PersonNavExpert
CSIR: Contextually and Socially Informed Robots for Efficient Person Goal Navigation
This preprint introduces CSIR, a planning framework for indoor person-goal navigation that combines semantic likelihoods from uncertain natural language requests with distance-aware route optimization. In synthetic benchmarks across 1,500 scenarios in three environments, CSIR achieved an average travel efficiency of 0.62, above the best classical baseline at 0.43 and comparable LLM-TRP at 0.60. It matters because it reduces dependence on private activity logs and fixed schedules, making service robots more deployable under realistic privacy and information-uncertainty constraints.