Bayesian Floor Field: Transferring people flow predictions across environments

arXiv:2208.10851v2 Announce Type: replace-cross
Abstract: Mapping people dynamics is a crucial skill for robots, because it enables them to coexist in human-inhabited environments. However, learning a model of people dynamics is a time consuming process which requires observation of large amount of people moving in an environment. Moreover, approaches for mapping dynamics are unable to transfer the learned models across environments: each model is only able to describe the dynamics of the environment it has been built in. However, the …

abstract arxiv bayesian cs.lg cs.ro dynamics environment environments flow however human mapping moving observation people predictions process robots them type