Mixed-Initiative Human-Robot Interaction: Definition, Taxonomy, and Survey

Abstract

The objectives of this article are: 1) to present a taxonomy for mixed-initiative human-robot interaction and 2) to survey its state of practice through the examination of past research along each taxonomical dimension. The paper starts with some definitions of mixed-initiative interaction (MII) from the perspective of human-computer interaction (HCI) to introduce the basic concepts of MII. We then synthesize these definitions to the robotic context for mixed-initiative humanrobot teams. A taxonomy for mixed-initiative in human-robot interaction is then presented. The goal of the taxonomy is to inform the design of mixed-initiative human-robot systems by identifying key elements of these systems. The state of practice of mixed-initiative human-robot interaction is then surveyed and examined along each taxonomical dimension.

Swarm Intelligence and cyber-physical systems: Concepts, challenges and future trends

“…Enabling human interactions with the swarm system [209,210] can provide a number of advantages since the CPS can potentially exploit humans' cognitive and sensory-motor capabilities, and, vice versa, human agents can use the CPS in closed loop interaction as an augmented external sensor-actuator system. The design and implementation of such mixed initiative systems [211] brings a number of scientific and technological challenges, ranging from how the interaction is physically performed in both directions (from single CPSs or CPS swarms to humans and vice versa), to how (and with which frequency) the complex state of the (distributed) CPS is presented to the human, to how the information or the commands from the human are disseminated to the CPS swarm. A lot of research interest has focused on developing interfaces and modalities for bidirectional interaction and dialogue, considering for instance the use of different multi-modal interfaces [168,212,213,214] for proximal interaction with the swarm.…”

A Taxonomy for Characterizing Modes of Interactions in Goal-driven, Human-robot Teams

“…(By physical situatedness, we mean an understanding about each other's perception of the environment; by cognitive situatedness we mean understanding about each other's goals, plans and mission status.) Finally, the level of information abstraction also depends upon the relevance of one interactants state to that of the other ( [6], [13]). This relationship can be assessed along the dimensions of goal and task dependency, as outlined in our dynamics taxonomy.…”

Robotics in the Modern World of Work - Results From an Empirical Study Regarding Business Ethics

“…to creation of new jobs, higher productivity and flexibility as well as reduced costs. In addition, the improvement of health and life quality are viewed as a positive effect of using robots especially in routinedominated or dangerous work places [16,36]. On the other hand, replacement of human labour especially of untrained workers by AI and robots as well as an increase in income equality are seen as the biggest threats [6,11,24,26].…”