Scalable Autonomous Drone Flight in the Forest with Visual-Inertial SLAM and Dense Submaps Built without LiDAR

2024-03-14

arXiv.org

AI Summary

Achieving fully autonomous navigation for micro air vehicles (MAVs) in unstructured forest environments remains challenging, particularly without LiDAR. Method: This paper proposes a vision-inertial (VI)-only large-scale autonomous navigation system. It introduces a novel dynamically updated dense voxel submap framework coupled with an online trajectory deformation anchoring mechanism to suppress long-term drift in VI-SLAM, ensuring robust high-speed localization and real-time path planning. The system runs entirely onboard, integrating VI-SLAM, incremental mapping, and loop-closure optimization. Contribution/Results: Evaluated in both real and simulated forests with tree densities exceeding 400 trees per hectare, the system enables sustained collision-free, fault-free flight at 3 m/s—marking the first pure VI-based MAV system to achieve such performance in dense natural forests.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Vision for Robotics & Autonomous Driving
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Forestry constitutes a key element for a sustainable future, while it is supremely challenging to introduce digital processes to improve efficiency. The main limitation is the difficulty of obtaining accurate maps at high temporal and spatial resolution as a basis for informed forestry decision-making, due to the vast area forests extend over and the sheer number of trees. To address this challenge, we present an autonomous Micro Aerial Vehicle (MAV) system which purely relies on cost-effective and light-weight passive visual and inertial sensors to perform under-canopy autonomous navigation. We leverage visual-inertial simultaneous localization and mapping (VI-SLAM) for accurate MAV state estimates and couple it with a volumetric occupancy submapping system to achieve a scalable mapping framework which can be directly used for path planning. As opposed to a monolithic map, submaps inherently deal with inevitable drift and corrections from VI-SLAM, since they move with pose estimates as they are updated. To ensure the safety of the MAV during navigation, we also propose a novel reference trajectory anchoring scheme that moves and deforms the reference trajectory the MAV is tracking upon state updates from the VI-SLAM system in a consistent way, even upon large changes in state estimates due to loop-closures. We thoroughly validate our system in both real and simulated forest environments with high tree densities in excess of 400 trees per hectare and at speeds up to 3 m/s - while not encountering a single collision or system failure. To the best of our knowledge this is the first system which achieves this level of performance in such unstructured environment using low-cost passive visual sensors and fully on-board computation including VI-SLAM.

Problem

• Autonomous drone navigation in unstructured outdoor environments
• Visual-inertial SLAM for accurate state estimation without LiDAR
• Scalable mapping and safe trajectory planning for MAVs

Innovation

• Visual-inertial SLAM for state estimation
• Volumetric occupancy submaps for scalable mapping
• Trajectory anchoring for safe navigation updates