Hiring.Camp

Thesis Work - Tactile-Aware Reinforcement Learning for Contact-Rich Manipulation

Abb

·

Oct 6, 2026

Location
Vaesteras, Sweden
Workplace
Onsite
Closing date
Oct 12, 2026
Source
Workday

Description

At ABB, we help industries outrun - leaner and cleaner. Here, progress is an expectation - for you, your team, and the world. As a global market leader, we’ll give you what you need to make it happen. It won’t always be easy, growing takes grit. But at ABB, you’ll never run alone. Run what runs the world.

This role sits within ABB's Robotics business, a leading global robotics company. We're entering an exciting new chapter as we’ve announced the plan for SoftBank Group to acquire ABB Robotics. SoftBank is a globally recognized technology group and investor/operator focused on AI, robotics, and next-generation computing.  By joining us now, you’ll be part of a pioneering team shaping the future of robotics—working alongside world-class experts in a fast-moving, innovation-driven environment.

This Position reports to:

R&D Center Lead


 

Your role and responsibilities


This thesis combines both investigation and prototype development in the area of tactile-guided robotic manipulation. The student will investigate how tactile sensing can improve the performance and robustness of contact-rich manipulation tasks. A digital twin of a robot arm equipped with a Psyonic/Linkerbot Hand will be provided by the supervisors in NVIDIA Isaac Sim. Building on this foundation, the student will extend the simulation framework with tactile sensing capabilities, develop reinforcement learning training environments and pipelines in NVIDIA Isaac Lab, and evaluate tactile-guided manipulation policies in simulation, with optional validation on real hardware.

 

The work is expected to include:


  • Conducting a literature review on tactile sensing, dexterous manipulation, and robot learning methods on Isaac Sim & Isaac Lab.
  • Developing tactile sensing simulation based on contact information available in Isaac Sim.
  • Implementing and training reinforcement learning policies for contact-rich manipulation tasks such as grasp stabilization, object manipulation, pick-and-place, and insertion.
  • Comparing tactile-aware policies against proprioception-only baselines.
  • Evaluating policy performance in terms of task success rate, robustness, and sim-to-real transfer capability.

 

The project has a well-defined technical direction, but students are encouraged to propose and explore their own ideas regarding tactile representations, learning algorithms, task design, or sim-to-real transfer strategies. We are open to suggestions that align with the overall goal of improving tactile-guided robotic manipulation.

 

Details:


  • Period: January to July, 2027
  • Number of credits:  30 ECTS/högskolepoäng (hp)
  • Number of students for this thesis work: 1
  • Location: on-site, Västerås

 

The thesis will be jointly supervised by two supervisors with complementary expertise in robotics and AI. Students will receive guidance on simulation development and tactile sensing, as well as on robot learning methods such as reinforcement learning and imitation learning. Additional expertise in robotics and control systems will be available throughout the project, providing comprehensive support across both AI and robotics domains.


Qualifications for the role


  • Master students interested in robotics and reinforcement learning
  • Python, C++, ROS 2 experience is preferred
  • Robotics fundamentals (kinematics, dynamics, control)
  • Machine learning basics
  • Linux and Git

More about us


Recruiting Manager LiWei Qi, +46 73 021 2309, Supervisors: Tong Hui, [email protected] Zhen Li [email protected] will answer your questions.

 

Positions are filled continuously. Please apply with your CV, academic transcripts, and a cover letter in English.

 

We look forward to receiving your application!

A Future Opportunity
Please note that this position is part of our talent pipeline and not an active job opening at this time. By applying, you express your interest in future career opportunities with ABB.

We value people from different backgrounds. Could this be your story? Apply today or visit www.abb.com to learn more about us and see the impact of our work across the globe.

Skills

PythonLinuxMachine LearningGit

Similar Jobs

30

Master Thesis Work - Local Virtual CMDB for e-SBOM and Release Traceability

Abb·Sweden

1w ago

Master Thesis Work - Industrializing e-SBOM Traceability across DevOps, Windchill and Product Lifecycle Systems

Abb·Sweden

1w ago

THESIS WORK: VERIFICATION, MAINTENANCE AND UPGRADE OF THE STRESSOMETER SYSTEM TEST ENVIRONMENT

Abb·Stockholm, Sweden

1w ago

Thesis Work for Seeing Is Verifying: Simulation-in-the-Loop Development of AI-Generated Robot Programs with Local Vision-Language Models

Abb·Remote

2w ago

Master Thesis work on advanced AI topics in the Telecom Sector (m/f/d)

Ericsson·Herzogenrath, North Rhine-Westphalia

2w ago

Thesis Work on Post-Fault Recovery Stability of AI Data Center in Weak Grids

Abb·Stockholm, Sweden

1mo ago

Thesis Work - Self-Adaptive Digital Twin for Robot Manipulation Through Continuous Real-Sim Discrepancy Learning

Abb·Stockholm, Sweden·Remote, Hybrid, Onsite

1mo ago

Thesis Work on Benchmarking of grid-forming converter control methods

Abb·Stockholm, Sweden

1mo ago

Thesis Work on Impact of Process-Heat Electrification on the Internal Electrical Infrastructure of an F&B Plant

Abb·Stockholm, Sweden

1mo ago

Thesis Work on Computational Fluid Dynamics Simulations for Deep Mine Applications

Abb·Stockholm, Sweden

1mo ago

Thesis Work on AI-assisted Automated Stability Assessment for Industrial Grids with MATLAB/Simulink interface

Abb·Stockholm, Sweden

1mo ago

Thesis Work -Active Vision for AI-based Robot Manipulation with a 2-DOF Movable Camera Head

Abb·Stockholm, Sweden

1mo ago

Thesis Work - AI-Assisted Design and FEM-Based Development of a Spherical Electrical Machine for Robotic Actuation

Abb·Stockholm, Sweden

1mo ago

Thesis Work -Depth-Aware Physical AI Models for Robot Manipulation

Abb·Stockholm, Sweden·Onsite

1mo ago

Thesis Work - Whole-Body Teleoperation and Imitation Learning for Humanoid Robots

Abb·Stockholm, Sweden·Onsite

1mo ago

Thesis Work -Current Source Inverters for High-Performance Electrical Drives in Robotic Applications

Abb·Stockholm, Sweden

1mo ago

Thesis Work for Design for circularity – Reversible adhesives

Abb·Stockholm, Sweden

1mo ago

Thesis work - Learning Robot-Individual Physics-Models from Calibration Data and Test Measurements

Abb·Stockholm, Sweden

1mo ago

Thesis Work: Physical AI Through Simulation-Driven Learning and Planning for Industrial Robots

Abb·Stockholm, Sweden

1mo ago

Thesis Work for Scalable Distributed Computation over TSN for Industrial Robot Controllers

Abb·Stockholm, Sweden·Remote, Hybrid

1mo ago

Thesis Work for Determinism and Scalability of ROS 2/DDS for Distributed Industrial Robot Controllers

Abb·Stockholm, Sweden·Remote, Hybrid

1mo ago

Thesis Work – Motion control limited mechanical dimensioning

Abb·Stockholm, Sweden

2mo ago

Thesis Work – Investigating the environmental impact of AI & Future Technologies at ABB Robotics

Abb·Stockholm, Sweden

2mo ago

Thesis Work – Applied probability and statistics for robot dimensioning

Abb·Stockholm, Sweden

2mo ago

Thesis Work – Advanced Computational Modeling for Engineering Applications

Abb·Stockholm, Sweden

2mo ago

Thesis Worker - Core handling study

valmet·Karlstad, Värmland

2d ago

Thesis Worker - Machine Concept Upgrade

valmet·Karlstad, Värmland

3d ago

Master´s thesis worker

Aalto·Finland·Onsite

1w ago

Intern PLC developer thesis worker

Danaher·SWE - Bjorkgatan 30 Uppsala - Cytiva, Sweden

4w ago

Master Thesis / Bachelor Thesis / Working Student

Voraus

1y+ ago