We rejected a stack of candidates on a feeling. I liked that it felt fair, right up until one of them asked me to explain a rejection and I could not. That was the whole problem. Not that I was…
Twice a year we drive home. Same route, same border crossings, same question in the queue: should we have left a day earlier? Nobody knows. I wanted to know which day and hour were best at each crossing. A navigation…
The visuo-tactile sensor uses TacSL [Akinola2025] to simulate sensors such as GelSight. It produces tactile RGB images and force fields for manipulation tasks. To use the tactile sensor in a simulation environment, run the example: --contact_object_type: Specify the type of contact object…
Train a gear-insertion policy in Isaac Lab, then deploy it with Isaac ROS and a custom inference node. The training setup uses domain randomization to account for differences between simulation and hardware. Universal Robots UR10e: 6-DOF industrial robot arm with Robotiq…
Small businesses in the USA are not hiring more people in 2026. They are hiring AI. I call it the $500 AI Employee. It costs around $500 per month and does the work of 3 full time employees. Here is how smart US startups…
The adaptive reuse of historic hospitals requires comparing prospective functions against inherited architectural configurations, heritage constraints and contextual conditions, often under incomplete documentation. This study develops and internally verifies HARP v1.1, a hospital-specific rule-based decision-support framework designed to make preliminary reuse…
From Quiet Streets to Visible Depth: A VR Vision Workout When the streets of Paris, Lyon,... Tagged with digital, software. #from-quiet-streets-to-visible-depth-a-vr-vision-workout From Quiet Streets to Visible Depth: A VR Vision Workout When the streets of Paris, Lyon, and Marseille froze…
It was the last week of July 2026. I had just flown back from India, I was jet-lagged, and at 10 PM I opened X. When I put the phone down it was 1:15 AM. The next morning I drove to work on too…
This set of codes/data implements our TPEC paper “Net Load Forecasting with Renewable Capacity Features: A Comparison of Direct and Indirect Neural Network Methods”. The indirect methods predict total load, solar generation, and wind generation separately, then calculate: All…
Multiple ML models are implemented for ERCOT short-term load forecasting, using weather and time features. Multiple variations of the above ML models are trained and evaluated. Raw weather data are from the Phase 2 of the North American Lan Data Assimilation…
Exploratory testing, bug triage, traceability, and release readiness.