© 2017, Springer Science+Business Media B.V., part of Springer Nature. We humans often engage in side-by-side walking even when we do not know where we are going. Replicating this capability in a robot reveals the complications of such daily interactions. We analyzed human–human interactions and found that human pairs sustained a side-by-side walking formation even when one of them (the follower) did not know the destination. When multiple path choices exist, the follower walks slightly behind his partner. We modeled this interaction by assuming that one needs knowledge from the environment, like the locations to which people typically move toward: subgoals. This model enables a robot to switch between two interaction modes; in one mode, it strictly maintains the side-by-side walking formation, and in another it walks slightly behind its partner. We conducted an evaluation experiment in a real shopping arcade and revealed that our model replicates human side-by-side walking better than other simple methods in which the robot simply moves to the side of a person and without the human tendency for choosing the next appropriate subgoals.