A Review of Verbal and Non-Verbal Human-Robot Interactive Communication (1401.4994v1)

Abstract: In this paper, an overview of human-robot interactive communication is presented, covering verbal as well as non-verbal aspects of human-robot interaction. Following a historical introduction, and motivation towards fluid human-robot communication, ten desiderata are proposed, which provide an organizational axis both of recent as well as of future research on human-robot communication. Then, the ten desiderata are examined in detail, culminating to a unifying discussion, and a forward-looking conclusion.

• The paper articulates ten desiderata outlining key requirements for advanced human-robot communication, from mixed initiative dialogue to affective interaction.
• It reviews historical developments in robotic communication, tracing progress from early systems to modern socially engaging machines.
• The study identifies future challenges such as real-time language processing, multimodal integration, and data-driven improvements in communicative robots.

Overview of Human-Robot Interactive Communication

The paper "A Review of Verbal and Non-Verbal Human-Robot Interactive Communication" by Nikolaos Mavridis provides a comprehensive examination of the field of human-robot interaction (HRI), focusing on both verbal and non-verbal communication aspects. The paper presents a historical context for human-robot communication, describes key challenges, and outlines ten desiderata that serve as both a reflection on past research and a prospectus for future developments.

Historical Context and Motivation

The historical review underscores the evolution of robots from mythological constructs to industrial entities and, more recently, to socially interactive machines. The paper traces advances in natural language conversational robots beginning in the 1990s, noting early examples like MAIA, RHINO, and AEOSOP. These systems were pioneering yet limited in their communicative capabilities. The evolving need for robots that can engage in more sophisticated, natural interactions with humans—moving beyond mere command-response interactions—frames the central motivation of the paper.

Ten Desiderata for Human-Robot Communication

The central contribution of the paper is the articulation of ten desiderata that highlight the necessary features and capabilities for advanced human-robot communication:

1. Breaking the Simple Commands Barrier: Systems should advance beyond basic command-following capabilities to support more complex interactions.
2. Multiple Speech Acts: The inclusion of diverse speech acts, beyond simple directives, is critical for nuanced communication.
3. Mixed Initiative Dialogue: Robots should engage in dialogues that allow for reciprocal exchange, where both parties can take initiative.
4. Situated Language and Symbol Grounding: The connection between language and the physical world through contextual and sensory grounding is emphasized, addressing the symbol grounding problem.
5. Affective Interaction: Recognition and generation of affective cues are crucial for empathetic interactions.
6. Motor Correlates and Non-Verbal Communication: The integration of verbal communication with gestures, gaze, and other non-verbal cues forms a comprehensive interaction repertoire.
7. Purposeful Speech and Planning: Communication should be goal-oriented, integrating dialogue planning with motor actions.
8. Multi-Level Learning: Robotic systems should be capable of learning at multiple stages, from offline design time to online real-time interactions.
9. Utilization of Online Resources and Services: By tapping into internet-based resources, robots can enhance their communicative abilities and knowledge.
10. Miscellaneous Abilities: These include understanding multiple conversational partners, supporting multilingual communication, and utilizing various modalities for natural language processing.

Implications and Future Directions

The paper identifies areas where human-robot communication is poised for significant growth, with challenges like real-time language processing, affective dialogue systems, and the integration of online services remaining pivotal. The prospect of deploying robots in real-world environments for mass data collection is suggested as a promising avenue for advancing data-driven communication models. Embracing these challenges could lead to robots seamlessly integrating into human environments, contributing meaningfully to societal goals.

In conclusion, while human-robot communication has made significant strides, the paper articulates that there remains substantial scope for research and innovation. The ten desiderata serve as a framework guiding future inquiry and development, aiming towards a future where human-robot interactions are as natural and fluid as human-human exchanges.