Reproduce “Trust as Extended Control: Active Inference and User Feedback During Human-Robot Collaboration” 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
Felix Schoeller, Mark Miller, Roy Salomon, Karl J. Friston
The authors present a conceptual framework for trust in human–robot collaboration. It treats trust as confidence in predicting a robot’s sensory consequences, linking the robot to a person’s perception–action cycle. Timely, relevant feedback is proposed to help compare expected and actual outcomes. The review does not test this mechanism, and which beliefs best represent trust remains open.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.