Project Smart Mobility SystemsModule description #50934 / Version 1
- 6 CP
- Internal internship
- Graded
- Winter and summer semester
- English
| Module / Version | #50934 / #1 |
|---|---|
| Validity | Since Summer semester 2025 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Park, Sangyoung |
| Grading | Graded |
| Exam format | Internal internship |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät V |
|---|---|
| Institute | Institut für Maschinenkonstruktion und Systemtechnik (IMS) |
| Academic chair | 35351900 FG Entwicklung digitaler Verkehrstechnologien / Smart Mobility Systems |
Contact
| Office | Not specified |
|---|---|
| Contact person | Park, Sangyoung |
| E-mail address | sangyoung.park@tu-berlin.de |
| Website | http://www.tu.berlin/sms |
Learning outcomes
This project is aimed at implementing state-of-the-art perception algorithms for autonomous vehicles. The algorithm will be implemented based on real-world car simulator, CARLA, and the performance will be tested on an automotive computing platform. The students will gain practical knowledge in running and porting AI algorithms and automotive computing platforms.
Content
- Review recent 3D occupancy network approaches in autonomous driving and robotics.
- Briefly compare them with traditional BEV-based perception and highlight how they improve occlusion handling and sensor fusion.
- Implement established occupancy network algorithms and train relevant machine learning models using real-world datasets such as Waymo or nuScenes to create robust occupancy representations.
- Generate autonomous driving scenarios using the CARLA simulation environment. Collect and record perception data from sensors including lidar and camera.
- Perform inference on synthetic data collected from CARLA using trained occupancy network models. This step will focus on deploying the model on an NVIDIA Jetson AGX Orin platform to enable real-time execution. Emphasis will be placed on evaluating the model's performance under real-time constraints and assessing its feasibility for embedded deployment.
- Document and report all findings, insights, and conclusions clearly and thoroughly.
- Briefly compare them with traditional BEV-based perception and highlight how they improve occlusion handling and sensor fusion.
- Implement established occupancy network algorithms and train relevant machine learning models using real-world datasets such as Waymo or nuScenes to create robust occupancy representations.
- Generate autonomous driving scenarios using the CARLA simulation environment. Collect and record perception data from sensors including lidar and camera.
- Perform inference on synthetic data collected from CARLA using trained occupancy network models. This step will focus on deploying the model on an NVIDIA Jetson AGX Orin platform to enable real-time execution. Emphasis will be placed on evaluating the model's performance under real-time constraints and assessing its feasibility for embedded deployment.
- Document and report all findings, insights, and conclusions clearly and thoroughly.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Smart Mobility Systems | Project | Winter and summer semester | [en] | 4 | ISIS |
Workload and credit points
Smart Mobility Systems (Project)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Documentation | 15 | 4 h | 60 h |
| Software/hardware implementation | 15 | 8 h | 120 h |
| 180 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
Learning through solving practical engineering tasks.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
- Coding experience (Python, C++ etc.)
- Framework experience (ROS ½, Git, Docker)
- Knowledge in Autonomous Driving and preferably computer vision, perception algorithms
- Independent and organized work attitude
- Open-minded team player
- Framework experience (ROS ½, Git, Docker)
- Knowledge in Autonomous Driving and preferably computer vision, perception algorithms
- Independent and organized work attitude
- Open-minded team player
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Internal internship |
| Language | English |
| Duration/Extent | 30 Minute presentation of the project at the end of August. |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter and summer semester.
Maximum number of participants
This module is not limited to a number of students.
Registration procedures
This module requires access to computing hardware at our chair and therefore the number of students can be restricted.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
No recommended literature given
Assigned programs
This module is not used in any program.
Miscellaneous
Not specified