383
Views
43
Downloads
1
Crossref
0
WoS
0
Scopus
0
CSCD
Environmental monitoring plays a critical role in creating and maintaining a comfortable, productive, and healthy environment. Built upon the advancements of robotics and data processing, mobile sensing demonstrates its potential to address problems regarding cost, deployment, and resolution that stationary monitoring encounters, which therefore has attracted increasing research attentions recently. To facilitate mobile sensing, two key algorithms are needed: the field reconstruction algorithm and the route planning algorithm. The field reconstruction algorithm is to reconstruct the entire environment field from spatially- and temporally-discrete measurements collected by the mobile sensors. The route planning algorithm is to instruct the mobile sensors where the mobile sensor needs to move to for the next measurements. The performance of mobile sensors highly depends on these two algorithms. However, developing and testing those algorithms in the real world is expensive, challenging, and time-consuming. To address these issues, we proposed and implemented an open-source virtual testbed, AlphaMobileSensing, that can be used to develop, test, and benchmark mobile sensing algorithms. AlphaMobileSensing aims to help users more easily develop and test the field reconstruction and route planning algorithms for mobile sensing solutions, without worrying about hardware fault, test accidents (such as collision during the test), etc. The separation of concerns can significantly reduce the cost of developing software solutions for mobile sensing. For versatility and flexibility, AlphaMobileSensing was wrapped up using the standardized interface of OpenAI Gym, and it also provides an interface for loading physical fields that were generated by numerical simulations as virtual test sites to perform mobile sensing and retrieving monitoring data. We demonstrated applications of the virtual testbed by implementing and testing algorithms for physical field reconstruction in both static and dynamic indoor thermal environments. AlphaMobileSensing provides a novel and flexible platform to develop, test, and benchmark mobile sensing algorithms more easily, conveniently, and efficiently.
AlphaMobileSensing is open sourced at https://github.com/kishuqizhou/AlphaMobileSensing.
Environmental monitoring plays a critical role in creating and maintaining a comfortable, productive, and healthy environment. Built upon the advancements of robotics and data processing, mobile sensing demonstrates its potential to address problems regarding cost, deployment, and resolution that stationary monitoring encounters, which therefore has attracted increasing research attentions recently. To facilitate mobile sensing, two key algorithms are needed: the field reconstruction algorithm and the route planning algorithm. The field reconstruction algorithm is to reconstruct the entire environment field from spatially- and temporally-discrete measurements collected by the mobile sensors. The route planning algorithm is to instruct the mobile sensors where the mobile sensor needs to move to for the next measurements. The performance of mobile sensors highly depends on these two algorithms. However, developing and testing those algorithms in the real world is expensive, challenging, and time-consuming. To address these issues, we proposed and implemented an open-source virtual testbed, AlphaMobileSensing, that can be used to develop, test, and benchmark mobile sensing algorithms. AlphaMobileSensing aims to help users more easily develop and test the field reconstruction and route planning algorithms for mobile sensing solutions, without worrying about hardware fault, test accidents (such as collision during the test), etc. The separation of concerns can significantly reduce the cost of developing software solutions for mobile sensing. For versatility and flexibility, AlphaMobileSensing was wrapped up using the standardized interface of OpenAI Gym, and it also provides an interface for loading physical fields that were generated by numerical simulations as virtual test sites to perform mobile sensing and retrieving monitoring data. We demonstrated applications of the virtual testbed by implementing and testing algorithms for physical field reconstruction in both static and dynamic indoor thermal environments. AlphaMobileSensing provides a novel and flexible platform to develop, test, and benchmark mobile sensing algorithms more easily, conveniently, and efficiently.
AlphaMobileSensing is open sourced at https://github.com/kishuqizhou/AlphaMobileSensing.
Abdel-Salam MMM (2022). Indoor exposure of elderly to air pollutants in residential buildings in Alexandria, Egypt. Building and Environment, 219: 109221.
Adzic F, Roberts BM, Hathway EA, et al. (2022). A post-occupancy study of ventilation effectiveness from high-resolution CO2 monitoring at live theatre events to mitigate airborne transmission of SARS-CoV-2. Building and Environment, 223: 109392.
Ainiwaer S, Chen Y, Shen G, et al. (2022). Characterization of the vertical variation in indoor PM2.5 in an urban apartment in China. Environmental Pollution, 308: 119652.
Arain MA, Bennetts VH, Schaffernicht E, et al. (2021). Sniffing out fugitive methane emissions: autonomous remote gas inspection with a mobile robot. International Journal of Robotics Research, 40: 782–814.
Awadalla M, Lu TF, Tian ZF, et al. (2013). 3D framework combining CFD and MATLAB techniques for plume source localization research. Building and Environment, 70: 10–19.
Cleveland WS (1979). Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association, 74: 829–836.
Cressie N, Wikle CK (2011). Statistics for Spatio-Temporal Data. New York: John Wiley & Sons.
Deng M, Wang X, Li D, et al. (2022). Digital ID framework for human-centric monitoring and control of smart buildings. Building Simulation, 15: 1709–1728.
Drucker P (1954). The Practice of Management. New York: Harper & Brothers.
Folsom L, Ono M, Otsu K, et al. (2021). Scalable information-theoretic path planning for a rover-helicopter team in uncertain environments. International Journal of Advanced Robotic Systems, 18: 172988142199958.
Geng Y, Yuan M, Tang H, et al. (2022). Robot-based mobile sensing system for high-resolution indoor temperature monitoring. Automation in Construction, 142: 104477.
Hirst B, Jonathan P, González del Cueto F, et al. (2013). Locating and quantifying gas emission sources using remotely obtained concentration data. Atmospheric Environment, 74: 141–158.
Hu Z, Cong S, Song T, et al. (2020a). AirScope: Mobile robots-assisted cooperative indoor air quality sensing by distributed deep reinforcement learning. IEEE Internet of Things Journal, 7: 9189–9200.
Hutchinson M, Oh H, Chen W (2017). A review of source term estimation methods for atmospheric dispersion events using static or mobile sensors. Information Fusion, 36: 130–148.
Jin M, Liu S, Schiavon S, et al. (2018). Automated mobile sensing: towards high-granularity agile indoor environmental quality monitoring. Building and Environment, 127: 268–276.
Kim J, Kim S, Bae S, et al. (2022). Indoor environment monitoring system tested in a living lab. Building and Environment, 214: 108879.
Kowadlo G, Russell RA(2008). Robot odor localization: A taxonomy and survey. International Journal of Robotics Research, 27: 869–894.
Kuroki Y, Young GS, Haupt SE (2010). UAV navigation by an expert system for contaminant mapping with a genetic algorithm. Expert Systems with Applications, 37: 4687–4697.
Laghmich N, Romani Z, Lapisa R, et al. (2022). Numerical analysis of horizontal temperature distribution in large buildings by thermo-aeraulic zonal approach. Building Simulation, 15: 99–115.
Li L, Revesz P (2004). Interpolation methods for spatio-temporal geographic data. Computers, Environment and Urban Systems, 28: 201–227.
Li J, Meng Q, Wang Y, et al. (2011). Odor source localization using a mobile robot in outdoor airflow environments with a particle filter algorithm. Autonomous Robots, 30: 281–292.
Li C, Yoo SJ, Ito K (2023). Impact of indoor ventilation efficiency on acetone inhalation exposure concentration and tissue dose in respiratory tract. Building Simulation, 16: 427–441.
Lu TF (2013). Indoor odour source localisation using robot: Initial location and surge distance matter? Robotics and Autonomous Systems, 61: 637–647.
Lu Y, Wang Z, Liu J, Dong J (2021). Zoning strategy of zonal modeling for thermally stratified large spaces. Building Simulation, 14: 1395–1406.
Mardia KV, Goodall C, Redfern EJ, et al. (1998). The Kriged Kalman filter. Test, 7: 217–282.
Morawska L, Thai PK, Liu X, et al. (2018). Applications of low-cost sensing technologies for air quality monitoring and exposure assessment: how far have they gone? Environment International, 116: 286–299.
Nielsen PV (2015). Fifty years of CFD for room air distribution. Building and Environment, 91: 78–90.
Ristic B, Gunatilaka A (2008). Information driven localisation of a radiological point source. Information Fusion, 9: 317–326.
Ristic B, Skvortsov A, Walker A (2014). Autonomous search for a diffusive source in an unknown structured environment. Entropy, 16: 789–813.
Singla S, Bansal D, Misra A, et al. (2018). Towards an integrated framework for air quality monitoring and exposure estimation—a review. Environmental Monitoring and Assessment, 190: 562.
Song J, Han K, Stettler MEJ (2021). Deep-MAPS: Machine-learning-based mobile air pollution sensing. IEEE Internet of Things Journal, 8: 7649–7660.
Sundell J (2004). On the history of indoor air quality and health. Indoor Air, 14(Suppl 7): 51–58.
Wang Z, Chen B, Li H, et al. (2021). AlphaBuilding ResCommunity: A multi-agent virtual testbed for community-level load coordination. Advances in Applied Energy, 4: 100061.
Wu Y, Liu H, Li B, et al. (2021). Individual thermal comfort prediction using classification tree model based on physiological parameters and thermal history in winter. Building Simulation, 14: 1651–1665.
Xie X, Semanjski I, Gautama S, et al. (2017). A review of urban air pollution monitoring and exposure assessment methods. ISPRS International Journal of Geo-Information, 6: 389.
Yang T, Zhao L, Li W, et al. (2021a). Towards healthy and cost-effective indoor environment management in smart homes: A deep reinforcement learning approach. Applied Energy, 300: 117335.
Yang Y, Liu J, Wang W, et al. (2021b). Incorporating SLAM and mobile sensing for indoor CO2 monitoring and source position estimation. Journal of Cleaner Production, 291: 125780.
Yokoyama H, Ooka R, Kikumoto H (2018). Study of mobile measurements for detailed temperature distribution in a high-density urban area in Tokyo. Urban Climate, 24: 517–528.
This work was supported by the Project of Autonomous Cruise UVC Disinfection and Microclimate Air-conditioning Robot Topic#3 Thermal Management for the UVC LED Disinfection Robotics (FSUST21-SHCIRI07C). This work was supported in part by the Project of Hetao Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone (HZQB-KCZYB-2020083).