], [11], can also be used in localizationonly mode. However, this is done for only one robot state, not exploiting the multi-hypothesis advantages of AMCLs.…”