Show last authors
1 The REAKT project (https://reakt.sh/ & https://www.schiene-m-l.de/) aims at developing new mobility concepts to reactivate rural rail lines. This project will evolve around developing an autonomous on-demand rail vehicle to flexibly provide service on single track lines. The **REAKTOR**. A prototype will be build in 1:32 scale, as well as a full scale version for the railway track Malente-Lütjenburg.
2
3 [[image:image-20240912102452-3.jpeg||height="219" width="292"]][[image:image-20240912102840-4.jpeg||height="217" width="264"]]
4
5 //(left) a railbike, the foundation of the upcoming autonomous draisine & (right) a stripped down [[LGB>>https://www.lgb.de/lp/20/willkommen-bei-lgb]] engine in for a 45mm model track.//
6
7 == Overview of topics (WIP) ==
8
9 All solutions should be scalable for both demonstrators!
10
11 ~1. An end-user app and management system for on-demand train service [Maybe split into two topics]
12
13 * App to call a train to a desired location and communicate desired destination
14 * Locations drawn from GNSS and appropriate abstraction in 1:32 scale
15 * Management of multiple trains on a single track line
16 * Schedules for cooperative passenger pick up
17 * Provisions for passenger transfer on open track
18 * Either based on a central or decentralized communication concept
19
20 2. An autonomous train controller with risk analysis using STPA
21
22 * Control of an autonomous passenger train model (conceptually working for both demonstrators)
23 * Capability for passenger transfer on open track (safe docking procedure)
24 * Risk analysis for the controller using STPA
25 * Safe behavior model generation using PASTA?
26 * Assumes preprocessed sensor input and destination determination (see other topics)
27
28 3. AI-based image recognition for autonomous train control [In cooperation with AG Distributed Systems]
29
30 * Sensor processing of a train mounted camera
31 * Obstacle detection at speeds up to 50 km/h
32 * [Optional] Distance measuring using multiple cameras
33
34 4. AI-based sensor processing for autonomous train control [In cooperation with AG Distributed Systems]
35
36 * Sensor processing of train mounted LiDAR or ultrasonic sensor
37 * Obstacle detection at speeds up to 50 km/h
38 * Distance measuring (ultrasonic sensor)
39
40 5. A digital twin for an autonomous on-demand train service [Tight interfacing with other topics]
41
42 * A digital twin for an autonomous passenger train
43 * Monitoring system for the state and location of the vehicle
44 * Remote control capabilities
45 * Monitoring and economic analysis of on-demand service operation [Integration of management system]
46 * Reliability analysis to ensure transparency of autonomous operation
47
48 == Goals ==
49
50 * TBA for each topic individually
51
52 == Scope ==
53
54 Bachelor's or Master's Thesis, with varying requirements to scientific scope.
55
56 == Related Work/Literature ==
57
58 * https://reakt.sh/
59 * [[https:~~/~~/www.schiene-m-l.de/>>https://www.schiene-m-l.de/)]]
60
61 == Involved Languages/Technologies ==
62
63 * TBA for each topic individually
64
65 == Supervised by ==
66
67 Alexander Schulz-Rosengarten
68 [[als@informatik.uni-kiel.de>>mailto:als@informatik.uni-kiel.de]]