Abdel Hakim Drid
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Abdel Hakim Drid has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Daniele Nardi
Sapienza University of Rome
3 shared publications - Imam Barket Ghiloubi
Identification, Command, Control and Communication Laboratory LI3CUB, Mohamed Khider University, Biskra 07000, Algeria
3 shared publications - Vincenzo Suriani
Sapienza University of Rome
3 shared publications - Abderrezzak Debilou
University of Biskra
2 shared publications - Latifa Abdou
Identification, Command, Control and Communication Laboratory LI3CUB, Mohamed Khider University, Biskra 07000, Algeria
2 shared publications - Oussama Lahmar
Identification, Command, Control and Communication Laboratory LI3CUB, Mohamed Khider University, Biskra 07000, Algeria
2 shared publications
Latest Publications
- 3 October 2026
- Published by Springer Nature
- p. 452-465
Rob-LAPI(S)$^2$: Robotic Language-to-Action Planning via Iterative Schema Synthesis- 3 October 2026
- Published by Springer Nature
- p. 452-465
Rob-LAPI(S)$^2$: Robotic Language-to-Action Planning via Iterative Schema Synthesis- 2 September 2026
- Published by Springer Nature
- p. 261-275
Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
- 2 September 2026
- Published by Springer Nature
- p. 261-275
Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
- Open Access
- 7 November 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 118 (1) , 8
YOLOv8-Based Autonomous Ball Detection and Tracking for Rotorcraft UAVs Using Onboard Vision Sensors
Drones equipped with onboard cameras offer promising potential for modern digital media and remote sensing applications. However, effectively tracking moving objects in real time remains a significant challenge. Aerial footage captured by drones often includes complex scenes with dynamic elements such as people, vehicles, and animals. These scenarios may involve large-scale changes in viewing angles, occlusions, and multiple object crossings occurring simultaneously, all of which complicate accurate object detection and tracking. This paper presents an autonomous tracking system that leverages the YOLOv8 algorithm combined with a re-detection mechanism, enabling a quadrotor to effectively detect and track moving objects using only an onboard camera. To regulate the drone’s motion, a PID controller is employed, operating based on the target’s position within the image frame. The proposed system functions independently of external infrastructure such as motion capture systems or GPS. By integrating both positional and appearance-based cues, the system demonstrates high robustness, particularly in challenging environments involving complex scenes and target occlusions. The performance of the optimized controllers was assessed through extensive real-world testing involving various trajectory scenarios to evaluate the system’s effectiveness. Results confirmed consistent and accurate detection and tracking of moving objects across all test cases. Furthermore, the system exhibited robustness against noise, light reflections, and illumination interference, ensuring stable object tracking even when implemented on low-cost computing platforms.
- 7 November 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 118 (1) , 8
Open AccessYOLOv8-Based Autonomous Ball Detection and Tracking for Rotorcraft UAVs Using Onboard Vision Sensors
Drones equipped with onboard cameras offer promising potential for modern digital media and remote sensing applications. However, effectively tracking moving objects in real time remains a significant challenge. Aerial footage captured by drones often includes complex scenes with dynamic elements such as people, vehicles, and animals. These scenarios may involve large-scale changes in viewing angles, occlusions, and multiple object crossings occurring simultaneously, all of which complicate accurate object detection and tracking. This paper presents an autonomous tracking system that leverages the YOLOv8 algorithm combined with a re-detection mechanism, enabling a quadrotor to effectively detect and track moving objects using only an onboard camera. To regulate the drone’s motion, a PID controller is employed, operating based on the target’s position within the image frame. The proposed system functions independently of external infrastructure such as motion capture systems or GPS. By integrating both positional and appearance-based cues, the system demonstrates high robustness, particularly in challenging environments involving complex scenes and target occlusions. The performance of the optimized controllers was assessed through extensive real-world testing involving various trajectory scenarios to evaluate the system’s effectiveness. Results confirmed consistent and accurate detection and tracking of moving objects across all test cases. Furthermore, the system exhibited robustness against noise, light reflections, and illumination interference, ensuring stable object tracking even when implemented on low-cost computing platforms.
- Open Access
- 12 September 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 105
Robustness Analysis of LQR-PID Controller Based on PSO and GWO for Quadcopter Attitude Stabilization
The robust control of quadcopters is essential for maintaining stability and performance in dynamic environments. This paper examines the effectiveness of Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) for tuning LQR-PID controllers tailored for a quadcopter constrained to rotational degrees of freedom, aiming to enhance attitude stabilization and perform a comparative robustness analysis under various disturbances. Using PSO and GWO to optimize the LQR controller’s Q and R matrices, the study minimizes a cost function based on attitude error and control effort. The optimized controllers are evaluated in a Simulink environment with external perturbation forces; noise perturbations and sudden impulse disturbances are introduced via feedback vector perturbations to simulate real-world operational challenges. The results reveal distinct robustness characteristics: the PSO-optimized controller achieves faster convergence with higher sensitivity to disturbances, while the GWO-optimized controller performs better under extreme parameter variations. By providing a detailed comparison of these optimization techniques, the study offers valuable insights into selecting the most suitable method for robust and reliable quadcopter attitude control.
- 12 September 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 105
Open AccessRobustness Analysis of LQR-PID Controller Based on PSO and GWO for Quadcopter Attitude Stabilization
The robust control of quadcopters is essential for maintaining stability and performance in dynamic environments. This paper examines the effectiveness of Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) for tuning LQR-PID controllers tailored for a quadcopter constrained to rotational degrees of freedom, aiming to enhance attitude stabilization and perform a comparative robustness analysis under various disturbances. Using PSO and GWO to optimize the LQR controller’s Q and R matrices, the study minimizes a cost function based on attitude error and control effort. The optimized controllers are evaluated in a Simulink environment with external perturbation forces; noise perturbations and sudden impulse disturbances are introduced via feedback vector perturbations to simulate real-world operational challenges. The results reveal distinct robustness characteristics: the PSO-optimized controller achieves faster convergence with higher sensitivity to disturbances, while the GWO-optimized controller performs better under extreme parameter variations. By providing a detailed comparison of these optimization techniques, the study offers valuable insights into selecting the most suitable method for robust and reliable quadcopter attitude control.
- Open Access
Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
Navigating and understanding complex and unknown environments autonomously demands more than just basic perception and movement from embodied agents. Truly effective exploration requires agents to possess higher-level cognitive abilities, the ability to reason about their surroundings, and make more informed decisions regarding exploration strategies. However, traditional RL approaches struggle to balance efficient exploration and semantic understanding due to limited cognitive capabilities embedded in the small policies for the agents, leading often to human drivers when dealing with semantic exploration. In this paper, we address this challenge by presenting a novel Deep Reinforcement Learning (DRL) architecture that is specifically designed for resource efficient semantic exploration. A key methodological contribution is the integration of a Vision-Language Model (VLM) common-sense through a layered reward function. The VLM query is modeled as a dedicated action, allowing the agent to strategically query the VLM only when deemed necessary for gaining external guidance, thereby conserving resources. This mechanism is combined with a curriculum learning strategy designed to guide learning at different levels of complexity to ensure robust and stable learning. Our experimental evaluation results convincingly demonstrate that our agent achieves significantly enhanced object discovery rates and develops a learned capability to effectively navigate towards semantically rich regions. Furthermore, it also shows a strategic mastery of when to prompt for external environmental information. By demonstrating a practical and scalable method for embedding common-sense semantic reasoning with autonomous agents, this research provides a novel approach to pursuing a fully intelligent and self-guided exploration in robotics.
Open AccessCurriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
Navigating and understanding complex and unknown environments autonomously demands more than just basic perception and movement from embodied agents. Truly effective exploration requires agents to possess higher-level cognitive abilities, the ability to reason about their surroundings, and make more informed decisions regarding exploration strategies. However, traditional RL approaches struggle to balance efficient exploration and semantic understanding due to limited cognitive capabilities embedded in the small policies for the agents, leading often to human drivers when dealing with semantic exploration. In this paper, we address this challenge by presenting a novel Deep Reinforcement Learning (DRL) architecture that is specifically designed for resource efficient semantic exploration. A key methodological contribution is the integration of a Vision-Language Model (VLM) common-sense through a layered reward function. The VLM query is modeled as a dedicated action, allowing the agent to strategically query the VLM only when deemed necessary for gaining external guidance, thereby conserving resources. This mechanism is combined with a curriculum learning strategy designed to guide learning at different levels of complexity to ensure robust and stable learning. Our experimental evaluation results convincingly demonstrate that our agent achieves significantly enhanced object discovery rates and develops a learned capability to effectively navigate towards semantically rich regions. Furthermore, it also shows a strategic mastery of when to prompt for external environmental information. By demonstrating a practical and scalable method for embedding common-sense semantic reasoning with autonomous agents, this research provides a novel approach to pursuing a fully intelligent and self-guided exploration in robotics.
- Open Access
- 16 July 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 93
Quadrotor Trajectory Tracking Under Wind Disturbance Using Backstepping Control Based on Different Optimization Techniques
Enhancing quadrotor control to improve both precision and responsiveness is essential for expanding their deployment in complex and dynamic environments. These aerial vehicles are widely used in applications, such as aerial mapping, delivery, disaster response, and defense, where maintaining stability and accuracy is critical, especially under external disturbances like wind. This paper makes three key contributions. First, it develops a nonlinear mathematical model of a quadrotor and designs a backstepping controller for trajectory tracking. Second, the controller’s parameters are optimized using three nature-inspired algorithms: Gray Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and the Flower Pollination Algorithm (FPA), enabling performance comparisons in terms of their tracking precision and control effort. Third, the robustness of the best-performing optimized controller is evaluated by applying wind disturbances at the simulation level, modeled as external forces acting along the x-axis and summed with the control input. The simulation results highlight the comparative efficiency of the optimization methods and demonstrate the robustness of the selected controller in maintaining stability and accuracy under wind-induced perturbations.
- 16 July 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 93
Open AccessQuadrotor Trajectory Tracking Under Wind Disturbance Using Backstepping Control Based on Different Optimization Techniques
Enhancing quadrotor control to improve both precision and responsiveness is essential for expanding their deployment in complex and dynamic environments. These aerial vehicles are widely used in applications, such as aerial mapping, delivery, disaster response, and defense, where maintaining stability and accuracy is critical, especially under external disturbances like wind. This paper makes three key contributions. First, it develops a nonlinear mathematical model of a quadrotor and designs a backstepping controller for trajectory tracking. Second, the controller’s parameters are optimized using three nature-inspired algorithms: Gray Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and the Flower Pollination Algorithm (FPA), enabling performance comparisons in terms of their tracking precision and control effort. Third, the robustness of the best-performing optimized controller is evaluated by applying wind disturbances at the simulation level, modeled as external forces acting along the x-axis and summed with the control input. The simulation results highlight the comparative efficiency of the optimization methods and demonstrate the robustness of the selected controller in maintaining stability and accuracy under wind-induced perturbations.