[REAKT] Project REAKTOR

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 rail vehicle, the **REAKTOR**, to flexibly provide on-demand service on single track lines. A prototype will be build in 1:32 scale for 45 mm gauge, 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 for a 45mm model track.//

6

7

== Overview of topics (WIP) ==

8

9

**The solutions in all topics must be scalable for both demonstrators!**

10

11

~1. An end-user app and management system for on-demand train service

12

// This topic may be split up into two theses (app & management)//

13

14

* A mobile app to call a train to a desired location and communicate desired destination

15

* Locations drawn from GNSS and appropriate abstraction for 1:32 scale for station-less entry or predefined locations

16

* Management of multiple on-demand trains on a single track line

17

* Schedules for cooperative passenger pick up

18

* Provisions for passenger transfer on open track ("Begegnungsverkehr", see concept art [[here>>https://cloud.rz.uni-kiel.de/index.php/s/ZMZSoLTerJCJi7L]])

19

* The inter train communication concept maybe based on a central or decentralized structure

20

21

2. An autonomous train controller with risk analysis using STPA **[already reserved]**

22

23

* Control of an autonomous passenger train model (conceptually working for both demonstrators)

24

* Capability for passenger transfer on open track (safe docking procedure; "Begegnungsverkehr", see concept art [[here>>https://cloud.rz.uni-kiel.de/index.php/s/ZMZSoLTerJCJi7L]])

25

* Risk analysis for the controller using STPA ([[http:~~/~~/psas.scripts.mit.edu/home/get_file.php?name=STPA_handbook.pdf>>url:http://psas.scripts.mit.edu/home/get_file.php?name=STPA_handbook.pdf]])

26

* Safe behavior model generation using PASTA ([[https:~~/~~/marketplace.visualstudio.com/items?itemName=kieler.pasta>>https://marketplace.visualstudio.com/items?itemName=kieler.pasta]])

27

* Assumes preprocessed sensor input and destination determination (see other topics)

28

29

3. AI-based obstacle detection for autonomous train control using image recognition

30

// This topic will be jointly advised with the AG Distributed Systems//

31

32

* Sensor processing of a train-mounted camera to detect objects (potential obstacles)

33

* Tasks will involve:

34

** Sensor mounting on the demonstrator

35

** Collection of data (images, videos)

36

** Labeling of data to enable training (esp. for small scale model)

37

** Training of AI

38

** Evaluation of quality

39

** Live testing

40

* Step-wise evaluation of the influence of vehicle speed on the detection quality

41

* Evaluate applicability and influence of training data due to different environments for the demonstrators (i.e. indoors vs. outdoors)

42

* (Optional) Trajectory detection to categorize safety threads of moving obstacles

43

* (Optional) Evaluate performance on different hardware, e.g. Rasberry Pi vs. AI hardware

44

* (Optional) Test and evaluate on the edge deployment

45

* For interfacing with the controller, the sensor should provide an assessment how safe the area in front of the train is, such that the controller can adjust its speed.

46

* Potential hardware (subject to changes):

47

** [[https:~~/~~/www.raspberrypi.com/documentation/accessories/camera.html>>https://www.raspberrypi.com/documentation/accessories/camera.html]]

48

** (((

49

[[https:~~/~~/www.axis.com/de-de/products/axis-p1455-le>>https://www.axis.com/de-de/products/axis-p1455-le]]

50

)))

51

52

4. Classic and AI-based distance sensing for autonomous train control using different sensors

53

// This topic will be jointly advised with the AG Distributed Systems//

54

55

* Explore and evaluate different sensors and processing techniques for distance measuring in rail vehicles

56

* Compare quality, ranges, and reliability w.r.t speed and size (demonstrator)

57

* Sensors and approaches:

58

*1. Ultrasonic sensor

59

*1. Single camera with AI image recognition

60

*1. (Multiple cameras)

61

*1. (LiDAR)

62

*1. (Sensorfusion)

63

* Potential hardware (subject to changes):

64

** [[https:~~/~~/www.elektronik-kompendium.de/sites/praxis/bauteil_ultrasonic-hcsr04p.htm>>https://www.elektronik-kompendium.de/sites/praxis/bauteil_ultrasonic-hcsr04p.htm]]

65

** [[https:~~/~~/www.pi-shop.ch/lidar-ld06-lidar-module-with-bracket-entwicklungskit-fuer-raspberry-pi-sbc>>https://www.pi-shop.ch/lidar-ld06-lidar-module-with-bracket-entwicklungskit-fuer-raspberry-pi-sbc]]

66

** (((

67

[[https:~~/~~/www.blickfeld.com/de/produkte/cube-1/>>https://www.blickfeld.com/de/produkte/cube-1/]]

68

)))

69

70

5. A digital twin for an autonomous on-demand train service **[already reserved]**

71

// Note: Tight interfacing with other topics//

72