Papers
3
Total Citations
14
H-Index
2
About
Tim Goller is a robotics researcher whose work centers on advanced control systems for robotic manipulation, with a particular focus on model predictive control and human-robot interaction. His research addresses one of the field's fundamental challenges: enabling robots to seamlessly transition between free motion and physical interaction with their environment in a principled, unified framework. Goller's most significant contribution is the development of Model Predictive Interaction Control (MPIC), an optimization-based approach that formulates complex manipulation tasks as sequences of primitives, accommodating the variable control structures — including motion control and force control — that different task phases demand. His 2020 foundational paper on a generic manipulation framework has garnered 8 citations, establishing MPIC as a coherent research direction. Building on this, his 2022 path-following formulation refined the approach by explicitly integrating environmental contact dynamics, earning 5 citations. His more recent 2025 work extends the framework further by incorporating systematic fault handling and recovery strategies, enabling robots to dynamically replan in response to unexpected failures. Goller's cumulative contributions reflect a sustained effort to make robotic manipulation more robust, generalizable, and practically deployable — work of growing relevance as robots increasingly operate in unstructured, real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3