<
From version < 29.1 >
edited by Alexander Schulz-Rosengarten
on 2024/09/16 16:34
To version < 31.3 >
edited by Alexander Schulz-Rosengarten
on 2024/09/19 13:51
>
Change comment: There is no comment for this version

Summary

Details

Page properties
Content
... ... @@ -26,17 +26,28 @@
26 26  * Safe behavior model generation using PASTA ([[https:~~/~~/marketplace.visualstudio.com/items?itemName=kieler.pasta>>https://marketplace.visualstudio.com/items?itemName=kieler.pasta]])
27 27  * Assumes preprocessed sensor input and destination determination (see other topics)
28 28  
29 -3. AI-based image recognition for autonomous train control
29 +3. AI-based obstacle detection for autonomous train control using image recognition
30 30  // This topic will be jointly advised with the AG Distributed Systems//
31 31  
32 -* Sensor processing of a train mounted camera
33 -* Obstacle detection at speeds up to 50 km/h
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 the
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
34 34  * Potential hardware (subject to changes):
35 35  ** [[https:~~/~~/www.raspberrypi.com/documentation/accessories/camera.html>>https://www.raspberrypi.com/documentation/accessories/camera.html]]
36 36  ** (((
37 37  [[https:~~/~~/www.axis.com/de-de/products/axis-p1455-le>>https://www.axis.com/de-de/products/axis-p1455-le]]
38 38  )))
39 -* [Optional] Distance measuring using multiple cameras
40 40  
41 41  4. AI-based sensor processing for autonomous train control
42 42  // This topic will be jointly advised with the AG Distributed Systems//
... ... @@ -52,7 +52,7 @@
52 52  * Distance measuring (ultrasonic sensor)
53 53  
54 54  5. A digital twin for an autonomous on-demand train service **[already reserved]**
55 - // Note: Tight interfacing with other topics//
66 +// Note: Tight interfacing with other topics//
56 56  
57 57  * A digital twin for an autonomous passenger train
58 58  * Monitoring system for the state and location of the vehicle
... ... @@ -61,15 +61,15 @@
61 61  * Reliability analysis/statistics to ensure transparency of autonomous operation
62 62  
63 63  6. A standalone sensor box for monitoring rail vehicles
64 - //This prototype will be tested (only) using the full-scale demonstrator and is intended for monitoring non-autonomous vehicles (not the REAKTOR)//
75 + //This prototype will be tested (only) using the full-scale demonstrator and is intended for monitoring non-autonomous vehicles (not the REAKTOR)//
65 65  
66 -* Development of a weather-resistant sensor array to monitor rail vehicle operation
67 -* Wireless communication of collected data
77 +* Development of a sensor array to monitor rail vehicle operation
78 +* It should serve as a plugin solution inside the train's cockpit for monitoring operation and as preparation for autonomous control
79 +* Design for wireless communication of collected data
68 68  * Possible sensors:
69 69  ** GPS
70 70  ** Accelerometer
71 71  ** Camera
72 -** (LiDAR)
73 73  * Analysis of data for autonomous driving
74 74  * Potential integration into digital twin infrastructure
75 75