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 Concept Videos

Decision Making01:20

Decision Making

217
Decision-making is a fundamental cognitive process that involves evaluating alternatives and selecting among them. This process can range from simple choices, such as deciding what to wear, to complex decisions, like choosing a major in college or a career path. The complexity of the decision often dictates the approach we use, which can be broadly categorized into two types: automatic and controlled decision-making.
Automatic decision-making is fast, intuitive, and relies on gut feelings...
217
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

4.3K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
4.3K
Decision Making: Traditional Method01:14

Decision Making: Traditional Method

4.1K
The process of hypothesis testing based on the traditional method includes calculating the critical value, testing the value of the test statistic using the sample data, and interpreting these values.
First, a specific claim about the population parameter is decided based on the research question and is stated in a simple form. Further, an opposing statement to this claim is also stated. These statements can act as null and alternative hypotheses, out of which a null hypothesis would be a...
4.1K
Reinforcement01:23

Reinforcement

328
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
328
Rolling Resistance: Problem Solving01:17

Rolling Resistance: Problem Solving

437
Rolling resistance, also known as rolling friction, is the force that resists the motion of a rolling object, such as a wheel, tire, or ball, when it moves over a surface. It is caused by the deformation of the object and the surface in contact with each other, as well as other factors like internal friction, hysteresis, and energy losses within the materials. Rolling resistance opposes the object's motion, requiring additional energy to overcome it and maintain movement. In practical...
437
Decision Making: P-value Method01:09

Decision Making: P-value Method

5.6K
The process of hypothesis testing based on the P-value method includes calculating the P- value using the sample data and interpreting it.
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim  is also stated. These statements can act as null and alternative hypotheses:  a null hypothesis would be a neutral statement while the alternative hypothesis can...
5.6K

You might also read

Related Articles

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

Sort by
Same author

Learning-Based Hierarchical Decision-Making Framework for Automatic Driving in Incompletely Connected Traffic Scenarios.

Sensors (Basel, Switzerland)·2024
Same author

Graph Reinforcement Learning-Based Decision-Making Technology for Connected and Autonomous Vehicles: Framework, Review, and Future Trends.

Sensors (Basel, Switzerland)·2023
Same author

Generalized Single-Vehicle-Based Graph Reinforcement Learning for Decision-Making in Autonomous Driving.

Sensors (Basel, Switzerland)·2022
Same author

Review on Vehicle Detection Technology for Unmanned Ground Vehicles.

Sensors (Basel, Switzerland)·2021
Same author

Basophils as a primary inducer of the T helper type 2 immunity in ovalbumin-induced allergic airway inflammation.

Immunology·2014
Same author

Longitudinal variability of phosphorus fractions in sediments of a canyon reservoir due to cascade dam construction: a case study in Lancang River, China.

PloS one·2014

Related Experiment Video

Updated: Sep 6, 2025

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants
06:28

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

6.1K

Multi-Agent Decision-Making Modes in Uncertain Interactive Traffic Scenarios via Graph Convolution-Based Deep

Xin Gao1, Xueyuan Li1, Qi Liu1

  • 1School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100080, China.

Sensors (Basel, Switzerland)
|June 24, 2022
PubMed
Summary

This study introduces a novel reward function matrix for reinforcement learning in autonomous driving, improving decision-making. The proposed graph convolutional network (GCN) methods enhance performance in complex traffic scenarios.

Keywords:
GQNMDGQNconnected autonomous vehiclesmulti-mode decision-makingreward function matrixuncertain highway exit scene

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

562
A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents
06:25

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

445

Related Experiment Videos

Last Updated: Sep 6, 2025

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants
06:28

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

6.1K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

562
A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents
06:25

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

445

Area of Science:

  • Artificial Intelligence
  • Robotics
  • Transportation Engineering

Background:

  • Reinforcement learning (RL) performance in real-world applications is often hindered by insufficient attention to reward function design.
  • Effective reward functions are crucial for training robust decision-making agents, especially in dynamic environments like traffic.

Purpose of the Study:

  • To propose a reward function matrix for training diverse decision-making modes in autonomous vehicles, focusing on incentives and punishments.
  • To enhance vehicle interaction modeling and feature extraction using graph models and graph convolutional networks (GCN).
  • To integrate GCN with deep Q-learning algorithms for developing advanced decision-making models.

Main Methods:

  • A reward function matrix was designed to guide training based on decision-making styles, incentives, and punishments.
  • Traffic scenes were modeled using graph structures, and graph convolutional networks (GCN) were employed for feature extraction.
  • GCN was combined with deep Q-learning and multi-step double deep Q-learning to create Graph Convolutional Deep Q-Network (GQN) and Multi-step Double Graph Convolutional Deep Q-Network (MDGQN) models.

Main Results:

  • The proposed reward function matrix demonstrated superiority over baseline methods in simulations.
  • Trained decision-making modes successfully met various driving requirements, including task completion, safety, comfort, and efficiency, by adjusting reward weights.
  • MDGQN-trained models exhibited superior performance compared to GQN models in uncertain highway exit scenarios.

Conclusions:

  • The developed reward function matrix and GCN-based approaches significantly improve reinforcement learning for autonomous driving decision-making.
  • The flexibility of the reward function matrix allows for customization to meet diverse driving needs.
  • MDGQN offers enhanced robustness and performance in complex and uncertain driving conditions.