Dear Friends and Affiliates,
With the start of the fall quarter on September 26 right around the corner, we are preparing for the CARS Annual Meeting. Please save the date for Monday, November 13 for an afternoon meeting starting with lunch at noon for the annual meeting at VAIL. We look forward to seeing you on campus and getting your input and feedback on a Sustainable Mobility Initiative we are developing along with the EV50 affiliate program that would look at four facets of sustainability: energy systems, urban infrastructure, safety and economics.
Please join us for the next CARS webinar on The Potential of Autonomous Vehicles in Future Transportation Systems on October 19 at noon PDT with CARS Fellow Ruolin Li, postdoctoral scholar in Marco Pavone's Autonomous Systems Lab. Ruolin will present her research which showcases the potential of autonomous vehicles to enhance transportation systems' efficiency and improve overall societal benefits. View the agenda here and join the webinar here.
Rohan Sinha, PhD candidate in the Autonomous Systems Lab presented a mini-class on Avoiding failures in ML-enabled systems: Tutorial on Runtime Monitoring and Contingency Planning. Rohan covered several state-of-the-art approaches to runtime monitoring of ML components alongside their respective strengths and weaknesses. The mini-class video recording is available here.
Sincerely,
Adele Tanaka
CARS Associate Director
|
|
|
|
Students from the Stanford Solar Car Project continued work over the summer on their latest vehicle, Azimuth, shown above as they work on the electrical system and battery packs. They presented their progress at the summer Stanford Undergraduate Research Institute poster session. |
|
|
October 19, 2023
CARS Webinar
12:00 pm - 1:00 pm PDT
|
|
The Potential of Autonomous Vehicles in Future Transportation Systems with Ruolin Li
CARS Fellow, Ruolin Li, postdoctoral scholar in the Autonomous Systems Lab, leads the next webinar on alleviating congestion by introducing autonomous vehicles into transportation systems and the importance of considering interactions between human and autonomous agents and to develop suitable control strategies. View the agenda here and join us on Zoom here. |
|
|
|
|
To improve EV batteries, study them on the road
Adding real-world driving data to battery management software and computer models of battery pack performance can lead to longer-lasting, more reliable batteries. Link
|
|
|
|
|
|
Battery material predicted by AI shows promise in the lab
A new paper concludes a seven year journey by the paper's co-author Austin Sendek, whose AI algorithms identified a promising new material for better batteries. A compound known as "LBS" has shown it can hold high levels of electricity without breaking down. Link
|
|
|
|
|
|
New paint gives extra insulation, saving on energy, costs, and carbon emissions
Stanford scientists have invented a new kind of paint that can reduce the need for both heating and air conditioning in buildings and other spaces, such as trains and trucks for refrigerated cargo. Link
|
|
|
|
|
|
Clean vehicle tax credit: The new industrial policy and its impact
A new SIEPR Policy Brief explains and evaluates how the Clean Vehicle Tax Credit in the Inflation Reduction Act (IRA) works and evaluates it from an industrial policy perspective. Link
|
|
|
|
|
|
Resilient Power Grids
A new Stanford study finds low-income communities in California have a disproportionate share of fire-prone overhead lines and proposes a way to equitably allocate the cost of moving more lines underground. Link
|
|
|
|
|
|
We Must Pass the Create AI Act
The CREATE AI Act (Creating Resources for Every American to Experiment with Artificial Intelligence Act) was introduced by both sides of the U.S. Congress last month. The bill would establish a national AI research resource to provide access to much-needed compute and datasets for academics, nonprofit researchers, and startups. Link
|
|
|
|
Avoiding failures in ML-enabled systems: Tutorial on Runtime Monitoring and Contingency Planning
Rohan Sinha, PhD candidate in the Autonomous Systems Lab will examine runtime monitoring as a paradigm to detect when an autonomous system operates outside its region of competence – its operational design domain (ODD) – and design methods to safely transition to a minimal risk condition. Please join us on July 20 at noon for the next CARS mini-class. View the mini-class recording here.
|
|
|
|
|
Transformers for Robotics: Architectural Concepts and Applications
This tutorial with Edward Schmerling, robotics researcher with the Autonomous Systems Lab. Schmerling will aim to answer questions at a conceptual level: what are transformers, what problems do they solve, and what applications in robotics, autonomous vehicles, operations research, and numerous other fields beyond their marquee use-case of natural language processing, may be amenable to their deployment? View the mini-class recording here and the slide presentation here.
|
|
|
|
Tutorial on Graph Reinforcement Learning: RL, Graph Neural Networks, and Applications to Mobility
Daniele Gammelli, postdoctoral scholar in the Autonomous Systems Lab, led this tutorial to introduce core concepts in the fields of Deep Reinforcement Learning and Graph Neural Networks from the ground up. By the end of the tutorial we will have introduced modern (graph-)reinforcement learning methods, and how to apply them in practice through a case study on intelligent transportation systems. View the mini-class recording here and the shared code material here.
|
|
|
For questions, please contact Adele Tanaka at adelet@stanford.edu.
|
|
|
|
|
|
|
