Skip to main content

Technology & Architecture Stack

A comprehensive architectural disclosure for municipal Chief Technology Officers, transportation engineers, and systems architects. Transparently distinguishing implemented simulation code from active hardware development.

🐍

Python Scientific & AI Core

Status: Fully Implemented Core

Python serves as the backbone for algorithmic modeling, TraCI socket communication, simulation orchestration, and data transformation pipelines.

# Simulation Loop Actuation Core (Python 3.11 + TraCI) import traci def run_traffic_step(step_idx, rl_agent): traci.simulationStep() state = extract_corridor_state() action = rl_agent.compute_phase_action(state) enforced_action = apply_maxband_safety_envelope(action) traci.trafficlight.setProgram("tl_corridor_01", enforced_action.program_id)

Key Libraries

PyTorch, NumPy, SciPy, Stable-Baselines3, Scikit-learn, Ray Tune.

Operational Role

Executes RL policy evaluation, state feature extraction, and mathematical queue optimization.

🚦

Eclipse SUMO & TraCI Simulation Engine

Status: Fully Implemented Core

Eclipse SUMO (Simulation of Urban MObility) is an open-source, highly portable, microscopic vehicular traffic simulator. Connected via the TraCI (Traffic Control Interface) socket protocol, it executes sub-second physical simulation runs with realistic car-following dynamics (Krauss / IDM models).

Microscopic Actuation

Simulates individual vehicle speed, braking, lane changing, and acceleration curves.

TraCI Real-Time Socket

Allows Python agents to inspect queues and modify signal phases step-by-step.

Demand Calibration

Loads synthetic and real-world origin-destination matrices from municipal count logs.

🗺️

Geospatial Engine: PostGIS, GeoPandas & OpenStreetMap

Status: Fully Implemented Data Layer

Spatial intelligence is powered by OpenStreetMap topology converted into PostGIS network graphs. GeoPandas and Shapely execute high-speed spatial joins, corridor bounding boxes, and Low-Emission Zone polygon geofences.

PostGIS 3.4 on PostgreSQL 16

Manages street centerlines, junction coordinates, crosswalk geometries, and spatial indexing (`GIST`) for microsecond proximity queries across metropolitan territories.

OSMnx & OpenStreetMap Ingestion

Downloads, models, and visualizes street networks directly from OSM, generating navigable directed multigraphs with edge speeds, lane counts, and turn restrictions.

🤖

Machine Learning: DQN, PPO, LSTM & GRU

Status: Implemented in Simulation Sandbox

Our dual AI pipeline combines predictive sequence modeling with closed-loop policy optimization:

Deep Reinforcement Learning (DQN & PPO)

Agents learn to dynamically adjust green phase durations by observing queue lengths, wait time variances, and downstream discharge capacities.

Time-Series Forecasting (LSTM & GRU)

Recurrent neural networks predict flow surges across arterial links up to 60 minutes in advance, enabling the signal controllers to adjust offsets before queues propagate.

👁️

Edge Computer Vision: YOLOv8 & RTSP Pipeline

Status: In Development (Edge Neural Benchmark)

Processes municipal RTSP video streams at the network edge. Tracks and classifies vehicles into classes (cars, buses, delivery trucks, motorcycles) while counting lane queue densities.

Edge Deployment Architecture: Compiled via TensorRT for ultra-low latency execution on NVIDIA Jetson or Intel OpenVINO edge hardware boxes installed directly in signal cabinet enclosures.
☁️

Backend & Cloud Architecture: FastAPI & Azure AKS

Status: Architectural Concept & Prototype API

High-concurrency asynchronous API layer engineered in FastAPI and Python 3.11 with containerized orchestration on Microsoft Azure Kubernetes Service (AKS).

FastAPI Async Engine

Sub-millisecond serialization of municipal telemetry feeds using Pydantic V2.

Redis In-Memory State

Maintains active intersection signal states, current phases, and operator overrides.

NTCIP 1202 & MQTT

Standard protocol bridging legacy 170/2070/ATC signal cabinets with cloud telemetry.