Reproduce “Utility Theory based Cognitive Modeling in the Application of Robotics: A Survey” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Qin Yang
This survey systematically reviews utility theory based cognitive modeling in robotics, tracing its evolution from behavior-based systems to complex cognitive architectures and highlighting its application in single-agent, multi-agent, trust, and human-robot interaction contexts. It also proposes an Agent Needs Hierarchy and identifies critical research gaps for future development.
Key insights
- Utility theory offers a robust computational framework for specifying models of representation, mechanisms, and processes crucial for cognitive functionalities in artificial agents.
- The proposed Agent Needs Hierarchy (ANH) provides a multi-level paradigm for prioritizing and modeling robot motivations, conceptually analogous to Maslow's hierarchy, from safety to learning needs.
- Trust between agents can be quantified using Relative Needs Entropy (RNE), a model combining utility and information theory to measure the similarity of agents' needs distributions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.