Ray Tracing-based Light Energy Prediction for Indoor Batteryless Sensors
summary
Solacle predicts indoor light-harvesting capability at any location by combining ray tracing with a gradient-free optimization that fits room optical properties from measured data. It uses LiDAR scans from iPhone/iPad Pro to build 3D geometry and collects power traces with solar-powered BLE sensors to estimate illuminance and luminous efficacy. The implemented system runs exhaustive placement queries, shows high accuracy across varied positions and orientations in controlled tests, and successfully predicts energy in two real spaces (one requiring a manually modeled lobby).
AI-written summary · about
related talks
25mFrom seed to store: AI to optimize the indoor farms of the future
48mIdentification of Building Thermal Model - Using Data
28mDiscussion: Humans As Sensors
47mOpen-Source Energy Storage Management Tools from DOE
22mUsing big data from RF monitoring...
45mPanel Discussion: Cost-Effective and Scalable Measurement of On...
06mRISC: Resource-Constrained Urban Sensing Task Scheduling Based on Commercial Fleets
46mML Use Cases at Think Big Analytics