Large-Scale Autonomous Flight With Real-Time Semantic SLAM Under Dense Forest Canopy

  title={Large-Scale Autonomous Flight With Real-Time Semantic SLAM Under Dense Forest Canopy},
  author={Xu Liu and Guilherme V. Nardari and Fernando Cladera Ojeda and Yuezhan Tao and Alex Zhou and Thomas Donnelly and Chao Qu and Steven W. Chen and Roseli Ap. Francelin Romero and Camillo Jose Taylor and Vijay R. Kumar},
  journal={IEEE Robotics and Automation Letters},
Semantic maps represent the environment using a set of semantically meaningful objects. This representation is storage-efficient, less ambiguous, and more informative, thus facilitating large-scale autonomy and the acquisition of actionable information in highly unstructured, GPS-denied environments. In this letter, we propose an integrated system that can perform large-scale autonomous flights and real-time semantic mapping in challenging under-canopy environments. We detect and model tree… 

Figures from this paper

Robust Sensor Fusion for Autonomous UAV Navigation in GPS denied Forest Environment

A robust multi-sensor fusion-based robust navigation method which has failure detection features is proposed to enable safe and reliable autonomous navigation in forest environment and the result shows the capability of autonomous flights in such a challenging environment.

Active Metric-Semantic Mapping by Multiple Aerial Robots

This work proposes an approach to the active metric-semantic mapping problem that enables multiple heterogeneous robots to collaboratively build a map of the environment, and represents the environment using informative but sparse object models.

A real-time dynamic obstacle tracking and mapping system for UAV navigation and collision avoidance with an RGB-D camera

A real-time dynamic obstacle tracking and mapping system for quadcopter obstacle avoidance using an RGB-D camera and the environment-aware trajectory prediction method is proposed based on the Markov chain using the states of tracked dynamic obstacles.

Overleaf Example

This paper develops a planning framework with two parts: one that maximizes planner completeness for a given graph size, and a second that dynamically maximizes graph size subject to computational constraints that is enabled by motion planning graphs that are defined by a single parameter—dispersion.

Recent developments and applications of simultaneous localization and mapping in agriculture

The applications and prospects of SLAM technology in agricultural mapping, agricultural navigation, and precise automatic agriculture are discussed and particular attention has been paid to the SLAM sensors, systems, and algorithms applied in agricultural tasks.

Stronger Together: Air-Ground Robotic Collaboration Using Semantics

In this work, we present an end-to-end heterogeneous multi-robot system framework where ground robots are able to localize, plan, and navigate in a semantic map created in real time by a

Multi-Modal Lidar Dataset for Benchmarking General-Purpose Localization and Mapping Algorithms

Lidar technology has evolved significantly over the last decade, with higher resolution, better accuracy, and lower cost devices available today. In addition, new scanning modalities and novel sensor

CNS Flight Stack for Reproducible, Customizable, and Fully Autonomous Applications

This work presents a freely available, high-level flight stack dubbed CNS Flight Stack that is platform-agnostic through a generalized (embedded) hardware abstraction layer, uses low compute complexity for online use on embedded hardware, and can be extended with other sensor modalities, integrity checks, and mission modules.

Analyzing General-Purpose Deep-Learning Detection and Segmentation Models with Images from a Lidar as a Camera Sensor

This work explores the potential of general-purpose DL perception algorithms, specifically detection and segmentation neural networks, for processing image-like outputs of advanced lidar sensors and shows that with adequate preprocessing, generalpurpose DL models can process these images, opening the door to their usage in environmental conditions where vision sensors present inherent limitations.

Algorithm and System Development for Robotic Micro-Volume Herbicide Spray Towards Precision Weed Management

The software and hardware design of an automatic system for micro-volume herbicide spray using a mobile robot for early-stage weed control is introduced and a binary linear programming-based algorithm to assign nozzles to the candidate line segments for optimal coverage is developed.



SLOAM: Semantic Lidar Odometry and Mapping for Forest Inventory

It is shown that traditional lidar and image based methods fail in the forest environment on both Unmanned Aerial Vehicle (UAV) and hand-carry systems, while this method is more robust, scalable, and automatically generates tree diameter estimations.

VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems

This paper presents a lightweight and real-time visual semantic SLAM framework running on board aerial robotic platforms that combines low-level visual/visual-inertial odometry (VO/VIO) along with geometrical information corresponding to planar surfaces extracted from detected semantic objects.

Robust Object-based SLAM for High-speed Autonomous Navigation

In ROSHAN, objects are represented as ellipsoids and infer their parameters using three sources of information – bounding box detections, image texture, and semantic knowledge – to overcome the observability problem inEllipsoid-based SLAM under common forward-translating vehicle motions.

Search and rescue under the forest canopy using multiple UAVs

A multi-robot system for GPS-denied search and rescue under the forest canopy is presented, and a novel procedure based on cycle consistent multiway matching to recover from incorrect pairwise data associations is proposed.

Stereo Visual Odometry and Semantics based Localization of Aerial Robots in Indoor Environments

This paper proposes a particle filter localization approach, based on stereo visual odometry (VO) and semantic information from indoor environments, for mini-aerial robots and validates it against ground truth and a state of the art visual SLAM approach.

Autonomous aerial navigation using monocular visual‐inertial fusion

It is shown that it is possible to achieve reliable online autonomous navigation using monocular VINS, and the backbone of the system is a highly accurate optimization‐based monocular visual‐inertial state estimator with online initialization and self‐extrinsic calibration.

Probabilistic data association for semantic SLAM

This paper forms an optimization problem over sensor states and semantic landmark positions that integrates metric information, semantic information, and data associations, and decomposes it into two interconnected problems: an estimation of discrete data association and landmark class probabilities, and a continuous optimization over the metric states.

LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping

We propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building.

Fast, autonomous flight in GPS‐denied and cluttered environments

The system design and software architecture of the proposed solution are described and how all the distinct components can be integrated to enable smooth robot operation are showcased.

Utilizing semantic visual landmarks for precise vehicle navigation

Experimental evaluations validate that the injection of semantic information associated with visual landmarks using the proposed gated factor graph framework achieves substantial improvements in accuracy on GPS-denied navigation solutions for large-scale urban scenarios.