Human-Centered Tech Advances: Bridging Gaps in Communication and Reality

The rapid advancement of human-centered technologies is revolutionizing various aspects of our lives, from disaster response and skill training to social interaction detection and communication for individuals with impairments. Researchers are leveraging augmented reality (AR), artificial intelligence (AI), and multimodal sensing to create innovative solutions that bridge gaps in communication and reality.

One such example is the development of an interactive AR-enabled outdoor scene visualization system for enhanced real-time disaster response (Source 1). This user-centered interface utilizes 3D Gaussian Splatting to visualize detailed scene reconstructions, maintaining situational awareness while keeping cognitive load low. Preliminary evaluations indicate that this design is easy to use and supports real-time coordination, highlighting the value of interaction and Points of Interest (POIs) for fast decision-making.

In a similar vein, researchers have created ViSTAR, a Virtual Skill Training system in AR that supports self-guided basketball skill practice with feedback on balance, posture, and timing (Source 3). ViSTAR provides feedback through visual overlays, rhythm and timing cues, and an AI-powered coaching agent using 3D motion reconstruction. Participants in two studies preferred the AI-generated feedback over coach feedback and reported that ViSTAR helped them improve their skills.

However, as these technologies advance, it is essential to critically examine the values and assumptions underlying their development. A recent position paper (Source 2) reflects on the fundamental values of universality, objectivity, and efficiency in data visualization research, arguing that these values permeate visualization tools, curricula, and research practices. The authors call for a more pluralistic range of values to shape the future of visualization research.

Another area where human-centered technologies are making a significant impact is in social interaction detection. SocialPulse, an on-watch interaction detection system, uses smartwatch multimodal sensing to capture diverse interactions in naturalistic settings (Source 4). The system detected 1,691 interactions in a real-world deployment, with 77.28% confirmed via participant self-reporting.

Lastly, researchers are exploring ways to combine unaided Augmentative and Alternative Communication (AAC) with speech-generated messages to harness the speed and naturalness of unaided AAC while maintaining the intelligibility of aided AAC (Source 5). AllyAAC, a wearable system with a wrist-worn IMU paired with a smartphone app, was developed through participatory design with AAC users. The system produced a dataset containing over 600,000 multimodal data points featuring atypical gestures, highlighting challenges and opportunities in expanding communication for individuals with impairments.

As these technologies continue to evolve, it is crucial to consider the values and assumptions underlying their development, as well as their potential impact on individuals and society. By embracing a more pluralistic range of values and prioritizing human-centered design, researchers can create innovative solutions that bridge gaps in communication and reality, ultimately enhancing our lives and well-being.

Sources:
1. Interactive Augmented Reality-enabled Outdoor Scene Visualization For Enhanced Real-time Disaster Response
2. A Critical Reflection on the Values and Assumptions in Data Visualization
3. ViSTAR: Virtual Skill Training with Augmented Reality with 3D Avatars and LLM coaching agent
4. SocialPulse: On-Device Detection of Social Interactions in Naturalistic Settings Using Smartwatch Multimodal Sensing
5. Giving Meaning to Movements: Challenges and Opportunities in Expanding Communication by Pairing Unaided AAC with Speech Generated Messages