Skip to main content
NVIDIA AI Podcast

Safer, Faster Public Transportation: AC Transit’s AI-Powered Upgrade with Hayden AI - Ep 290

29 min episode · 2 min read
·
Asan Baig,Marty Beard

Episode

29 min

Read time

2 min

Topics

Leadership, Design & UX, Artificial Intelligence

AI-Generated Summary

Key Takeaways

  • Automated enforcement accuracy: Legacy manual systems at AC Transit required operators to press a button to photograph violations, yielding under 5% citation success. Switching to Hayden AI's edge-based computer vision system—targeting over 90% accuracy—eliminated operator distraction and dramatically increased enforceable citation rates by automating the entire capture-to-review workflow.
  • Edge AI architecture for mobile enforcement: Hayden's system runs entirely on NVIDIA edge hardware installed inside buses, not in the cloud. Cameras mounted behind windshields feed a compact onboard control unit running AI algorithms that detect vehicles in restricted zones, assess dwell time, and package violation evidence for transmission—all while the bus moves through its route.
  • Privacy-by-design as a policy requirement: To gain board approval and comply with California AB 917, AC Transit required that no facial data or personal identifiers be retained. The system captures only vehicle license plates under defined parameters, stores nothing on the edge device after transmission, and Hayden retains no identity information—making privacy architecture a non-negotiable procurement criterion.
  • Pilot-to-scale procurement model for public agencies: AC Transit began with a five-bus proof of concept before seeking board approval for full deployment. This structured POC approach—evaluating image quality, lighting conditions, cybersecurity, and citation accuracy simultaneously—allowed a public agency with elected oversight to validate ROI before committing budget, reducing institutional risk on unproven technology.
  • Measurable transit performance gains: Within the 100-bus pilot, AC Transit recorded a 70% reduction in repeat first-time offenders blocking dedicated lanes and bus stops, alongside measurable improvements in on-time performance and ADA accessibility. These KPIs are being compared against historical baselines to build the legislative case for renewing AB 917 before its 2027 expiration.

What It Covers

AC Transit CTO Asan Baig and Hayden AI CEO Marty Beard detail how NVIDIA-powered edge AI cameras mounted inside East Bay buses automatically detect and process bus lane and bus stop violations, replacing a manual system that achieved under 5% citation success rates across AC Transit's 55–57 million annual riders.

Key Questions Answered

  • Automated enforcement accuracy: Legacy manual systems at AC Transit required operators to press a button to photograph violations, yielding under 5% citation success. Switching to Hayden AI's edge-based computer vision system—targeting over 90% accuracy—eliminated operator distraction and dramatically increased enforceable citation rates by automating the entire capture-to-review workflow.
  • Edge AI architecture for mobile enforcement: Hayden's system runs entirely on NVIDIA edge hardware installed inside buses, not in the cloud. Cameras mounted behind windshields feed a compact onboard control unit running AI algorithms that detect vehicles in restricted zones, assess dwell time, and package violation evidence for transmission—all while the bus moves through its route.
  • Privacy-by-design as a policy requirement: To gain board approval and comply with California AB 917, AC Transit required that no facial data or personal identifiers be retained. The system captures only vehicle license plates under defined parameters, stores nothing on the edge device after transmission, and Hayden retains no identity information—making privacy architecture a non-negotiable procurement criterion.
  • Pilot-to-scale procurement model for public agencies: AC Transit began with a five-bus proof of concept before seeking board approval for full deployment. This structured POC approach—evaluating image quality, lighting conditions, cybersecurity, and citation accuracy simultaneously—allowed a public agency with elected oversight to validate ROI before committing budget, reducing institutional risk on unproven technology.
  • Measurable transit performance gains: Within the 100-bus pilot, AC Transit recorded a 70% reduction in repeat first-time offenders blocking dedicated lanes and bus stops, alongside measurable improvements in on-time performance and ADA accessibility. These KPIs are being compared against historical baselines to build the legislative case for renewing AB 917 before its 2027 expiration.

Notable Moment

Baig revealed that California's AB 917 legislation—which authorizes automated bus lane enforcement—expires in 2027, meaning AC Transit must continuously supply performance data to lawmakers to justify renewal. The technology's legal existence depends on proving measurable public benefit on an ongoing basis.

Know someone who'd find this useful?

Episode Transcript

Welcome to the NVIDIA AI podcast. I'm Noah Kravitz. Join us at the world's premier AI conference. GTC San Jose is online and in person, March 16 through the nineteenth. From physical AI and AI factories to AgenTek AI and Inference, GTC twenty twenty six will showcase the breakthrough shaping every industry. Learn more and register now at nvidia.com/gtc. Today, we're diving into the future of public transit safety and efficiency. I'm excited to be joined by two guests who are at the forefront of this transformation. Asan Baig, CTO of AC Transit, the third largest bus operator in California and main bus operator for the East Bay region of the San Francisco Bay Area, shout out Alameda County, And Marty Beard, CEO of Hayden AI, a San Francisco based company that's using technology to make roads safer and public transit better. Hassan, Marty, thank you both so much for taking the time to join the AI podcast. Welcome. Thank you. Thanks for the opportunity. So maybe we can start with a little bit about what AC Transit does, and then we'll get to what Hayden does. And, Hassan, you can speak just a little bit about your role as CTO. And then as we go, we'll get into the collaboration, that brought you guys together and brought us here today. Yeah. Sure. Thank you so much, Noah. Thanks for the opportunity. Hassan Bey, chief technology officer, Alameda contract cost County's transit. So a lot of time, people think AC is only Alameda, so we do serve in Alameda and Contra Costa County. So so, basically, we are a two county public transit system. I just wanna clarify also, we are bus only. As you mentioned, Noah, we're the third largest in in the in the state, and we are the largest bus only in the in the Northern California region. Our pre COVID, daily ridership was about 200,000 people. Roughly about, you know, when you look into on an annual basis, you're talking about 55 to 57,000,000 riders, on on on an annual basis. I mean, that's a fairly significant mobility domain area if you if you wanna look from that perspective. Our mission, at AC Transit is safe, secure, reliable, and sustainable public transit. AC Transit is really kind of a unique that our board is an elected board. It's different from many other public transit agencies. There are only possibly, I think, three public transit agencies in the country. They have elected boards. Oh, is that right? Okay. Really means, Noah, is that it, basically, these are the board members elected board members are sort of really the people who are passionate about public transit and about mobility services. So I'm really, you know, proud of, part of the team. I've been here for almost eight years, managing the the technology programs, innovation program, and, you know, love my job and really, I'm passionate about providing those services to my customers in the East Bay. Well, as …

Get the full transcript (5,249 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all NVIDIA AI Podcast transcripts →

You just read a 3-minute summary of a 26-minute episode.

Get NVIDIA AI Podcast summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from NVIDIA AI Podcast

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into NVIDIA AI Podcast.

Every Monday, we deliver AI summaries of the latest episodes from NVIDIA AI Podcast and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime