Mbadiwe Samuel Benyeogor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Mbadiwe Samuel Benyeogor has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Kosisochukwu Nnoli
2 shared publicationsOladayo Olakanmi
2 shared publications- Abdelaaziz Hessane
Moulay Ismail University of Meknes
1 shared publication - Adeboye Olatunbosun
Department of Electrical and Electronic Engineering, Faculty of Technology, University of Ibadan, Ibadan, Nigeria
1 shared publication - Daniel S. Hong
Department of Electrical and Computer Engineering, Michigan Technological University, Houghton, MI 49931, USA
1 shared publication Eric Gratton
1 shared publication
Latest Publications
- Open Access
A Self-Balancing Tandem-Wheel Mobile Robotic System Using Differential Propeller Thrust for Active Roll Stabilization
Maintaining upright stability in tandem-wheel robotic systems is particularly challenging during stationary and low-speed operation, where steering-induced stabilization and gyroscopic effects become limited. Also, alternative mechanisms such as reaction wheels, control-moment gyroscopes, and movable balancing masses can increase mass and mechanical complexity. To address these limitations, this paper proposes an elevated, vectored differential-propeller-thrust approach for active roll stabilization and presents the design, prototyping, and experimental validation of a self-balancing tandem-wheel mobile robotic system employing the proposed principle. Two laterally oriented ducted propeller fans are mounted above the vehicle’s center of mass to increase the available roll-moment arm, while thrust vectoring provides an additional contribution to the corrective rolling moment. The system integrates a perpendicular drivetrain, front-wheel steering mechanism, inertial sensing, wireless communication, and a real-time proportional–integral–derivative (PID) controller utilizing direct gyroscope roll-rate feedback. The system is characterized through geometry-based roll-moment and dynamic analyses, including open-loop pole analysis and a Routh–Hurwitz assessment of the PID-controlled roll dynamics. A Python-based supervisory interface provides wireless command generation, real-time telemetry visualization, and data logging. Experimental evaluation includes static stability, dynamic roll-reference tracking, and variable-speed driving-performance tests. The analytical results identify an open-loop unstable upright equilibrium and reveal the mechanical and actuator parameter conditions for local asymptotic stability under PID-controlled differential thrust. The results of the experiments demonstrate effective upright stabilization, accurate roll-reference tracking, smooth differential-thrust allocation, and reliable attitude regulation during stationary and low-speed operation. The principal contribution is the development and experimental demonstration of an elevated, vectored differential-thrust stabilization architecture for active roll control of a slender tandem-wheel robotic platform, providing a foundation for further development of dynamically stabilized single-track robotic systems.
Open AccessA Self-Balancing Tandem-Wheel Mobile Robotic System Using Differential Propeller Thrust for Active Roll Stabilization
Maintaining upright stability in tandem-wheel robotic systems is particularly challenging during stationary and low-speed operation, where steering-induced stabilization and gyroscopic effects become limited. Also, alternative mechanisms such as reaction wheels, control-moment gyroscopes, and movable balancing masses can increase mass and mechanical complexity. To address these limitations, this paper proposes an elevated, vectored differential-propeller-thrust approach for active roll stabilization and presents the design, prototyping, and experimental validation of a self-balancing tandem-wheel mobile robotic system employing the proposed principle. Two laterally oriented ducted propeller fans are mounted above the vehicle’s center of mass to increase the available roll-moment arm, while thrust vectoring provides an additional contribution to the corrective rolling moment. The system integrates a perpendicular drivetrain, front-wheel steering mechanism, inertial sensing, wireless communication, and a real-time proportional–integral–derivative (PID) controller utilizing direct gyroscope roll-rate feedback. The system is characterized through geometry-based roll-moment and dynamic analyses, including open-loop pole analysis and a Routh–Hurwitz assessment of the PID-controlled roll dynamics. A Python-based supervisory interface provides wireless command generation, real-time telemetry visualization, and data logging. Experimental evaluation includes static stability, dynamic roll-reference tracking, and variable-speed driving-performance tests. The analytical results identify an open-loop unstable upright equilibrium and reveal the mechanical and actuator parameter conditions for local asymptotic stability under PID-controlled differential thrust. The results of the experiments demonstrate effective upright stabilization, accurate roll-reference tracking, smooth differential-thrust allocation, and reliable attitude regulation during stationary and low-speed operation. The principal contribution is the development and experimental demonstration of an elevated, vectored differential-thrust stabilization architecture for active roll control of a slender tandem-wheel robotic platform, providing a foundation for further development of dynamically stabilized single-track robotic systems.
- Open Access
- 27 June 2024
- Published by MDPI AG in Sustainability
- Vol. 16 (13) , 5505
Meta-Learning Guided Weight Optimization for Enhanced Solar Radiation Forecasting and Sustainable Energy Management with VotingRegressor
Solar radiation prediction plays a crucial role in renewable energy management, impacting various decision-making processes aimed at optimizing the utilization of solar resources and promoting sustainability. Ensemble regression methods, notably VotingRegressor, have emerged as promising tools for accurate solar radiation forecasting. By integrating predictions from multiple base estimators, ensemble methods have the potential to capture intricate patterns inherent in solar radiation data. However, achieving optimal predictive performance with ensemble methods heavily relies on the careful weighting assigned to each base estimator, presenting a significant challenge. In this study, a novel approach is presented to enhance solar radiation prediction by utilizing meta-learning techniques to optimize the weighting mechanism in the VotingRegressor ensemble. Meta-learning, a subfield of machine learning focusing on learning algorithms across different tasks, provides a systematic framework for learning to learn. This enables models to adapt and generalize more effectively to new datasets and tasks. Our proposed methodology demonstrated significant improvements, with the VotingRegressor with meta-learning techniques achieving an RMSE of 8.7343, an MAE of 5.42145, and an R² of 0.991913. These results mitigate the need for manual weight tuning and improve the adaptability of the VotingRegressor to varying solar radiation conditions, ultimately contributing to the sustainability of renewable energy systems. The methodology involves a comprehensive exploration of meta-learning techniques, encompassing gradient-based optimization, reinforcement learning, and Bayesian optimization.
- 27 June 2024
- Published by MDPI AG in Sustainability
- Vol. 16 (13) , 5505
Open AccessMeta-Learning Guided Weight Optimization for Enhanced Solar Radiation Forecasting and Sustainable Energy Management with VotingRegressor
Solar radiation prediction plays a crucial role in renewable energy management, impacting various decision-making processes aimed at optimizing the utilization of solar resources and promoting sustainability. Ensemble regression methods, notably VotingRegressor, have emerged as promising tools for accurate solar radiation forecasting. By integrating predictions from multiple base estimators, ensemble methods have the potential to capture intricate patterns inherent in solar radiation data. However, achieving optimal predictive performance with ensemble methods heavily relies on the careful weighting assigned to each base estimator, presenting a significant challenge. In this study, a novel approach is presented to enhance solar radiation prediction by utilizing meta-learning techniques to optimize the weighting mechanism in the VotingRegressor ensemble. Meta-learning, a subfield of machine learning focusing on learning algorithms across different tasks, provides a systematic framework for learning to learn. This enables models to adapt and generalize more effectively to new datasets and tasks. Our proposed methodology demonstrated significant improvements, with the VotingRegressor with meta-learning techniques achieving an RMSE of 8.7343, an MAE of 5.42145, and an R² of 0.991913. These results mitigate the need for manual weight tuning and improve the adaptability of the VotingRegressor to varying solar radiation conditions, ultimately contributing to the sustainability of renewable energy systems. The methodology involves a comprehensive exploration of meta-learning techniques, encompassing gradient-based optimization, reinforcement learning, and Bayesian optimization.
- Open Access
- 16 March 2021
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Creative Technologies
- Vol. 8 (26)
Edu-Rover: Application of Unmanned Vehicle Systems for Robotics and STEM Education in Nigeria
- 16 March 2021
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Creative Technologies
- Vol. 8 (26)
Open AccessEdu-Rover: Application of Unmanned Vehicle Systems for Robotics and STEM Education in Nigeria
- Open Access
- 6 February 2020
- Published by European Open Science in European Journal of Engineering and Technology Research
- Vol. 5 (2) , 178-182
Airborne System for Pipeline Surveillance Using an Unmanned Aerial Vehicle
Our work involves the development of a quadcopter Unmanned Aerial Vehicle (UAV) system with remote sensors onboard for monitoring oil and gas pipelines. Two Liquefied Petroleum Gas (LPG) sensors were used for LPG gas leakage detection. The Multiwii software is used to control, track and simulate the 3D motion of the UAV in flight. Using this device, experimental data from field tests were analyzed with MATLAB. Results reveal that the developed system has performed as expected. Thus, our device can be used to enhance asset monitoring and operational safety in the oil industry.
- 6 February 2020
- Published by European Open Science in European Journal of Engineering and Technology Research
- Vol. 5 (2) , 178-182
Open AccessAirborne System for Pipeline Surveillance Using an Unmanned Aerial Vehicle
Our work involves the development of a quadcopter Unmanned Aerial Vehicle (UAV) system with remote sensors onboard for monitoring oil and gas pipelines. Two Liquefied Petroleum Gas (LPG) sensors were used for LPG gas leakage detection. The Multiwii software is used to control, track and simulate the 3D motion of the UAV in flight. Using this device, experimental data from field tests were analyzed with MATLAB. Results reveal that the developed system has performed as expected. Thus, our device can be used to enhance asset monitoring and operational safety in the oil industry.
- 1 March 2019
- Published by Elsevier in Internet of Things
- Vol. 5, 97-115
Internet based tele-autonomous vehicle system with beyond line-of-sight capability for remote sensing and monitoring
- 1 March 2019
- Published by Elsevier in Internet of Things
- Vol. 5, 97-115
Internet based tele-autonomous vehicle system with beyond line-of-sight capability for remote sensing and monitoring
- Open Access
- 13 July 2018
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Context-aware Systems and Applications
- Vol. "0"
An Algorithmic Approach to Adapting Edge-based Devices for Autonomous Robotic Navigation
- 13 July 2018
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Context-aware Systems and Applications
- Vol. "0"
Open AccessAn Algorithmic Approach to Adapting Edge-based Devices for Autonomous Robotic Navigation