Predicting and Sharing of Multi-Human Intentions in Multi-Robot Systems: A Bayesian Approach

Abstract This research addresses shared intention prediction in multi-human, multi-robot environments. We propose an intention prediction pipeline based on Bayesian inference, enabling robots to predict humans’ navigational intent. Our pipeline uses prior semantic knowledge about potential goal destinations of the humans. We furthermore investigated different strategies for robots to share information to improve their predictions. A dataset was collected specifically for testing our pipeline and comparing different sharing strategies. The dataset consists of camera feeds from two robots observing two humans performing simple pick-up tasks. The pipeline correctly predicts 63% of the cases. Implementing a relatively simple data sharing strategy increased accuracy to 77%. However, a poorly designed data sharing strategy reduced accuracy to 47%. A validation dataset was collected in a more realistic office setting, which supports the observed relative differences in performance, despite the increased complexity of this environment. Our key finding is thus that the choice of sharing strategy can significantly impact prediction performance. The insights gained from our experiments can help progress the development of more effective shared intention prediction in multi-human, multi-robot teams.