Behavior Synthesis via Contact-Aware Fisher Information Maximization
For robotics researchers, this work addresses the challenge of actively generating informative contact interactions to learn object properties, though the improvements are incremental over existing optimal experimental design methods.
The paper proposes a contact-aware Fisher information maximization approach to synthesize robot behaviors that produce information-rich contact data for learning object parameters, demonstrating improved parameter learning efficiency across simulations and real robotic experiments.
Contact dynamics hold immense amounts of information that can improve a robot's ability to characterize and learn about objects in their environment through interactions. However, collecting information-rich contact data is challenging due to its inherent sparsity and non-smooth nature, requiring an active approach to maximize the utility of contacts for learning. In this work, we investigate an optimal experimental design approach to synthesize robot behaviors that produce contact-rich data for learning. Our approach derives a contact-aware Fisher information measure that characterizes information-rich contact behaviors that improve parameter learning. We observe emergent robot behaviors that are able to excite contact interactions that efficiently learns object parameters across a range of parameter learning examples. Last, we demonstrate the utility of contact-awareness for learning parameters through contact-seeking behaviors on several robotic experiments.