1. Home page
  2. Search

Optimal Motion Planning in 3D Workspaces: Integrating a Panel-Method-Based Motion Planner with Continuous Deep Reinforcement Learning

This item is provided by the institution :
National Technical University of Athens   

Repository :
Digital Library of National Technical University of Athens | Dspace@NTUA   

see the original item page
in the repository's web site and access all digital files if the item*



Optimal Motion Planning in 3D Workspaces: Integrating a Panel-Method-Based Motion Planner with Continuous Deep Reinforcement Learning (EN)
Μαλλιαρόπουλος Κατσίμης, Μάριος (EL)
Malliaropoulos Katsimis, Marios (EN)
Παπαδόπουλος, Ευάγγελος (EL)
ntua (EL)
Κυριακόπουλος, Κώστας (EL)
Αντωνιάδης, Ιωάννης (EL)
Kyriakopoulos, Kostas (EN)
bachelorThesis
2023-07-01
2023-08-23T07:22:13Z
This diploma thesis proposes a novel and proven correct reactive method for planning three-dimensional optimal motion in complex environments. By combining fluid flow equations, optimal control theory, and deep reinforcement learning techniques, this study offers an interdisciplinary and unique approach, effectively merging positive attributes from different scientific fields. The method models the 3D motion planning problem by solving streamlines of the potential fluid flow, enabling the proper handling of various terrain types. This is achieved through the discretization of the geometry into surface panels, while the safety criteria are ensured via a set of von-Neumann boundary conditions. The proposed fluid-based planner guarantees a continuous-time, natural-looking, stable and safe solution for the motion planning problem with Artificial Harmonic Potential Fields (AHPFs). Furthermore, this thesis presents a model-based reinforcement learning algorithm for learning the optimal non-linear control in continuous time and action space with respect to an infinite horizon cost function. The algorithm utilizes an actor-critic scheme based on policy iteration, to successively approximate the optimal solution of the Hamilton-Jacobi-Bellman equation. This way, the optimal robot motion is obtained by iteratively updating the fluid flow parameters (i.e., the controller parameters) in a deterministic manner. The proposed method demonstrates fast convergence and outperforms widely used methods such as the RRT*, highlighting its contribution to the field of 3D optimal motion planning. (EN)
3D Σχεδιασμός Πορείας (EL)
Μηχανική των Ρευστών (EL)
Ρομποτική (EL)
Ενισχυτική Μάθηση (EL)
Βέλτιστος Έλεγχος Συστημάτων (EL)
Fluid Mechanics (EN)
3D Motion Planning (EN)
Optimal Control Systems (EN)
Deep Reinforcement Learning (EN)
Robotics (EN)
English
Control Systems Lab (EL)
Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Μηχανολόγων Μηχανικών (EL)
Αναφορά Δημιουργού - Μη Εμπορική Χρήση - Παρόμοια Διανομή 3.0 Ελλάδα
National Technical University of Athens
Digital Library of National Technical University of Athens | Dspace@NTUA
Κεντρική Βιβλιοθήκη Ε.Μ.Π.
Ιδρυματικό Αποθετήριο
Διπλωματικές Εργασίες



*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)