simobility

simobility is a light-weight mobility simulation framework. Best for quick prototyping

simobility is a human-friendly Python framework that helps scientists and engineers to prototype and compare fleet optimization algorithms (autonomous and human-driven vehicles). It provides a set of building blocks that can be used to design different simulation scenarious, run simulations and calculate metrics. It is easy to plug in custom demand models, customer behavior models, fleet types, spatio-temporal models (for example, use OSRM for routing vehicles and machine learning models trained on historical data to predict ETA).

Motivation

Create an environment for experiments with machine learning algorithms for decision-making problems in mobility services and compare them to classical solutions.

Some examples:

Installation

pip install simobility

Contributions and thanks

Thanks to all who contributed to the concept/code:

Examples

Grid world simulation

Simple simulation

Taxi service

Log example

Benchmarks

Benchmark simulations with LinearRouter and GreedyMatcher. Simulations will run slower with OSRMRouter because OSRM cannot process requests as fast as the linear router.

Processor: 2,3 GHz Dual-Core Intel Core i5; Memory: 8 GB 2133 MHz LPDDR3

Simulated time	Simulation step	Vehicles	Bookings per hour	Execution time	Generated events	Pickup rate
1 hour	10 sec	50	100	4 sec	1082	96.97%
24 hours	1 min	50	100	12 sec	23745	88.37%
24 hours	10 sec	50	100	20 sec	23880	88.84%
12 hours	10 sec	200	100	18 sec	13337	99.89%
12 hours	10 sec	50	500	31 sec	40954	53.92%
12 hours	10 sec	200	500	46 sec	65444	99.3%
12 hours	10 sec	1000	500	1 min 48 sec	66605	99.98%
1 hour	1 min	1000	1000	14 sec	11486
1 hour	10 sec	1000	1000	18 sec	11631
24 hours	1 min	1000	1000	5 min 1 sec	262384
24 hours	10 sec	1000	1000	6 min 20 sec	262524

A heuristic that allows estimating a maximum number of booking a fleet of N vehicles can handle: assume that an avarage trip duration is 15 minute, than 1 vehicle can not more then handle 4 booking per hour and the upper limit for 1000 vehicles is 4000 bookings per hour.

Metrics example

{
    "avg_paid_utilization": 63.98,
    "avg_utilization": 96.87,
    "avg_waiting_time": 292.92,
    "created": 3998,
    "dropoffs": 589,
    "empty_distance": 640.37,
    "empty_distance_pcnt": 33.67,
    "fleet_paid_utilization": 63.98,
    "fleet_utilization": 96.87,
    "num_vehicles": 50,
    "pickup_rate": 15.48,
    "pickups": 619,
    "total_distance": 1902.04,
}

Simulation logs

The are multiple ways to collect simulation log - use CSV or InMemory log handler or implement your own handler: loggers

Read CSV logs with pandas:

import pandas as pd

data = pd.read_csv(
    "simulation_output.csv",
    sep=";",
    converters={"details": lambda v: eval(v)},
)

details = data.details.apply(pd.Series)

Run OSRM

wget http://download.geofabrik.de/north-america/us/new-york-latest.osm.pbf
docker run -t -v "${PWD}:/data" osrm/osrm-backend osrm-extract -p /opt/car.lua /data/new-york-latest.osm.pbf
docker run -t -v "${PWD}:/data" osrm/osrm-backend osrm-partition /data/new-york-latest.osrm
docker run -t -v "${PWD}:/data" osrm/osrm-backend osrm-customize /data/new-york-latest.osrm
docker run -d -t -i -p 5010:5000 -v "${PWD}:/data" osrm/osrm-backend osrm-routed --algorithm mld /data/new-york-latest.osrm

Project Name	Stars	Repos Using This	Packages Using This	Most Recent Commit	Total Releases	Latest Release	Open Issues	License	Language
Awesome Mobility Machine Learning Contents	181			3 years ago				mit
Machine Learning / Deep Learning Contents in Mobility Industry(Transportation)
Motoro	73			5 years ago			9	mit	JavaScript
Smart contracts for decentralized rentals of vehicles.
Multiobjecttracker	56			6 years ago			2		Python
Advanced multiple object tracker using dlib and OpenCV.
Transportation	31			7 years ago			1	mit	CSS
PubNub Transportation Solution
Simobility	21			3 years ago			5	mit	Python
simobility - light-weight mobility simulation framework. Best for quick prototyping
Opennhtsa	21			8 years ago				gpl-2.0	R
An R wrapper for the U.S. Department of Transportation National Highway Traffic Safety Administration's API.
Bkk_stop	20			a month ago					Python
HomeAssistant custom component for Budapest public transportation
Falsehoods	17			2 years ago			1
Falsehoods programmers believe in about public transportation.
Transportation	16	3	5	2 years ago	43	April 13, 2022		mit	JavaScript
node.js module to display and manipulate public transport data
Zero_virus	14			3 years ago			1	other	Python
Zero-VIRUS: Zero-shot VehIcle Route Understanding System for Intelligent Transportation (CVPR 2020 AI City Challenge Track 1)

Simobility