Georgia Institute of Technology
A Scalable Solution to Lifelong Multi-Agent Path Planning
Abstract
dc:description.abstractThis thesis investigates the challenges of real-time operation and scalability in Multi-Agent Pickup and Delivery (MAPD) systems, which are critical for applications like warehouse automation and autonomous fleet management. It introduces two novel algorithms, Adaptive Task Token Framework (ATTF) and Neural ATTF, designed to handle dynamic environments with efficient task allocation and collision-free path planning. The proposed methods are evaluated against leading MAPD algorithms and demonstrated in a real-world case study within an automotive manufacturing factory, highlighting their effectiveness in optimizing robot coordination and system performance.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Biomedical Engineering (Joint GT/Emory Department)
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shah, Kushal Jignesh
- Advisor dc:contributor.advisor
-
- Choi, Seung-Kyum
- Committee members dc:contributor.committeemember
-
- Zhao, Ye
- Jiao, Roger
Subjects
dc:subject × 3Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/81496