Jakob Hollenstein

Papers

Total Citations

H-Index

About

Jakob Hollenstein is a robotics and machine learning researcher whose work sits at the intersection of continual learning, learning from demonstration (LfD), and intelligent automation. His research addresses one of the most pressing challenges in modern robotics: enabling robots to acquire new motor skills incrementally without forgetting previously learned behaviors — a problem known as catastrophic forgetting. His most influential contribution, "Continual Learning from Demonstration of Robotics Skills" (2023, 33 citations), introduced a framework allowing robots to accumulate movement skills over time, significantly advancing the practicality of real-world robotic deployment. Building on this, his 2026 work on hypernetwork-generated stable dynamics models extends this vision by ensuring both stability and scalability in continual LfD systems — a critical requirement for safe robot operation. Beyond motion learning, Hollenstein has demonstrated breadth by tackling real-world automation challenges, including a visual intelligence scheme for robotic disassembly in e-waste recycling (2020, 16 citations), reflecting a commitment to socially impactful applications of AI. His growing citation record and trajectory across foundational and applied robotics mark him as an emerging voice shaping how future robots will learn, adapt, and operate sustainably in dynamic environments.