JobbSafariLediga jobbMaster thesis - Embodiment-Aware Autonomous Driving Policies with Deep Learning
Master thesis - Embodiment-Aware Autonomous Driving Policies with Deep Learning
Scania GroupRekommenderat
Sammanfattning
This Master's thesis opportunity focuses on developing embodiment-aware autonomous driving policies using deep learning techniques. The project, based at TRATON Group R&D in Södertälje, aims to enhance the adaptability of driving policies across diverse vehicle configurations through imitation learning. Students will work on motion-planning policies, transfer-learning strategies, and unified learning frameworks over a 20-week period starting January 2027. This role is ideal for those pursuing aJobbet i korthet
Arbetstid
deltid
Det här erbjuder vi
Opportunity to work closely with TRATON Group R&D and build professional relationships.Hands-on experience in cutting-edge research in autonomous driving.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-10-01
Beskrivning
30 credits - Embodiment-Aware Autonomous Driving Policies with Deep Learning
Introduction
A Master's thesis is an excellent way to get closer to TRATON Group R&D and build relationships for the future.
Background
Recent advances in autonomous driving have been largely driven by large-scale imitation learning (IL) from human driving data. By leveraging large datasets of expert demonstrations, learned driving policies have achieved impressive performance across a wide range of driving scenarios. A key challenge for autonomous trucking is that vehicle configurations differ substantially in geometry, articulation, axle layout, payload capacity, braking authority, and steering constraints. These differences influence feasible driving behaviors and motion-planning decisions. While separate policies can be trained for each vehicle configuration, such an approach scales poorly as fleets become increasingly diverse. Conversely, learning a shared policy across multiple vehicle types is challenging because embodiment-specific behaviors must be preserved while still leveraging common driving knowledge.
Similar challenges have recently been studied in robotics under the umbrella of multi-embodiment learning. Prior work has shown that conditioning policies on robot morphology, kinematics, or learned dynamics representations can improve transfer across heterogeneous platforms1,2. These ideas suggest that embodiment-aware learning may provide a scalable approach for developing autonomous driving policies that generalize across diverse vehicle configurations while adapting to their unique constraints.
Objective
Inspired by related works3, this thesis investigates how vehicle-configuration-aware driving policies can be learned from heterogeneous driving data. In particular, the work will explore how policies trained on passenger-vehicle data can be adapted to heavy-duty vehicle configurations, whether embodiment conditioning improves generalization across vehicle platforms, and how training on diverse multi-vehicle datasets influences policy performance and behavior.
Job description
The goal of this thesis is to investigate the learning of vehicle-configuration-aware driving policies using imitation learning and embodiment conditioning. The assignment is divided into several subtasks:
Education/program/focus
Master (civilingenjör) in computer science, robotics, electrical engineering, or applied mathematics, preferably with specialization in artificial intelligence algorithms.
Number of students: 1-2
Start date: January 2027
Estimated time needed: 20 weeks
Contact persons and supervisors
Caroline Skoglund, Industrial PhD Student (KTH Robotics, Perception and Learning) caroline.skoglund@scania.com
Yunus Emre Sahin, Research & Development Engineer in Autonomous Motion yunus-emre.sahin@scania.com
Hiring Manager: Magnus Granström, magnus.granstrom@scania.com
Application:
Your application must include a CV, cover letter and transcript of grades.
A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.
References
[1] K. Bousmalis et al., "RoboCat: A self-improving generalist agent for robotic manipulation," Trans. Mach. Learn. Res., 2024.
[2] A. Gupta, L. Fan, S. Ganguli, and L. Fei-Fei, "MetaMorph: Learning universal controllers with transformers," in Proc. Int. Conf. Learn. Representations (ICLR), 2022.
[3] H. Oh and J. Park, "MVAdapt: Zero-shot multi-vehicle adaptation for end-to-end autonomous driving," 2026. [Online]. Available: https://arxiv.org/abs/2604.11854
Publication date:
1.10.2026 - 30.11.2026 (applications evaluated continuously)
Requisition ID: 33767
Number of Openings: 1.0
Part-time / Full-time: Full-time
Permanent / Temporary: Temporary
Country/Region: SE
Location(s):
Södertälje, SE, 151 38
Required Travel: 0%
Workplace: Hybrid
Introduction
A Master's thesis is an excellent way to get closer to TRATON Group R&D and build relationships for the future.
Background
Recent advances in autonomous driving have been largely driven by large-scale imitation learning (IL) from human driving data. By leveraging large datasets of expert demonstrations, learned driving policies have achieved impressive performance across a wide range of driving scenarios. A key challenge for autonomous trucking is that vehicle configurations differ substantially in geometry, articulation, axle layout, payload capacity, braking authority, and steering constraints. These differences influence feasible driving behaviors and motion-planning decisions. While separate policies can be trained for each vehicle configuration, such an approach scales poorly as fleets become increasingly diverse. Conversely, learning a shared policy across multiple vehicle types is challenging because embodiment-specific behaviors must be preserved while still leveraging common driving knowledge.
Similar challenges have recently been studied in robotics under the umbrella of multi-embodiment learning. Prior work has shown that conditioning policies on robot morphology, kinematics, or learned dynamics representations can improve transfer across heterogeneous platforms1,2. These ideas suggest that embodiment-aware learning may provide a scalable approach for developing autonomous driving policies that generalize across diverse vehicle configurations while adapting to their unique constraints.
Objective
Inspired by related works3, this thesis investigates how vehicle-configuration-aware driving policies can be learned from heterogeneous driving data. In particular, the work will explore how policies trained on passenger-vehicle data can be adapted to heavy-duty vehicle configurations, whether embodiment conditioning improves generalization across vehicle platforms, and how training on diverse multi-vehicle datasets influences policy performance and behavior.
Job description
The goal of this thesis is to investigate the learning of vehicle-configuration-aware driving policies using imitation learning and embodiment conditioning. The assignment is divided into several subtasks:
- Develop or extend a motion-planning policy capable of incorporating vehicle-configuration information.
- Evaluate transfer-learning strategies for adapting policies from passenger vehicles to heavy-duty vehicle configurations.
- Investigate how driving data from multiple vehicle configurations can be combined within a unified learning framework.
- Implement, train, and evaluate the proposed solutions in terms of their generalization capabilities, data efficiency, and driving performance.
Education/program/focus
Master (civilingenjör) in computer science, robotics, electrical engineering, or applied mathematics, preferably with specialization in artificial intelligence algorithms.
Number of students: 1-2
Start date: January 2027
Estimated time needed: 20 weeks
Contact persons and supervisors
Caroline Skoglund, Industrial PhD Student (KTH Robotics, Perception and Learning) caroline.skoglund@scania.com
Yunus Emre Sahin, Research & Development Engineer in Autonomous Motion yunus-emre.sahin@scania.com
Hiring Manager: Magnus Granström, magnus.granstrom@scania.com
Application:
Your application must include a CV, cover letter and transcript of grades.
A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.
References
[1] K. Bousmalis et al., "RoboCat: A self-improving generalist agent for robotic manipulation," Trans. Mach. Learn. Res., 2024.
[2] A. Gupta, L. Fan, S. Ganguli, and L. Fei-Fei, "MetaMorph: Learning universal controllers with transformers," in Proc. Int. Conf. Learn. Representations (ICLR), 2022.
[3] H. Oh and J. Park, "MVAdapt: Zero-shot multi-vehicle adaptation for end-to-end autonomous driving," 2026. [Online]. Available: https://arxiv.org/abs/2604.11854
Publication date:
1.10.2026 - 30.11.2026 (applications evaluated continuously)
Requisition ID: 33767
Number of Openings: 1.0
Part-time / Full-time: Full-time
Permanent / Temporary: Temporary
Country/Region: SE
Location(s):
Södertälje, SE, 151 38
Required Travel: 0%
Workplace: Hybrid
Ansök till tjänsten
Master thesis - Embodiment-Aware Autonomous Driving Policies with Deep Learning
Rekommenderat
OM FÖRETAGET
Scania Group
