We build a proof of concept for your problem for 5,000–8,000€. You get a tangible demo instead of slides with promises.
Pittsburgh's East Liberty neighborhood faced severe urban traffic congestion, with fixed-time traffic signals causing long waits and inefficient flow. Traditional systems operated on preset schedules, ignoring real-time variations like peak hours or accidents, leading to 25-40% excess travel time and higher emissions.[1] The city's irregular grid and unpredictable traffic patterns amplified issues, frustrating drivers and hindering economic activity.
City officials sought a scalable solution beyond costly infrastructure overhauls. Sensors existed but lacked intelligent processing; data silos prevented coordination across intersections, resulting in wave-like backups. Emissions rose with idling vehicles, conflicting with sustainability goals.[2]
Rapid Flow Technologies developed Surtrac, a decentralized AI system using machine learning for real-time traffic prediction and signal optimization. Connected sensors detect vehicles, feeding data into ML models that forecast flows seconds ahead, adjusting greens dynamically.[3]
Unlike centralized systems, Surtrac's peer-to-peer coordination lets intersections 'talk,' prioritizing platoons for smoother progression. This optimization engine balances equity and efficiency, adapting every cycle.[4] Spun from Carnegie Mellon, it integrated seamlessly with existing hardware.
We build a proof of concept for your problem for 5,000–8,000€. You get a tangible demo instead of slides with promises.
Surtrac leverages machine learning prediction models trained on historical and real-time data from inductive loop sensors and cameras. The core decentralized scheduling algorithm uses optimization to allocate green time, predicting traffic arrivals up to 120 seconds ahead with high accuracy.[1] Intersections communicate via Ethernet, sharing predictions for coordinated 'green waves.' This avoids global synchronization pitfalls.
Launched June 2012 in Pittsburgh's East Liberty with 9 intersections. Initial setup integrated with legacy controllers in weeks, using off-the-shelf hardware. By October 2013, expanded to Bakery Square district. Early metrics showed immediate gains: 25% travel time drop during pilots.[2]
Challenges like sensor calibration were overcome via edge computing, processing data locally to minimize latency (<1 second cycles). CMU researchers refined ML models iteratively based on live data.
Rapid Flow formed in 2015 to commercialize; deployed across ~150 intersections in Pittsburgh by 2019. System proved robust in snow, rush hours. Miovision acquisition (recent) rebranded as Miovision Adaptive, expanding to other cities with cloud analytics.[5]
Implementation steps: 1) Sensor audit/integration; 2) AI model tuning per corridor; 3) Phased rollout with A/B testing; 4) Performance dashboards for DOT. Cost: $50K-100K per intersection, ROI in 1-2 years via fuel savings.
Initial hurdles: Data sparsity in low-traffic directions solved by probabilistic forecasting. Equity concerns addressed via minimum green guarantees. Scalability tested at 50+ nodes without central server failure.[3] Integration with SCATS/InSync via APIs enabled hybrid ops.
Today, real-time adaptation handles events like emergencies via V2I. Future: Full autonomy with LiDAR/AV integration.
We build a proof of concept for your problem for 5,000–8,000€. You get a tangible demo instead of slides with promises.
Founder & Partner
Reruption GmbH
Falkertstraße 2
70176 Stuttgart
Phone