Lukas Tanz

Papers

Total Citations

H-Index

About

Lukas Tanz is a robotics researcher focused on bridging the gap between simulation and reality in industrial automation. His primary research areas include offline robot programming, skill adaptation, and few-shot learning for manufacturing systems. Tanz’s most impactful contribution, "Automated Commissioning of Offline-Generated Robot Programs" (2022, 10 citations), addresses a critical bottleneck in reconfigurable production: the mismatch between digital planning models and physical environments. This work proposes methods to automate the commissioning process, enabling seamless adaptation of simulated robot programs to real-world conditions. More recently, in "Constrained Bootstrapped Learning for Few-Shot Robot Skill Adaptation" (2024), Tanz introduces a hybrid approach combining learning from demonstration and reinforcement learning. This method seeds learning with compact, structured skill models, allowing robots to rapidly adapt to new tasks online with minimal data. His work is notable for its practical focus on industrial deployment, offering solutions that reduce downtime and manual recalibration. Tanz’s research is particularly relevant for students and engineers seeking to implement flexible, autonomous robotic systems in dynamic manufacturing environments.