Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 17 of 17 for “"MAPF"”.
-
LEARNING SCALABLE POLICIES FOR COOPERATIVE AND MIXED MULTI-AGENT SYSTEMS
… and robotics. Multi-Agent Path Finding (MAPF) is a representative mixed MAS problem that becomes increasingly challenging at large scales due to limited observability, high agent density, and complex environments. This thesis tackles these challenges by integrating traditional …
-
Goal Distribution in Conflict-Based Search for Multi-Agent Pathfinding and its Implications to Monte-Carlo Sampling
… framework for solving MultiAgent Path Finding (MAPF). At its high-level, CBS searches over a Constraint Tree (CT). A body of publications looked at various approaches to perform the high-level search and find a goal (conflict-free) node efficiently. The performance of these variants is dependent …
-
Multi-Agent Navigation: A Study of CBS and CBSS on Turtlebots
Multi-Agent Pathfinding (MAPF) and its generalized counterpart, Multi-Agent Combinatorial Pathfinding (MCPF), are critical problems in robotics where multiple agents must navigate efficiently while avoiding collisions with static obstacles or with other agents. MAPF focuses on planning …
-
Multi-Agent Pathfinding in Mixed Discrete-Continuous Time and Space
In the multi-agent pathfinding (MAPF) problem, agents must move from their current locations to their individual destinations while avoiding collisions. Ideally, agents move to their destinations as quickly and efficiently as possible. MAPF has many real-world applications such as navigation, …
-
k-robust CBS with continuous time for multi-robot coordination
… applications. Many MultiAgent Path Finding (MAPF) algorithms have been proven to be successful in addressing this challenge. Nevertheless, some MAPF algorithms exhibit shortcomings when handling high-level abstractions, neglecting real-life aspects, consequently leading to failures in live …
-
Probabilistically Robust Continuous-time Multi-Agent Path Finding Dynamic Risk Allocation and Chance-Constrained Planning under Execution Uncertainty
… systems use Multi-Agent Path Finding (MAPF) algorithms to coordinate collision-free routes. In real-world industrial deployments, execution uncertainties such as mechanical variations and friction inevitably cause delays. Current robust MAPF algorithms handle this either through …
-
Adaptive Planning for Robot Teams: Deep Reinforcement Learning in Dynamic Environments
… Networks (GNN) for Multi-Agent Path Finding (MAPF) applications. In this study, the real-world environment is mapped to a topological graph with dynamic edge weights. Various solutions to this problem exist, providing both sub-optimal and optimal solutions. However, a majority of these methods …
-
Multi-agent pathfinding with discrete speeds - and its application for vehicle road networks
… to the multi-agent path-finding problem (MAPF) by extending existing algorithms with optimal and efficient routing for roads with multiple lanes and intersections. It also considers the continuous case, where agents are forbidden from performing actions during a non-discrete interval of …
-
Experimental and numerical study of flow characteristics and segregation in flow enhanced systems
… called the Magnetically Assisted Powder Flow (MAPF) method. In the MAPF, small magnetic particles and powders are placed in a test hopper. A mesh is placed at the bottom of the hopper to hold the magnetic particles while the powder is discharged through the mesh. It is shown that this method …
-
Framework for multi-agent path finding A framework for multi-agent path finding with focus on transport systems
… is desirable to apply multi agent path finding (MAPF) algorithms to vehicles in transport systems, as it has the potential to reduce transit time and fuel consumption. However, the application is hampered by the high level of abstraction that these problems are typically solved at. This work …
-
TEAM-INSPIRED REPRESENTATION LEARNING FOR DECENTRALIZED MULTI-ROBOT COORDINATION
… three stages. First, in multi-agent pathfinding (MAPF), we propose ALPHA, which integrates local observations with learned structural context to mitigate myopic decisions. Second, to overcome behavioral homogeneity caused by parameter sharing, we introduce SYLPH, enabling agents to learn and …
-
Planering och styrning av en flotta autonoma mobila robotar med centraliserad rörelsespårning
… is addressed through a multi agent path finding (MAPF) strategy evaluating a local collision resolver A* (LCRA*). LCRA* is based on the model lifelong priority based search (LPBS) and the benefit of using LCRA* is that it significantly improves computational performance as it does not require …
-
Žemėlapio reprezentacijos įtaka formuotę išlaikančiam agentų judėjimo planavimui /
… representation provides for formation-preserving MAPF is smaller than in single-agent pathfinding. The applicability of each representation is shaped by trade-offs between computation cost and path quality, discussed in detail in the work.
-
Χρήση Αρχιτεκτονικών Transformer και Ενισχυτικής Μάθησης με Μάθηση Μίμησης για το Πρόβλημα της Πολυπρακτορικής Εύρεσης Μονοπατιών
… LSTM, GRU, Transformer για το πρόβλημα του MAPF μέσω μιας απλοποιημένης εκδοχής του PRIMAL. Οι πειραματισμοί μας οδήγησαν στην ανάπτυξη ενός αλγοριθμικού πλαισίου το οποίο χρησιμοποιεί Transformer για τη λήψη αποφάσεων και επικοινωνία από τους πράκτορες μαζί με μάθηση μίμησης, …
-
Delay-tolerant Multi-Agent Path Finding: Delay-tolerant methods for solving multi-agent path finding problems in autonomous systems
… finding problems. There are methods, such as MAPF-POST, which find the delay tolerance of a given schedule and, in some cases, allow agents to be delayed without doing expensive replanning. We propose a modification to the multi-agent path finding algorithm Conflict-based search, which makes …
-
Pathfinding Algorithm Optimization Via Evolution
… and apply HEHA* to Multi-Agent Pathfinding (MAPF) problems. MAPF is the fundamental problem of many robotic and logistic applications, where the main constraint is that all agents can find the shortest paths while not colliding with each other. While the current trend favors the central …
-
Abstraction Hierarchies for Multi-Agent Pathfinding
Multi-Agent Pathfinding is an NP-Complete search problem with a branching factor that is exponential in the number of agents. Because of this exponential feature, it can be difficult to solve optimally using traditional search techniques, even for relatively small problems. Many recent optimal …