WeRide Launches GENESIS Autonomous Driving Simulation Platform

WeRide launched GENESIS, a simulation platform combining physical and generative AI to accelerate autonomous vehicle training by replicating real-world driving scenarios in virtual environments within minutes.

WeRide has introduced WeRide GENESIS, a general-purpose simulation model designed to accelerate autonomous vehicle development, training, and validation. The platform combines physical AI and generative AI to create virtual environments that replicate real-world driving conditions.

Highlights

  • WeRide GENESIS integrates four core AI modules to generate realistic virtual cities within minutes and simulate rare driving scenarios difficult to capture through road testing.
  • The platform supports Level 2++ ADAS through Level 4 Robotaxi configurations, enabling global AV training on a single system without city-specific simulations.
  • WeRide operates AVs in over 40 cities across 11 countries and holds autonomous driving permits in eight markets, including the United States, China, and the UAE.

Addressing Global Commercialization Challenges

Autonomous driving commercialization faces significant obstacles due to variations in road networks, traffic behaviors, infrastructure, weather conditions, and regulatory environments across different cities. Real-world testing remains costly, slow, and limited in scenario coverage.

WeRide GENESIS addresses these constraints by allowing AVs to operate in virtual cities, exposing AI drivers to diverse conditions including rare and high-risk events that would be impractical to test on public roads.

Four Core AI Modules

The simulation platform integrates four specialized components that work together to create comprehensive testing environments.

AI Scenarios

This module simulates driving situations AVs encounter on real roads:

  • Sudden vehicle cut-ins and unprotected left turns
  • Emergency evasive maneuvers and pedestrian intrusions
  • Extreme events including fires, earthquakes, road blockages, and adverse weather

The module draws on billions of kilometers of real-world driving data and over eight years of edge cases from WeRide’s public road operations.

AI Agents

The AI Agents module builds intelligent behavior models for human drivers, pedestrians, riders, and other road users. These models simulate the full spectrum of traffic behaviors, from routine driving to high-risk actions.

This capability allows engineering teams to evaluate AV decision-making safety and system robustness under different algorithm configurations and predict performance across multiple Operational Design Domains.

AI Metrics

The AI Metrics module provides quantitative evaluation covering:

  • Safety compliance and regulatory adherence
  • Passenger comfort scoring and feedback
  • Travel efficiency measurement
  • Automated assessment of algorithm improvements

AI Diagnosis

This module automates root-cause analysis when sub-optimal driving behaviors occur. It detects issues, analyzes underlying causes, and provides actionable solutions for perception delays or prediction errors in complex scenarios.

Single Platform for Global Operations

WeRide GENESIS supports diverse urban road conditions, sensor perspectives, and vehicle configurations ranging from Level 2++ advanced driver-assistance systems to Level 4 Robotaxis. This enables AI drivers worldwide to train and test on one platform without separate simulations for different cities or vehicle types.

WeRide currently holds autonomous driving permits in eight markets: China, the UAE, Singapore, France, Switzerland, Saudi Arabia, Belgium, and the United States.

“WeRide GENESIS builds us a digital universe that can be generated, scaled, and evolved on demand,” said Dr. Yan Li, Co-Founder and CTO of WeRide. “With it, our AI drivers can familiarize themselves with the driving environment of any city worldwide within minutes.”

WeRide was named to Fortune’s 2025 Change the World and 2025 Future 50 lists.

Self Drive News
Self Drive News Staff

Self Drive News is the trade publication of record for vehicle autonomy. Published by Hagman Media and edited by founder Brian Hagman, it covers autonomous vehicles, robotaxis, ADAS, self-driving software and hardware, and L4 commercial deployments for an audience of AV engineers, software safety professionals, and mobility investors.