Shania Argiliana
Research Subjects
Shania Argiliana has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
Estiyanti Ekawati
1 shared publication- Faqihza Mukhlish
Institut Teknologi Bandung
1 shared publication
Latest Publications
- Open Access
- 14 June 2025
- Published by Universitas Muhammadiyah Yogyakarta in Journal of Robotics and Control (JRC)
- Vol. 6 (4) , 1710-1720
Adaptive Strategies for Dynamic Obstacle Avoidance and Formation Control in Multi-Agent Drone Systems: A Review
Obstacle avoidance in multi-agent systems is a critical area of research driven by advancements in autonomous technology and artificial intelligence. This review examines various approaches to path planning, formation control, and communication architectures, focusing on their effectiveness in static and dynamic environments. The research contribution is a comprehensive analysis of current techniques based on a structured selection process evaluating peer-reviewed studies through computational efficiency, real-time adaptivity, and scalability. The findings highlight the strengths and limitations of classical methods, such as the Improved Artificial Potential Field (IAPF), and modern techniques like Reinforcement Learning (RL) and Model Predictive Control (MPC). Comparative analysis reveals that while these approaches improve adaptivity, they also introduce challenges such as high computational loads, difficulties in large-scale multi-agent coordination, and sensitivity of parameter tuning. Additionally, existing formation control strategies depend highly on stable inter-agent communication, making them vulnerable to delays and failures in decentralized networks. This review identifies key research gaps and suggests future directions, including hybrid RL-MPC formation control, adaptive path planning algorithms, and scalable communication protocols to enhance multi-agent system performance in real-world applications.
- 14 June 2025
- Published by Universitas Muhammadiyah Yogyakarta in Journal of Robotics and Control (JRC)
- Vol. 6 (4) , 1710-1720
Open AccessAdaptive Strategies for Dynamic Obstacle Avoidance and Formation Control in Multi-Agent Drone Systems: A Review
Obstacle avoidance in multi-agent systems is a critical area of research driven by advancements in autonomous technology and artificial intelligence. This review examines various approaches to path planning, formation control, and communication architectures, focusing on their effectiveness in static and dynamic environments. The research contribution is a comprehensive analysis of current techniques based on a structured selection process evaluating peer-reviewed studies through computational efficiency, real-time adaptivity, and scalability. The findings highlight the strengths and limitations of classical methods, such as the Improved Artificial Potential Field (IAPF), and modern techniques like Reinforcement Learning (RL) and Model Predictive Control (MPC). Comparative analysis reveals that while these approaches improve adaptivity, they also introduce challenges such as high computational loads, difficulties in large-scale multi-agent coordination, and sensitivity of parameter tuning. Additionally, existing formation control strategies depend highly on stable inter-agent communication, making them vulnerable to delays and failures in decentralized networks. This review identifies key research gaps and suggests future directions, including hybrid RL-MPC formation control, adaptive path planning algorithms, and scalable communication protocols to enhance multi-agent system performance in real-world applications.