Jove
Visualize
Contact Us

Related Concept Videos

Absolute Motion Analysis- General Plane Motion01:24

Absolute Motion Analysis- General Plane Motion

364
Visualize a drone, with its propellers spinning rapidly, hovering mid-air. The fascinating movements and operations of this drone can be comprehended by applying the principle of general plane motion.
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the...
364

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Deep Learning-Based NMPC for Local Motion Planning of Last-Mile Delivery Robot.

Sensors (Basel, Switzerland)·2022
Same author

Transfer Learning Based Semantic Segmentation for 3D Object Detection from Point Cloud.

Sensors (Basel, Switzerland)·2021
Same author

An End-to-End Deep Reinforcement Learning-Based Intelligent Agent Capable of Autonomous Exploration in Unknown Environments.

Sensors (Basel, Switzerland)·2018
See all related articles
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Nov 7, 2025

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect
09:00

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect

Published on: December 19, 2016

14.9K

Deep Reinforcement Learning for End-to-End Local Motion Planning of Autonomous Aerial Robots in Unknown Outdoor

Oualid Doukhi1, Deok-Jin Lee2

  • 1Center for Artificial Intelligence & Autonomous Systems, Kunsan National University, 558 Daehak-ro, Naun 2(i)-dong, Gunsan 54150, Jeollabuk-do, Korea.

Sensors (Basel, Switzerland)
|April 30, 2021
PubMed
Summary

This study introduces a new method for autonomous navigation in micro aerial vehicles (MAVs) using reinforcement learning. The system enables MAVs to avoid obstacles and reach goals in GPS-denied areas without mapping.

Keywords:
autonomous navigationcollision-freedeep reinforcement learningunmanned aerial vehicle

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.5K
Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

404

Related Experiment Videos

Last Updated: Nov 7, 2025

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect
09:00

Insect-controlled Robot: A Mobile Robot Platform to Evaluate the Odor-tracking Capability of an Insect

Published on: December 19, 2016

14.9K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.5K
Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

404

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Autonomous Systems

Background:

  • Autonomous navigation in dynamic environments is challenging for robotics, especially for micro aerial vehicles (MAVs) with limited resources.
  • Existing methods often require mapping and path planning, which are difficult for MAVs in GPS-denied settings.

Purpose of the Study:

  • To develop a novel approach for autonomous navigation and collision avoidance in MAVs using reinforcement learning.
  • To enable MAVs to reach a goal location in GPS-denied environments without prior mapping or path planning.

Main Methods:

  • An actor-critic-based reinforcement learning technique was employed to train the MAV in a Gazebo simulator.
  • The system directly maps the MAV's state and laser scan data to continuous motion control for point-goal navigation.
  • The trained policy was validated through extensive simulations and real-time experiments, comparing it with nonlinear model predictive control.

Main Results:

  • The reinforcement learning policy enabled collision-free flight in real-world scenarios after training solely in a 3D simulator.
  • The system demonstrated effective generalization to new, unseen environments and robustness against localization noise.
  • The approach successfully planned smooth forward linear velocity and heading rates for safe navigation and goal achievement.

Conclusions:

  • The proposed actor-critic reinforcement learning approach provides an effective solution for autonomous navigation and collision avoidance in MAVs.
  • The method overcomes limitations of traditional approaches by eliminating the need for mapping and path planning in GPS-denied environments.
  • The system's performance in simulations and real-world experiments highlights its potential for practical MAV applications.