Anticipating Human Activities for Reactive Robotic Response

An important aspect of human perception is anticipation. Anticipating which activities will a human do next (and how to do them) can enable an assistive robot to plan ahead for reactive responses in the human environments. Furthermore, anticipation can even improve the detection accuracy of past activities. This video shows each possible future using an anticipatory temporal conditional random field (ATCRF) that models the rich spatial-temporal relations through object affordances. The authors then consider each ATCRF as a particle and represent the distribution over the potential futures using a set of particles.