Links of the week #15

Automotive

• Unreliable Pedestrian Detection and Driver Alerting in Intelligent Vehicles , by Missy Cummings . From the abstract : "These intelligent vehicles also detected the pedestrian earlier if there were no established lane lines, suggesting that in well-marked areas, typically the case in for established crossings, pedestrians may be at increased risk of a possible conflict."

• Waymo’s Robotaxis Are Hitting The Highway, A First For Self-Driving Cars. At least there are no pedestrians on highways :)

• The January issue of ADAS & Autonomous Vehicle is out

• CAN bus in 2024: Operation, Advantages and Recent Developments , wirtten by Samba Ndome

AI

• New material found by AI could reduce lithium use in batteries (via Ivan Wilson ). We will probably hear dozens of similar stories in the coming years before such solutions come to production, but this is still exciting :)

• https://github.com/jupyterlab/jupyter-ai (via Khuyen Tran ), bringing generative AI in JupyterLab

Robotics

• You Should Log More , by Davide Faconti . It's always a pleasure to watch Davide's talks :) In this one he promotes DataTamer , a work in progress library for "fearless numerical logging".

• Capella MBSE Integration for Robotic Arm Development , video of a presentation during the latest Capella Days. I'm afraid that the screen capture visible at t=6'48 and reproduced below may frighten even motivated people :) But it's pretty rare to see robotics companies dive into MBSE, so ... let's dive with them !

• Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis . A paper with an impressive casting (Carnegie Mellon, Bosch, FAIR, DeepMind among others) that is too much involved for my level of understanding. But surveys are always worth reading ... even for the tiny bits we can figure out :)

Structural mechanics

• Implicit Modeling in Altair Inspire (via Ken Welch )