Issa Hanou

Building 28

Office 4.East.180

Van Maurik Broekmanweg 6

Delft, The Netherlands

As a PhD student in the RAIL Lab, I work with the Dutch railway companies NS and ProRail to look at the logistics involved in maintaining the rolling stock outside the runtimes in the timetable. In my work, I apply AI planning to solve real-world railway operation problems and use insights of these problems to develop new methods for AI planning. Besides planning, I am interested in program synthesis and neuro-symbolic AI.

Previous to starting my PhD position, I received both my bachelor’s and master’s degrees from TU Delft. During my studies, I was a TA for several courses within the bachelor’s program as well.

selected publications

2024

ICAPS

Replanning in Advance for Instant Delay Recovery in Multi-Agent Applications: Rerouting Trains in a Railway Hub

Issa Hanou*, Devin Wild Thomas*, Wheeler Ruml, and Mathijs De Weerdt

In Proceedings of the Thirty-Fourth International Conference on Automated Planning and Scheduling, 2024

Abs HTML PDF Code Poster

Train routing is sensitive to delays that occur in the network. When a train is delayed, it is imperative that a new plan be found quickly, or else other trains may need to be stopped to ensure safety, potentially causing cascading delays. In this paper, we consider this class of multi-agent planning problems, which we call Multi-Agent Execution Delay Replanning. We show that these can be solved by reducing the problem to an any-start-time safe interval path planning problem. When an agent has an any-start-time plan, it can react to a delay by simply looking up the precomputed plan for the delayed start time. We identify crucial real-world problem characteristics like the agent’s speed, size, and safety envelope, and extend the any-start-time planning to account for them. Experimental results on real-world train networks show that any-start-time plans are compact and can be computed in reasonable time while enabling agents to instantly recover a safe plan.

2023

ICAPS

Moving Trains Like Pebbles: a Feasibility Study on Tree Yards

Issa Hanou, Jesse Mulderij, and Mathijs De Weerdt

In Proceedings of the Thirty-Third International Conference on Automated Planning and Scheduling, 2023

Abs HTML PDF Supp Poster

The Train Unit Shunting Problem concerns the parking of trains outside their scheduled use on so-called shunting yards. This is an NP-hard problem, and the current algorithm used by the Netherlands Railways cannot detect whether an instance is infeasible. So, infeasible instances can cause needlessly long computation times. Therefore, this paper fills the gap by providing novel approaches to determine the feasibility. For this, the Pebble Motion problem is considered which moves pebbles from their starting node to their goal node in the graph, such that no two pebbles occupy a node at the same time. A variant of the Pebble Motion problem is proposed to model the Train Unit Shunting Problem, where train units are represented by pebbles and the arrival and departure of train unit combinations are also included. This paper specifically looks at dead-end track shunting yards, as they can be abstractly represented by trees, such that trains arrive and depart at the root node. Furthermore, trains cannot be reallocated between arrival and departure in the tree, since reallocation in practice is a very costly process as moves need to be performed by a small set of drivers. The conditions for realizing the departure order of trains are studied, and an efficient method to (partially) determine the feasibility of problem instances is given, which can find the minimal number of tracks required to park the trains. Furthermore, a special case with tracks of length two is shown to be polynomially solvable, while another subset of problem instances with tracks of length six or more is demonstrated to be NP-complete.

news

Apr 9, 2025	Last week, I attended the 11th International Conference on Railway Operations Modeling and Analysis 2025, or RailDresden. I presented a poster on our ongoing work applying Multi-Agent Pathfinding to Railway Routing and had many interesting discussions about these algorithms and the complexity of the Train Unit Shunting Problem for passenger trains.
Jan 17, 2025	I presented work by our RAIL Lab at the TU Delft AI & Mobility Day during the Dies Natalis week.
Dec 21, 2024	Nazariy Lonyuk defended his MSc thesis on Train Unit Shunting and Servicing as an Automated Planning problem.
Nov 20, 2024	I attended the BNAIC/BeNeLearn conference in Utrecht, where I presented our paper “Replanning in Advance for Instant Delay Recovery in Multi-Agent Applications: Rerouting Trains in a Railway Hub” again and I also presented ongoing work on generalized landmarks with a poster. Great to see some people again from the local community and also meet some new faces!
Sep 23, 2024	I gave my first lecture on AI planning!
Sep 12, 2024	I attended the AI4RAILS workshop at the Optimization and Decision Science conference, where I presented our paper “Replanning in Advance for Instant Delay Recovery in Multi-Agent Applications: Rerouting Trains in a Railway Hub” again and Mathijs presented our joint work on Multi-Agent Path Finding for Train Shunting. It was a very interesting conference and great to meet so many people working on improving railway operations with AI!
Jun 25, 2024	AI PhD poster day 2024
Jun 6, 2024	I attended the ICAPS2024 conference and summer school and presented our paper called “Replanning in Advance for Instant Delay Recovery in Multi-Agent Applications: Rerouting Trains in a Railway Hub” written together with Devin Wild Thomas, Wheeler Ruml and Mathijs de Weerdt.
Apr 18, 2024	I attended the Transport Research Arena in Dublin.
Feb 12, 2024	Our paper “Replanning in Advance for Instant Delay Recovery in Multi-Agent Applications: Rerouting Trains in a Railway Hub” together with Devin Wild Thomas, Wheeler Ruml and Mathijs de Weerdt was accepted at the International Conference on Automated Planning and Scheduling (ICAPS24).