HRI 2022 Workshop on Joint Action, Adaptation, and Entrainment in Human-robot interaction

overview

Research in joint action focuses on the psychological, neurological, and physical mechanisms by which humans collaborate with other agents, and overlaps with several domains related to human-robot interaction.

The development of artificial systems that can support or emulate the requisite aspects of joint action could lead to improved human-robot team performance as well as improvements in subjective metrics (e.g., trust).

This workshop highlights theoretical and technical considerations about human-robot joint action and real-time adaptation, with a particular focus on socio-motor entrainment, showing how the emulation of psychological mechanisms (e.g., emotion, intention signaling, mirroring) can lead to improved performance.

We have invited speakers with backgrounds in robotics, neuroscience and psychology, as well as speakers with a focus in adjacent works, such as in human-robot coordinated dance, alignment, or synchronization. We call for papers that utilize the theory of joint-action in an interactive human-robot context. We also call for position papers on the application of the theory of joint action to robotics, with a heavy focus on psychological mechanisms that could potentially be emulated or adapted to a human-robot context. Participants will have the opportunity to brainstorm considerations and techniques that would be applicable to joint action inspired works through breakout sessions with the aim to lead to new and improved collaborations across fields.

The workshop will take place on Monday March 7th, 2022 from 9am to 6pm EST.

details

This workshop intends to highlight techniques and considerations for human and robot joint action, with an additional focus on socio-motor entrainment showing how the emulation of psychological mechanisms can lead to improved performance. The workshop will highlight three themes: joint action, adaptation, and entrainment. These perspectives will be explored from the viewpoints of roboticists, neuropsychologists, and cognitive psychologists. The workshop will also have opportunities for cross collaboration in the form of interactive breakout sessions.

Major Themes:

  • Joint Action in humans has been studied extensively in psychology to model the fundamental cognitive and behavioral mechanisms enabling interaction, cooperation and coordination in collaborative tasks [1,2,3]. Processes such as joint attention, entrainment, task co-representation, adaptation, and anticipation occur naturally in human-human joint actions [4] while emotion has also been highlighted as a key consideration that enables such joint actions [5]. In robotics, the theory of joint action has been adopted to solve a plethora of problems that arise in human-robot-interaction (HRI) tasks. From examining role assignment policies for human–robot joint motor action, human action and intention detection to shared control, force control, human-robot teaming, and human-robot handovers; the theory of joint action has been shown to be an appropriate model for HRI [4, 6]. In this theme, we seek to showcase latest results and insights from research in human-human and human-robot joint action, from psychologists, neuroscientists and roboticists, in order to bridge the gap between the fields and promote tighter collaboration.

  • Adaptation: this extends the discussion in the earlier theme by focusing on adaptation in joint action; a critical component in human-robot interaction for which insights could be invaluable. To effectively collaborate, humans and animals are often adapting and co-adapting to changes in environmental, cognitive, and physical processes. For robots to seamlessly collaborate with humans, such adaptive and co-adaptive behaviors must be the basis of any interaction scenario. Research from the robotics community as well as neuroscience and psychology, have extensively explored mechanisms, organizational principles, and architectures that can express adaptive behaviors in computational, physical, or mathematical models in both biological as well as autonomous artificial systems. In this theme, we seek to explore the current challenges in the cognitive, behavioral and engineering sciences to better understand the role of adaptation in human-robot interactive systems. Topics of interest can include (but not limited to): adaptation in perception and motor control, embodied cognition, learning, neural mechanisms of adaptation and co-adaptation, decision making, mechanical and cognitive adaptation in robotic systems, etc.

  • Examples of Insights from Joint Action (e.g. Entrainment): in this theme, we wish to explore examples of insights from joint action, with entrainment as an example that could lead to improved human robot collaboration. Entrainment is a general term describing temporal coordination of individuals, with experimental evidence suggesting that it is extremely hard to resist [3]. More specifically, entrainment is the process that leads to the synchronization of two collaborating individuals, even ``in the abscence of a direct mechanical coupling'' [7]. This theme is not limited to entrainment, but can include additional examples of insights that lead to improved interaction. Much of the work on the subject within the HRI community has been limited to lexical entrainment [8,9], rhythmic group actions (e.g. dance) [10], or rhythmic, combined actions [11]. However, the scope of entrainment (or the resultant synchronization) could be much larger; applying to more complex tasks, dynamic group behaviors, or abstract rhythmic interactions. In this workshop, we wish to highlight entrainment as an example of an insight from joint action that, in itself, could lead to improved human-robot collaboration. It stands to reason that this process could lead to improvements in human-robot coordination, improving objective metrics of human-robot teaming (such as fluency [12]), and potentially improving efficiency of tasks.

Workshop format

We have invited speakers with backgrounds in both robotics and psychology. We have also invited speakers with a focus in adjacent works, such as in human-robot coordinated dance, alignment, or synchronization.

The workshop will have an interactive component. Participants will brainstorm considerations and techniques that would be applicable to joint action inspired works that could also lead to new and improved collaborations. We call for papers that utilize the theory of joint-action in an interactive human-robot context. We will all for position papers on the application of the theory of joint action to robotics, with a heavy focus on psychological mechanisms that could potentially be emulated or adapted to a human-robot context.