Can robots learn from the work they already do? In this master's thesis at 120ft, you will investigate how operational data can improve robot learning for real assembly tasks.
Host: 120ft Factory AB, Stockholm
Company supervisor: Sulthan Suresh Fazeela
Field: Machine learning and robotics
120ft builds Factory OS, a software layer that lets humanoid robots, currently the Unitree G1-D, carry out high-mix, low-volume assembly work. Robot behaviour comes from Vision-Language-Action (VLA) policies trained on recorded demonstrations.
Today, almost all training data comes from dedicated teleoperation sessions. Every hour of that data costs an operator's hour. But the robot also generates data every time it runs.
The research questionOperational rollouts include per-frame tags showing whether a human or a policy was driving. You will investigate whether data from policy-driven episodes can improve the policy, how it can be combined with teleoperation demonstrations, and which data helps rather than hurts.
What you will investigateThis is an offline, experimental project using already-collected rollout data, rather than building a live production pipeline. The goal is to characterise the data and give an evidence-based recommendation on its value for training.
Compare the operational dataset with curated teleoperation datasets: volume, success and failure balance, and recurring failure modes.
Test whether fine-tuning on operational data changes policy quality, and whether filtering or weighting by operator-judged outcome labels makes a difference.
Explore other data-centric questions that emerge, including the reliability and consistency of outcome labels.
A technical supervisor.
Access to existing operational and curated datasets.
Access to the training stack for fine-tuning experiments.
Access to a real Unitree G1-D if additional rollouts are needed.
You are a master's student in machine learning or robot learning, comfortable with empirical experimentation and data analysis.
ApplySend your CV and a GitHub, LinkedIn or website link. Tell us why this thesis interests you and share an example of work you are proud of.
Skills Required
- Master's student in machine learning or robot learning
- Comfortable with empirical experimentation
- Comfortable with data analysis
What We Do
120ft Factory is a Swedish manufacturing startup developing autonomous local micro-factories powered by Physical AI. Its Factory-as-a-Service approach uses containerised production cells and humanoid robots for flexible, high-mix, low-volume assembly. The company is building Factory OS and robotic systems to help manufacturing SMEs automate complex assembly, bring production closer to customers, and reduce dependence on rigid global supply chains through locally operated production facilities.
