Jove
Visualize
Contact Us
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: Feb 22, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

12.3K

Obstacle Recognition Based on Machine Learning for On-Chip LiDAR Sensors in a Cyber-Physical System.

Fernando Castaño1, Gerardo Beruvides2, Rodolfo E Haber3

  • 1Centre for Automation and Robotics, Technical University of Madrid-Spanish National Research Council (UPM-CSIC), Ctra. Campo Real Km. 0.2, Arganda del Rey 28500, Spain. fernando.castano@car.upm-csic.es.

Sensors (Basel, Switzerland)
|September 15, 2017
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Helical Milling of CFRP/Ti6Al4V Stacks Using Nano Fluid Based Minimum Quantity Lubrication (NF-MQL): Investigations on Process Performance and Hole Integrity.

Materials (Basel, Switzerland)·2023
Same author

A Novel Flushing Mechanism to Minimize Roughness and Dimensional Errors during Wire Electric Discharge Machining of Complex Profiles on Inconel 718.

Materials (Basel, Switzerland)·2022
Same author

Needs, Requirements and a Concept of a Tool Condition Monitoring System for the Aerospace Industry.

Sensors (Basel, Switzerland)·2021
Same author

Merit-Based Motion Planning for Autonomous Vehicles in Urban Scenarios.

Sensors (Basel, Switzerland)·2021
Same author

A Grid-Based Framework for Collective Perception in Autonomous Vehicles.

Sensors (Basel, Switzerland)·2021
Same author

Computer Vision System for Welding Inspection of Liquefied Petroleum Gas Pressure Vessels Based on Combined Digital Image Processing and Deep Learning Techniques.

Sensors (Basel, Switzerland)·2020

This study presents an obstacle recognition library for advanced driver-assistance systems, using artificial intelligence methods like neural networks and support vector machines for collision avoidance. The library demonstrated promising accuracy across various weather conditions.

Area of Science:

  • Cyber-physical systems
  • Artificial Intelligence
  • Transportation Engineering

Background:

  • Advanced driver-assistance systems (ADAS) require reliable obstacle detection for collision avoidance.
  • Current systems face challenges in diverse environmental conditions.
  • A robust obstacle recognition library is crucial for enhancing ADAS safety.

Purpose of the Study:

  • To design and evaluate an obstacle recognition library for transportation cyber-physical systems.
  • To integrate virtual light detection and ranging (LiDAR) sensors within a co-simulation framework.
  • To compare the performance of three artificial intelligence (AI) methods for obstacle detection.

Main Methods:

  • Developed a cyber-physical system in SCANeR software, integrating virtual LiDAR sensors.
Keywords:
co-simulation frameworkobstacle recognition libraryon-chip LiDARsensor-in-the-loopvirtual cyber-physical system

Related Experiment Videos

Last Updated: Feb 22, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

12.3K
  • Implemented three AI-based obstacle recognition methods: multi-layer perceptron (MLP) neural network, self-organization map (SOM), and support vector machine (SVM).
  • Utilized a sensory information database from SCANeR for training and testing the AI models.

    • Main Results:

    • The MLP neural network achieved the best accuracy in sunny and foggy conditions.
    • The support vector machine (SVM) performed best in rainy conditions.
    • The self-organized map (SOM) demonstrated superior performance in snowy conditions.

    Conclusions:

    • The developed obstacle recognition library shows promising results for collision avoidance in ADAS.
    • Different AI methods exhibit varying strengths under different weather conditions.
    • The co-simulation framework effectively models and evaluates sensor-based AI systems for transportation.