Article
Vision Object-Oriented Augmented Sampling-Based
Autonomous Navigation for Micro Aerial Vehicles
Xishuang Zhao
1
, Jingzheng Chong
1
, Xiaohan Qi
1
and Zhihua Yang
1,2,
*
Citation: Zhao, X.; Chong, J.; Qi, X.;
Yang, Z. Vision Object-Oriented
Augmented Sampling-Based
Autonomous Navigation for Micro
Aerial Vehicles. Drones 2021, 5, 107.
https://doi.org/10.3390/
drones5040107
Academic Editor: George
Nikolakopoulos
Received: 14 August 2021
Accepted: 23 September 2021
Published: 30 September 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Communication Engineering Research Center, Harbin Institute of Technology, Shenzhen 518000, China;
19s152074@stu.hit.edu.cn (X.Z.); chongjz@stu.hit.edu.cn (J.C.); qixiaohan@stu.hit.edu.cn (X.Q.)
2
Pengcheng Lab, Shenzhen 518000, China
* Correspondence: yangzhihua@hit.edu.cn
Abstract:
Autonomous navigation of micro aerial vehicles in unknown environments not only
requires exploring their time-varying surroundings, but also ensuring the complete safety of flights at
all times. The current research addresses estimation of the potential exploration value neglect of safety
issues, especially in situations with a cluttered environment and no prior knowledge. To address
this issue, we propose a vision object-oriented autonomous navigation method for environment
exploration, which develops a B-spline function-based local trajectory re-planning algorithm by
extracting spatial-structure information and selecting temporary target points. The proposed method
is evaluated in a variety of cluttered environments, such as forests, building areas, and mines. The
experimental results show that the proposed autonomous navigation system can effectively complete
the global trajectory, during which an appropriate safe distance could always be maintained from
multiple obstacles in the environment.
Keywords: vision-based navigation; path planning; sampling; B-spline
1. Introduction
Due to their good flexibility, strong maneuverability, easy operation, and unique
viewpoint, micro aerial vehicles (MAVs) are widely used in aerial photography, search-
and-rescue missions [
1
], delivery of goods, and mine exploration [
2
], etc. The autonomous
navigation systems of drones can replace humans to complete some tasks that are dan-
gerous or impractical for humans. The research on autonomous navigation systems can
effectively reduce the complexity of tasks and improve the efficiency of their execution.
It has attracted widespread attention in recent years. For example, in search-and-rescue
missions, an autonomous navigation system can autonomously control the MAV to avoid
obstacles in real time and provide image information with a unique perspective for res-
cue operations.
Typically, an autonomous navigation system consists of four parts: perception, map-
ping, planning and control, in which the planning provides a real-time, safe, collision-free
trajectory for MAVs that meets dynamic constraints. At the present, the research of plan-
ning based on target searches in unknown environments mainly deals with two problems:
the first is obstacle avoidance, while the second is solving the problem of getting stuck
at local minima. This poses a special problem in unexplored or partially unexplored en-
vironments, where only locally optimal or reactive planners will frequently fail to find a
path [
3
]. Different from the known environment, an autonomous navigation system in
partially known or unknown environments will model the environment through sensors
step by step. Since the environmental information is gradually obtained, there is a high
risk of possible collision in the trajectory at the current and next moments. Therefore, the
planning policy should not only gradually complete the task through exploration, but also
have the capability of guaranteeing the safety of the MAV in unknown surroundings.
Drones 2021, 5, 107. https://doi.org/10.3390/drones5040107 https://www.mdpi.com/journal/drones
