ECE Research Seminar – Friday, November 15, 12-1 pm
November 11, 2024
Please join us for our November 2024 ECE Research Seminar
November 15, 2024, Friday, 12:00 – 1:00 pm, Simrall 104
https://msstate.webex.com/msstate/j.php?MTID=m5db6c54e66e2e141a6995f384c9d0447
Optimizing Robot Navigation, Mapping and Motion Planning:
Integrating Bio-Inspired Strategies and Human Interaction in Graph-Based Systems
Timothy Sellers | tej97@msstate.edu
Abstract: Robotic path planning plays a vital role in advancing autonomous systems, greatly impacting various sectors of society by enabling efficient navigation, safety, and task completion in dynamic environments. Over recent years, it has facilitated the development of technologies across industries, supporting growth in fields like logistics, healthcare, and urban infrastructure by improving the capabilities of autonomous robots. Graph-based path planning methods leverage the principles of graph theory to provide structure, precision, and robustness in navigation. By connecting nodes and constructing optimal paths, these methods ensure reliable and efficient route planning, even in unpredictable and complex environments. Graph-based approaches excel in defining clear navigational frameworks, offering consistency and dependability crucial for autonomous navigation. Complementing this, bio-inspired algorithms in path planning are shaped by natural processes, enabling efficient, adaptable responses to environmental challenges. By mimicking phenomena like the branching paths of lightning or the structural integrity of spider webs, these algorithms achieve computational efficiencies that make them ideal for dynamic settings where adaptability is essential. To address the limitations of autonomy in dynamic environments, we propose a Human-Autonomy Teaming (HAT) framework specifically designed to enhance safe and efficient path planning in complex settings. Central to our approach is a hybrid graph system that integrates the Generalized Voronoi Diagram (GVD) with spatio-temporal graphs, combining human feedback with key environmental factors to adaptively navigate complex spaces. Additionally, our improved Node Selection Algorithm (iNSA), supported by revised Grey Wolf Optimization (rGWO), enhances adaptability, while an obstacle tracking model provides predictive data, further increasing system efficiency. By involving human input at critical points, such as setting waypoints and responding to unexpected changes, our framework achieves a balanced, resilient approach to navigation in real-world applications. This research underscores the importance of integrating human insight within autonomous systems, providing a pathway toward safer and more effective navigation strategies. By combining advanced algorithmic approaches with Human-Autonomy Teaming, our framework advances robotic path planning, enhancing adaptability, safety, and reliability in complex environments.
Timothy Sellers received the B.S. degree in Robotics and Automation Technology and Applied Science in Electro-Mechanical Engineering from the Alcorn State University, Lorman, MS, USA in 2020. He is currently pursuing a Ph.D. degree in the Department of Electrical and Computer Engineering at Mississippi State University, under the supervision of Dr. Chaomin Luo. His research interests include robotics, autonomous systems, navigation, nature-inspired intelligence, and machine learning.
* For further information contact: Dr. Jenny Du | du@ece.msstate.edu | 5-2035
For WebEx access, scan the QR code
The Department of Electrical and Computer Engineering at Mississippi State University consists of 27 faculty members (including seven endowed professors), seven professional staff, and over 700 undergraduate and graduate students, with approximately 100 being at the Ph.D. level. With a research expenditure of over $14.24 million, the department houses the largest High Voltage Laboratory among North American universities.