The head created by SSSA and Robotech is the advanced HRI interface in TAXI missions. It can be used to select destinations and to interact with the user (detect load and unload, stop and resume, etc) while carrying him to the destination.

The supervisor and task allocation modules integrated in Romeo communicate with the head for accomplishing the interactions.

This video shows several ideas and situations about Romeo (developed by AICIA) navigating in urban environments.

First, the low level navigation architecture is shown. Romeo uses a combination of behaviors, trying to follow the path given by the path planner while at the same time avoiding the obstacles from a priori map, and the ones detected by the sensors on board.

Romeo basically carries 4 laser rangefinders: three deployed in the front and sides of the robot, and one on the top of the roof (tilted with respect to the horizontal).

From the lasers, different kind of obstacles can be identified, as shown in the video.

The video shows Romeo avoiding another robot of the fleet (Tibi), a group of persons in a given meeting and also other persons present on the campus.

It can be also seen the limitations of a non-holonomic vehicle. As the maximum turning radius is limited, Romeo cannot reach all the points in the scenario without maneouvers and replanning. It can be seen a situation in which a set of stopped robots restrict the space available; therefore, Romeo tries to follow the path through a secondary way, until it gets stuck. The robots stops automatically, and warns the higher levels of the situation.

The video shows Romeo in a WP8 Experiment. The objective is to act as a TAXI for a given person. The taxi service can be requested through a mobile phone.

When a TAXI is requested, the robot is first directed to a taxi station, where the user is loaded. Then, the user is carried to the desired destination. An human-robot interaction interface allows to now when the person is on board and the destination (as a set of places of interest). Moreover, the interface allows the user to stop and resume the robot at any moment. A simple version of the interface can be observed in the video, using a touch screen.

The mission described here involves several tasks, covering two fully autonomous taxi missions performed without any stop.

The formation movement control is based on a virtual structure composed by spring-dampers elements, which allows the formation to comply with the environment shape. A different navigation strategy is applied to the leader of the formation and to the rest of robots of the team. The leader plans the trajectories by using a two-level path planner with obstacle avoidance capabilities. The motion of the follower robots is controlled by the virtual structure, which adapts to the environment while the leader is tracked, taking into account the kinodynamic constraints of the vehicles