Recent years have witnessed a profound transformation in the use of intelligent technology in our daily lives. This technology is now a ubiquitous reality that provides us with personal assistants deployed in several platforms, ranging from small devices, such as smart phones, smart watches and smart speakers, to domestic robots, such as Roomba and Pepper.

In a near future, people will inhabit intelligent physical environments endowed with ambient intelligence and populated with smart devices and robots. As the number of robots continue to increase, we expect to see robots interacting more and more with a variety of other robots and humans. In many of these interactions, the robots may share the same goal and consequently cooperate to perform a task. However, many robots may not have coordination and standard communication protocols, because they have been designed by different developers and at different times.

Ad hoc teamwork [Sto+10] is a research topic that aims to address the aforementioned problem. This research community focuses on building learning agents, such as softbots or robots, that engage in cooperative tasks with other unknown agents, without relying on any predefined coordination strategy and communication protocols.

However, many works within the ad hoc teamwork literature use simple scenarios that are not close to effective deployment situations. In particular, none of these research works are tailored for human-robot interactions due to several limitations. For example, many works rely on the following assumptions: (i) the robot knows its role and the target task in advance, (ii) the robot can observe the teammates’ actions, (iii) the robot can fully observe the states, (iv) the environment provides a reward signal to the robot. These assumptions, however, are rarely true in real-world scenarios with human and robots. For instance, human-robot interaction settings may have (i) humans that cannot communicate the intended task to the robot, (ii) robots that are not capable of observing the teammates’ actions, (iii) robots that cannot fully observe the states, and (iv) interactions that do not generate an implicit/explicit reward signal.

We thus believe that ad hoc teamwork in the presence of human teammates is one of the most promising applications for this research topic; however, it largely remains to be explored. We envisage an exciting research work that explores the challenges that the collaborative interaction between robots and humans pose in terms of decision making, which is the key goal of the HOTSPOT project.