# Connection Scan Algorithm

arXiv: https://arxiv.org/abs/1703.05997 · HTML: https://mlsanity.com/paper/1703.05997/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2017.

## Built on by (most cited first, 5 of 5)

- [Timetable Nodes for Public Transport Network](https://mlsanity.com/paper/2410.15715/) (2024)
- [Adapting Dijkstra for Buffers and Unlimited Transfers](https://mlsanity.com/paper/2603.11729/) (2026)
- [Early Pruning for Public Transport Routing](https://mlsanity.com/paper/2603.12592/) (2026)
- [TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation](https://mlsanity.com/paper/2605.22355/) (2026)
- [LegalFarePlan: A Label-Setting Framework for Fare-Transparent Urban Rail Route Planning under Non-Additive Fare Rules](https://mlsanity.com/paper/2607.09755/) (2026)

## Abstract (arXiv)

We introduce the Connection Scan Algorithm (CSA) to efficiently answer queries to timetable information systems. The input consists, in the simplest setting, of a source position and a desired target position. The output consist is a sequence of vehicles such as trains or buses that a traveler should take to get from the source to the target. We study several problem variations such as the earliest arrival and profile problems. We present algorithm variants that only optimize the arrival time or additionally optimize the number of transfers in the Pareto sense. An advantage of CSA is that is can easily adjust to changes in the timetable, allowing the easy incorporation of known vehicle delays. We additionally introduce the Minimum Expected Arrival Time (MEAT) problem to handle possible, uncertain, future vehicle delays. We present a solution to the MEAT problem that is based upon CSA. Finally, we extend CSA using the multilevel overlay paradigm to answer complex queries on nation-wide integrated timetables with trains and buses.