An AI-optimized routing plan was rejected by a route planner because it broke established, valuable relationships between specific drivers and customers. The insight is that pure optimization is naive; successful AI must assist human workflows and account for intangible human context.

After proving its robo-taxis are 90% safer than human drivers, Waymo is now making them more "confidently assertive" to better navigate real-world traffic. This counter-intuitive shift from passive safety to calculated aggression is a necessary step to improve efficiency and reduce delays, highlighting the trade-offs required for autonomous vehicle integration.

The massive pressure of the 1984 Olympics forced Los Angeles to develop the ATSAC system, a centralized traffic control network. Initially an experiment for the games, its success in reducing delays by 35% led to its permanent adoption and expansion, fundamentally changing the city's infrastructure and becoming a global model.

Waymo vehicles froze during a San Francisco power outage because traffic lights went dark, causing gridlock. This highlights the vulnerability of current AV systems to real-world infrastructure failures and the critical need for protocols to handle such "edge cases."

The goal of a traffic system isn't to create a pain-free experience for everyone, which is impossible. Instead, it's a utilitarian calculation to manage and distribute delay and frustration across the network, prioritizing the "greatest good for the greatest number" and ensuring everyone shares the burden.

Achieving near-perfect AV reliability (99.999%) is exponentially harder than getting to 99%. This final push involves solving countless subtle, city-specific issues, from differing traffic light colors and curb heights to unique local sounds like emergency sirens, which vehicles must recognize.

Sebastian Thrun points out a startling fact: even a highway at a standstill is 92% empty space due to inefficient car spacing and lane design. This illustrates the immense, untapped capacity in our infrastructure that could be unlocked by the precision of coordinated, self-driving vehicles.

Urban infrastructure provides a fixed amount of physical space (streets). With demand for that space exceeding supply, the only variable engineers can truly control is time. Their entire job revolves around allocating slivers of time (green lights) to competing users, framing the problem as a temporal, not spatial, challenge.

While driven by data and algorithms, effective traffic engineering is fundamentally about understanding and shaping human behavior. Small physical changes, like moving a painted line by six inches, can alter driving speeds and actions more than a complex equation, making it as much an art as a science.