From Invisible to Actionable: Augmented Reality Interactions with Indoor CO2

TL;DR

This work tackles the invisibility of indoor CO2 by coupling a wrist-worn CO2 sensor (CoWear) with a smartphone AR interface that visualizes local CO2 as bubbles in 3D space. Through a mixed-methods study with 35 participants, the authors demonstrate that AR visualization increases awareness and motivates concrete ventilation actions, leading to substantial CO2 reductions compared with a baseline 2D heatmap. Key contributions include a wearable sensor design, an AR grounding method with 3D spatial anchoring, a personified visualization of CO2 bubbles, and a game-like interaction that incentivizes ventilation. The approach shows practical potential for improving indoor air quality and occupant engagement, while also acknowledging trade-offs with thermal comfort and the need for future extensions to other pollutants and multi-user scenarios.

Abstract

Indoor carbon dioxide (CO2) can rapidly accumulate to form invisible pollution hotspots, posing significant health risks due to its odorless and colorless nature. Despite growing interest in wearable or stationary sensors for pollutant detection, effectively visualizing CO2 levels and engaging individuals remains an ongoing challenge. In this paper, we develop a portable wrist-sized pollution sensor that detects CO2 in real time at any indoor location and reveals CO2 bubbles by highlighting sudden spikes. In order to promote better ventilation habits and user awareness, we also develop a smartphone-based augmented reality (AR) game for users to locate and disperse these high-CO2 zones. A user study with 35 participants demonstrated increased engagement and heightened understanding of CO2's health impacts. Our system's usability evaluations yielded a median score of 1.88, indicating its strong practicality.

Figures (12)

• Figure 1: The responders of the prestudy (a) agree that CO2 is harmful, but (b) most of them have never measured indoor pollutants. (c) Awareness about indoor pollutants -- response to a false statement about indoor CO2 standards.
• Figure 2: (a) Effectiveness of different ventilation methods in a family gathering, as perceived by the responders. (b,c) Perception of the responders on (b) the fact that the general population is unaware of indoor pollution and (c) their confidence in reducing the pollution through a visualization method. The survey indicates the need for effective pollution visualization, like an AR-based solution.
• Figure 3: CO2 distribution at various locations of a room at different heights. [G] represents ground height, [T] represents table height, and [C] represents ceiling height. The CO2 concentration increases over time with the occupancy level of the room without ventilation (i.e., window ventilator is turned on at time $t$) - (a) three-person occupancy at $t$-60 minutes, (b) four-person occupancy at $t$-30 minutes, (c) seven-person occupancy at $t$, maximal CO2 concentration of $1635$ ppm in bottom-left corner, window ventilator is turned on for ventilation. Occupants leave the room. CO2 distribution when the room is - (d) ventilated for 30 minutes, (e) ventilated for 60 minutes. We observe that CO2 accumulates and gets trapped in corners of the room at source height (i.e., occupants, table height). Lastly, (f) Turned on the stand fan from the bottom-right corner towards the top-right corner, reducing accumulated CO2 in the bottom-right corner. Thus, targeted airflow can reduce trapping of CO2 in specific areas of the room (e.g., corners).
• Figure 4: CoWear wrist-wearable.
• Figure 5: Augmented reality application - green bubble represents less CO2 concentration, relatively larger yellow bubble represents moderate CO2 concentration, and the largest red bubble represents more than $2000$ ppm CO2 concentration. The bubbles' color and diameter vary according to the sensor readings (i.e., $400$ ppm $\Rightarrow$ green, $0.2$m bubble, and $3000$ ppm $\Rightarrow$ red, $1.5$m bubble).