Summary

• Page properties (2 modified, 0 added, 0 removed)
• Attachments (0 modified, 0 added, 2 removed)
  • image-20240912102452-3.jpeg
  • image-20240912102840-4.jpeg

Details

Page properties

Title

...	...	@@ -1,1 +1,1 @@
1		-[REAKT] Project REAKTOR
	1	+[REAKT] Projecting Irregular Vehicle Positions on Tracks

Content

...	...	@@ -1,123 +1,35 @@
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.
	1	+The REAKT DATA project (https://reakt.sh/) includes visualizing rail vehicle positions on the track based on a set of position data from GNNS trackers. These position data are sparse and include errors and variation, yet it can be safely assumed that the rail vehicle will not leave the track in normal operation. Hence, this topic will investigate an algorithm to process the data and project the position of the vehicles onto the track.
2	2
3		-[[image:image-20240912102452-3.jpeg||height="219" width="292"]][[image:image-20240912102840-4.jpeg||height="217" width="264"]]
	3	+[[image:position.png]]
4	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.//
	5	+== Goals ==
6	6
7		-{{info}}
8		-Kick-off meeting on Monday 7th Oct. at 10am in room 1115 CAP4
9		-{{/info}}
	7	+* Develop and implement an algorithm for computing a best-effort projection of a vehicle position on a track
	8	+* Evaluate the algorithm (and potential variants of the algorithm) with the real-world data collected on the Malente-Lütjenburg track
10	10
11		-== Overview of topics (WIP) ==
	10	+==== Consiterations for the Algorithm ====
12	12
13		-**The solutions in all topics must be scalable for both demonstrators!**
	12	+* Errors in GNNS data
	13	+* Gaps in GNNS data (missing network)
	14	+* Different accuracy of tracking devices (Smartphones vs. dedicated Trackers)
	15	+* Showing estimates of expected movement or potential location areas
	16	+* Handling inconsistencies
	17	+* Unrealistic position jumps
	18	+* Passing other vehicles (quickly) on single-lane track
	19	+* Vehicles changing direction without stopping
14	14
15		-~1. An end-user app and management system for on-demand train service **[(partially) reserved]**
16		-// This topic may be split up into two theses (app & management)//
17		-
18		-* A mobile app to call a train to a desired location and communicate desired destination
19		-* Locations drawn from GNSS and appropriate abstraction for 1:32 scale for station-less entry or predefined locations
20		-* Management of multiple on-demand trains on a single track line
21		-* Schedules for cooperative passenger pick up
22		-* Provisions for passenger transfer on open track ("Begegnungsverkehr", see concept art [[here>>https://cloud.rz.uni-kiel.de/index.php/s/ZMZSoLTerJCJi7L]])
23		-* The inter train communication concept maybe based on a central or decentralized structure
24		-
25		-2. An autonomous train controller with risk analysis using STPA **[already reserved]**
26		-
27		-* Control of an autonomous passenger train model (conceptually working for both demonstrators)
28		-* 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]])
29		-* 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]])
30		-* Safe behavior model generation using PASTA ([[https:~~/~~/marketplace.visualstudio.com/items?itemName=kieler.pasta>>https://marketplace.visualstudio.com/items?itemName=kieler.pasta]])
31		-* Assumes preprocessed sensor input and destination determination (see other topics)
32		-
33		-3. AI-based obstacle detection for autonomous train control using image recognition
34		-// This topic will be jointly advised with the AG Distributed Systems//
35		-
36		-* Sensor processing of a train-mounted camera to detect objects (potential obstacles)
37		-* Tasks will involve:
38		-** Sensor mounting on the demonstrator
39		-** Collection of data (images, videos)
40		-** Labeling of data to enable training (esp. for small scale model)
41		-** Training of AI
42		-** Evaluation of quality
43		-** Live testing
44		-* Step-wise evaluation of the influence of vehicle speed on the detection quality
45		-* Evaluate applicability and influence of training data due to different environments for the demonstrators (i.e. indoors vs. outdoors)
46		-* (Optional) Trajectory detection to categorize safety threads of moving obstacles
47		-* (Optional) Evaluate performance on different hardware, e.g. Rasberry Pi vs. AI hardware
48		-* (Optional) Test and evaluate on the edge deployment
49		-* 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.
50		-* Potential hardware (subject to changes):
51		-** [[https:~~/~~/www.raspberrypi.com/documentation/accessories/camera.html>>https://www.raspberrypi.com/documentation/accessories/camera.html]]
52		-** (((
53		-[[https:~~/~~/www.axis.com/de-de/products/axis-p1455-le>>https://www.axis.com/de-de/products/axis-p1455-le]]
54		-)))
55		-
56		-4. Classic and AI-based distance sensing for autonomous train control using different sensors **[already reserved]**
57		-// This topic will be jointly advised with the AG Distributed Systems//
58		-
59		-* Explore and evaluate different sensors and processing techniques for distance measuring in rail vehicles
60		-* Compare quality, ranges, and reliability w.r.t speed and size (demonstrator)
61		-* Sensors and approaches:
62		-*1. Ultrasonic sensor
63		-*1. Single camera with AI image recognition
64		-*1. (Multiple cameras)
65		-*1. (LiDAR)
66		-*1. (Sensorfusion)
67		-* Potential hardware (subject to changes):
68		-** [[https:~~/~~/www.elektronik-kompendium.de/sites/praxis/bauteil_ultrasonic-hcsr04p.htm>>https://www.elektronik-kompendium.de/sites/praxis/bauteil_ultrasonic-hcsr04p.htm]]
69		-** [[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]]
70		-** (((
71		-[[https:~~/~~/www.blickfeld.com/de/produkte/cube-1/>>https://www.blickfeld.com/de/produkte/cube-1/]]
72		-)))
73		-
74		-5. A digital twin for an autonomous on-demand train service **[already reserved]**
75		-// Note: Tight interfacing with other topics//
76		-
77		-* A digital twin for an autonomous passenger train
78		-* Monitoring system for the state and location of the vehicle
79		-* Simulation capabilities to test and replay behavior (virtual environment)
80		-* Monitoring and economic analysis of on-demand service operation (//integration/interfacing of management system//)
81		-* Reliability analysis/statistics to ensure transparency of autonomous operation
82		-
83		-6. Remote control for rail vehicles
84		-//Note: Tight interfacing with other topics//
85		-
86		-* Remote control of speed and brakes //(interfacing with controller)//
87		-* Live streaming of camera data and other sensors
88		-* Evaluation and setup of a wireless communication network with a high reliability
89		-* (Optional) Construction of a [[remote control panel>>https://cloud.rz.uni-kiel.de/index.php/s/jCxitwKzddqEctD]]
90		-* (Optional) Augmented reality integration to simulate training scenarios
91		-
92		-7. A standalone sensor box for monitoring rail vehicles **[already reserved]**
93		-//This prototype will be tested (only) using the full-scale demonstrator and is intended for monitoring non-autonomous vehicles (not the REAKTOR)//
94		-
95		-* Development of a sensor array to monitor rail vehicle operation
96		-* It should serve as a plugin solution inside the train's cockpit for monitoring operation and as preparation for autonomous control
97		-* Design for wireless communication of collected data
98		-* Possible sensors:
99		-** GPS
100		-** Accelerometer
101		-** Camera
102		-* Analysis of data for autonomous driving
103		-* Potential integration into digital twin infrastructure
104		-
105		-== Goals ==
106		-
107		-* TBA for each topic individually
108		-
109	109	== Scope ==
110	110
111		-Bachelor's or Master's Thesis, with varying requirements to scientific scope.
	23	+Bachelor's Thesis
112	112
113	113	== Related Work/Literature ==
114	114
115	115	* https://reakt.sh/
116		-* [[https:~~/~~/www.schiene-m-l.de/>>https://www.schiene-m-l.de/)]]
	28	+* https://github.com/kieler/RailTrail/wiki/Data-processing#computation-of-vehicle-position-speed-and-heading
117	117
118	118	== Involved Languages/Technologies ==
119	119
120		-* TBA for each topic individually
	32	+* Python
121	121
122	122	== Supervised by ==
123	123

image-20240912102452-3.jpeg

Author

...	...	@@ -1,1 +1,0 @@
1		-XWiki.als

Size

...	...	@@ -1,1 +1,0 @@
1		-362.3 KB

Content

image-20240912102840-4.jpeg

Author

...	...	@@ -1,1 +1,0 @@
1		-XWiki.als

Size

...	...	@@ -1,1 +1,0 @@
1		-148.4 KB

Content