How to pick a mobile robot simulator: A quantitative comparison of CoppeliaSim, Gazebo, MORSE and Webots with a focus on accuracy of motion

Farley, A. N.; Wang, Jie; Marshall, Joshua A.

doi:10.1016/j.simpat.2022.102629

Cited by 40 publications

(22 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CoppeliaSim is a robot 3D simulation platform widely used in the fields of robot education, controller design, and reinforcement learning [9]. Compared to other popular robot simulation platforms, CoppeliaSim has highest accuracy in robot motion [10]. Additionally, CoppeliaSim supports the largest number of programming languages, physics engines, and model types.…”

Section: Environmentmentioning

confidence: 99%

Position control of mobile robot based on deep reinforcement learning

Hu,

Chai,

et al. 2024

Second International Conference on Informatics, Networking, and Computing (ICINC 2023)

View full text Add to dashboard Cite

In the field of mobile robot control, the utilization of reinforcement learning methods often faces the challenge of sparse rewards, resulting in suboptimal control performance. This paper proposes an approach that leverages the Diversity is All You Need (DIAYN) framework to dynamically generate reward functions and enhance the policy network weights of reinforcement learning algorithms. A comparative analysis is conducted with traditional reinforcement learning algorithms, namely Deep Deterministic Policy Gradient (DDPG), Deep Q-Network (DQN), and behavior-based robotic and proportional-integral-derivative (BBR_PID) planning control algorithm. The results obtained from the CoppeliaSim simulation experiment demonstrate that, under identical training conditions, the DIAYN-based DDPG algorithm exhibits superior learning capability and achieves faster convergence to optimal actions. Consequently, the mobile robot can reach the target point more efficiently and with greater stability.

show abstract

Section: Environmentmentioning

confidence: 99%

Position control of mobile robot based on deep reinforcement learning

Hu,

Chai,

et al. 2024

Second International Conference on Informatics, Networking, and Computing (ICINC 2023)

View full text Add to dashboard Cite

show abstract

“…CoppeliaSim was chosen since others claimed CoppeliaSim performed relatively better compared to other simulators (e.g., Gazebo) in terms of real time factor, CPU efficiency, physics engine support, sensor accuracy, etc. [13]. Also, CoppeliaSim enabled more realistic and computationally stable modeling of the omni-wheels, essential for properly modeling the dynamics of a ballbot.…”

Section: ) Vr Headset and Joystickmentioning

confidence: 99%

Hands-Free Physical Human-Robot Interaction and Testing for Navigating a Virtual Ballbot

Song¹,

Marin²,

Xiao³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>This is a submitted (IEEE RO-MAN 2023) draft of a paper on the testing of a hands-free human-robot interaction for navigating a ballbot in a virtual environment. In this study, able-bodied users and manual wheelchair users controlled a virtual ballbot using a hands-free (HF) lean-to-steer control concept that uses torso motions. A custom sensor system (i.e., Torso-dynamics Estimation System (TES)) was utilized to measure and convert the dynamics of the rider’s torso motions into commands to provide HF control of the robot. A simulation study was conducted to explore the efficacy of the HF controller compared to a traditional joystick (JS) controller, and whether there were differences in performance by manual wheelchair users (mWCUs), who may have reduced torso function, compared to able-bodied users (ABUs). Twenty test subjects (10 mWCUs + 10 ABUs) used the subject-specific adjusted TES while wearing a virtual reality headset and were asked to navigate a virtual human rider on the ballbot through obstacle courses replicating seven indoor environment zones. </p>

show abstract

“…Farley et al fizeram um estudo comparando resultados simulados para robôs de solo utilizando os simuladores Coppe-liaSim, Gazebo, MORSE e Webots [13]. Os autores comparam o resultado dessa simulac ¸ão com testes práticos, realizados dentro do ambiente do laboratório.…”

Section: Trabalhos Relacionadosunclassified

Desenvolvendo Simulações de Uso de Drones em Cidades Inteligentes

Moraes

Sabino

Hilario

et al. 2022

Anais Estendidos Do XII Simpósio Brasileiro De Engenharia De Sistemas Computacionais (SBESC Estendido 2022)

View full text Add to dashboard Cite

Dada a dificuldade de planejamento de missões para voos de drones nas cidades, devido ao ambiente e aos recursos limitados da aeronave, torna-se necessária a utilização de tecnologias de ambiente de simulação para treinamento e preparo para missões de campo. Com isso, este trabalho tem como objetivo descrever e analisar uma metodologia de desenvolvimento de simulação de voo de drones para o planejamento de missões de campo com um cenário verossímil comparado à realidade em termos de tempo e distância. Ao utilizar os simuladores, foi possível obter um tempo médio de 97,62% de precisão nos testes do ambiente virtual em relação aos testes de campo, apresentando uma verossimilhança alta obtida através dos ajustes realizados entre o Modelo Digital de Superfície e calibração dos sistemas de coordenadas utilizado.

show abstract

How to pick a mobile robot simulator: A quantitative comparison of CoppeliaSim, Gazebo, MORSE and Webots with a focus on accuracy of motion

Cited by 40 publications

References 3 publications

Position control of mobile robot based on deep reinforcement learning

Position control of mobile robot based on deep reinforcement learning

Hands-Free Physical Human-Robot Interaction and Testing for Navigating a Virtual Ballbot

Desenvolvendo Simulações de Uso de Drones em Cidades Inteligentes

Contact Info

Product

Resources

About