Robots Ask the Way: Communication-Enabled Social Navigation
2026-07-01 • Robotics
Robotics
AI summaryⓘ
The authors created a new way for robots to find specific people in busy places by actually talking and asking nearby people for help. They made a system called Communication-enabled Social Navigation (CommNav) that lets robots ask questions about where someone might be. Testing this system in a simulated environment with multiple humans showed that robots using communication found people more successfully. They also found that the robots could understand natural, everyday language just as well as perfect structured data. This shows that letting robots talk with humans can make them better at navigating crowded spaces.
autonomous robotssocial navigationhuman-robot communicationmulti-agent environmentsHabitat 3.0communication protocolsnatural language instructionspre-trainingnavigation policymulti-person navigation
Authors
Valentino Sacco, Luca Scofano, Indro Spinelli, Fabio Galasso
Abstract
Assistive autonomous robots operating in multi-agent environments require efficient strategies to locate specific individuals among multiple residents. Current social navigation methods focus on reactive collision avoidance and trajectory adaptation, but lack mechanisms to proactively gather information through human-robot communication. We introduce Communication-enabled Social Navigation (CommNav). In this novel task, robotic agents actively seek assistance from residents to locate target individuals by requesting information about recent sightings, locations, and movements. To evaluate CommNav, we extend Habitat 3.0 to create Habitat 3.0c, a communication-enabled variant supporting multi-human environments with information exchange protocols. Adding our communication module (COMM) to a state-of-the-art social navigation model yields a 10 percentage-point improvement in Episode Success. We further investigate the transition from structured data to natural language by evaluating models trained on LLM-generated instructions and on colloquial instructions collected from a human study. Our experiments reveal that: (i) explicit human-robot communication substantially enhances multi-person navigation performance; (ii) pre-training COMM on a communication pretext task effectively addresses the challenge of occasional interaction signals; and (iii) the navigation policy is highly robust to natural, colloquial human language, achieving an episode success statistically similar to the model using perfect structured data.