Causal analysis shows social signals help robots navigate corridors
Estimating the Causal Impact of Social Navigation Signals in Corridor Scenarios
RoboticsArtificial Intelligence
Summary
When robots move through crowded hallways, they sometimes use social signals to communicate with people and avoid collisions. The authors show that just looking at observations can lead to wrong conclusions about whether these signals help or hurt. By using a method called causal inference, they can separate real effects from misleading factors like obstacles. Their study found that social signals actually improve the robot’s success in navigating, contrary to what simple observations suggested.
What this means in practice
- •For robotics engineers: Improve robot navigation in shared spaces by using causal models to decide when to emit social signals.
- •For human factors teams: Design better human-robot interaction strategies by accurately evaluating the impact of robot social signals on pedestrian navigation.
Authors
Francesco Baldo, Luca Castri, Gloria Beraldo, Nicola Bellotto
Abstract
Deploying robots in human-shared environments requires deciding not only how to navigate, but also when dedicated social signals are worth emitting. Classic observation-based inference can be misleading in such settings: confounding factors may bias the estimated relationship between a signal and the task outcome, leading to incorrect decisions. Causal inference provides a framework for disentangling these relationships by modelling the mechanisms linking observations, actions, and outcomes, and by estimating interventional effects after accounting for confounding paths. We study a human-robot interaction scenario in a corridor and use a causal model to estimate whether a social navigation signal causally improves transit success. We represent the interaction as a causal DAG involving robot action, pedestrian occupancy, available space, task outcome, and a controlled confounder (static obstacles). We compare the interventional estimate with the observational estimate obtained by conditioning only on the robot action, which does not explicitly model interventions. Our results show that accounting for confounding variables can reverse the conclusions drawn from naive observational analysis: the observational estimate wrongly suggests that the social signal is detrimental, whereas the causal estimate shows that it is beneficial. This discrepancy highlights how failing to account for confounding can lead to incorrect conclusions and demonstrates the importance of causal models for context-aware signalling decisions in social robot navigation.