RouteOpti

How RouteOpti uses Kurai to power their newest projects.

Industry

Logistics & Transportation

Location

Chicago, IL

Employees

180

Identity Provider

RouteOpti

Workloads

Route Optimization, Reinforcement Learning, Genetic Algorithms, Python

About

RouteOpti is a logistics platform managing 5,000+ delivery trucks and 100K+ daily deliveries across North America. Their fleet carries everything from e-commerce packages to refrigerated goods.

Challenge

Manual route planning was inefficient, with trucks driving 28% more miles than necessary. Fuel costs were $12M/month and drivers averaged 12 hours/day. Delivery delays were 22% during peak periods.

Solution

Kurai built an ML-powered route optimization system using reinforcement learning and genetic algorithms. The system plans routes for 5K trucks in 15 minutes daily, reducing miles driven by 28% and cutting fuel costs by $3.4M/month.

Results

28% reduction in miles driven (fuel savings: $3.4M/month)...

18% improvement in on-time delivery rate...

Driver overtime reduced by 35%...

$40.8M annual cost savings...

Route Optimization ML: 28% Fuel Savings

The Problem

RouteOpti’s fleet of 5,000 trucks was driving 28% more miles than necessary. Manual route planning couldn’t handle complex constraints: delivery windows, truck capacity, driver hours, traffic patterns, and fuel costs. Fuel costs were $12M/month and rising.

The Solution

Kurai deployed a reinforcement learning system that optimizes routes for 5,000 trucks in 15 minutes daily. The system balances 47 constraints including traffic patterns, delivery windows, driver breaks, fuel prices, and vehicle capacity.

Model Architecture:

  • Algorithm: Proximal Policy Optimization (PPO) + genetic algorithms
  • Training data: 2 years of historical routes and GPS data
  • Features: Traffic, weather, delivery density, fuel prices, driver availability
  • Optimization: Multi-objective (minimize miles, fuel, time; maximize on-time rate)

The Results

  • Miles driven: -28% (fuel savings: $3.4M/month)
  • On-time delivery: 78% → 96% (+18%)
  • Driver overtime: 12 hrs → 7.8 hrs/day (-35%)
  • Annual savings: $40.8M

Technology Stack

PyTorch, Ray RLlib, FastAPI, PostgreSQL, Redis, AWS ECS, GPS integration via REST API

Key Metrics

MetricBeforeAfterImprovement
Miles driven100K/day72K/day-28%
Fuel cost$12M/month$8.6M/month-28%
On-time rate78%96%+18%
Driver overtime4 hrs/day1.5 hrs/day-63%

RouteOpti now saves $40.8M annually while delivering 18% more packages on-time.

Trusted by Industry Leaders

Empowering innovators, shaping the future

David Gutierrez

David Gutierrez

CTO at TechFlow AI

"The RAG system they built for us reduced our support tickets by 60%. Their expertise in LLM integration is unmatched."

Pierluigi Camomillo

Pierluigi Camomillo

VP Engineering at DataScale

"They migrated our monolith to microservices seamlessly. We saw a 40% cost reduction and significantly improved scalability."

Ella Svensson

Ella Svensson

Founder at MediSort Health

"Their ML-powered patient triage system transformed our operations. 70% faster triage with 94% accuracy—sim incredible results."

Alexa Rios

Alexa Rios

Chief Product Officer at ShopMax

"The recommendation engine they built increased our AOV by 32%. Highly recommended for any e-commerce business looking to leverage AI!"