HOTSPOT: An Ad Hoc Teamwork Platform for Mixed Human-Robot Teams

Ad hoc teamwork is a research topic in multi-agent systems whereby an agent (the "ad hoc agent") must successfully collaborate with a set of unknown agents (the "teammates") without any prior coordination or communication protocol. However, research in ad hoc teamwork is predominantly focused on agent-only teams, but not in agent-human teams, which we believe is an exciting research avenue and has enormous application potential in human-robot teams. This paper will tap into this potential by proposing HOTSPOT, the first framework for ad hoc teamwork in human-robot teams. Our framework comprises two main modules, addressing the two key challenges in the interaction between a robot acting as the ad hoc agent and human teammates. First, a <i>decision-theoretic module</i> that is responsible for all task-related decision making (task identification, teammate identification, and planning). Second, a <i>communication module</i> that uses natural language processing in order to parse all communication between the robot and the human. To evaluate our framework, we use a task where a mobile robot and a human cooperatively collect objects in an open space, illustrating the main features of our framework in a real-world task.

HOTSPOT: An Ad Hoc Teamwork Platform for Mixed Human-Robot Teams

Ad hoc teamwork is a research topic in multi-agent systems whereby an agent (the "ad hoc agent") must successfully collaborate with a set of unknown agents (the "teammates") without any prior coordination or communication protocol. However, research in ad hoc teamwork is predominantly focused on agent-only teams, but not in agent-human teams, which we believe is an exciting research avenue and has enormous application potential in human-robot teams. This paper will tap into this potential by proposing HOTSPOT, the first framework for ad hoc teamwork in human-robot teams. Our framework comprises two main modules, addressing the two key challenges in the interaction between a robot acting as the ad hoc agent and human teammates. First, a <i>decision-theoretic module</i> that is responsible for all task-related decision making (task identification, teammate identification, and planning). Second, a <i>communication module</i> that uses natural language processing in order to parse all communication between the robot and the human. To evaluate our framework, we use a task where a mobile robot and a human cooperatively collect objects in an open space, illustrating the main features of our framework in a real-world task.

Attributing Blame in Human-Robot Teams with Robots of Differing Appearance

As automation becomes increasingly common in daily life the importance of understanding how we interact with automated systems increases, especially attribution of blame for accidents involving a human-automation team. The current research project looks at how humans attribute blame in an accident involving a human operator and a robot worker and is based on a previous study (Furlough et al., 2019). Participants will read two scenarios detailing an accident while being shown both the operator and robot. The robot’s appearance is manipulated to imply varying levels of automation, ranging from a simple robot to one with a human appearance. Results showed no significant effects, however, this research still has the potential to contribute to the understanding of interactions between humans and automated systems and could inform design in the future to facilitate a positive working environment with robots and humans.