AI for Road Safety

Make Indian roads safer for the public, by reducing traffic accidents using AI-based collision avoidance systems.


Premium participation: Get 1-on-1 Mentoring & Guidance

Try a free mentoring session

Unveiling Accident Triggers: Uncovering Patterns and Signals through Exploratory Data Analysis.

Identify new insights using exploratory data analysis and derive interesting patterns that help identify accident-prone zones, dangerous driver behavior patterns, or any such additional signal/modalities that correlate with more accidents.

With a focus on identifying accident-prone zones, understanding dangerous driver behavior patterns, and uncovering additional signal modalities that correlate with accidents, this challenge equips organizations with actionable information to improve road safety.

By harnessing the derived insights, organizations can implement targeted interventions, enhance infrastructure, and develop effective awareness campaigns. The findings serve as a catalyst for driving positive changes, making Indian roads safer for the public and reducing the occurrence of road traffic accidents.

Info session

Our challenge partner

In this challenge, we will 

  • Analyze the given dataset
  • Identify patterns in given real-time data
  • Use other relevant, supplementary data to explain patterns
  • Learn, understand the insights and build a model if necessary.
  • If required, use explainable AI to understand model predictions.

Technologies we will use

  • Regression
  • Time series analysis
  • Exploratory data analysis
  • Data science / Statistical analysis 

Who are we looking for? 

Students in Computer science, AI/ML enthusiasts, transportation engineers, researchers at universities. Undergraduate/Graduate or higher.

You will collaborate with a diverse team of up to 50 international collaborators in subteams. You can join as a contributor (8-12 hours per week commitment for 8 weeks) or coach (2-4 hours per week, only for experienced ML professionals)

We’ll organize a masterclass on using the dataset provided by iRaaste for the challenge.

Dataset description

The proposed dataset is a pseudo-anonymized real-time data from vehicles on roads. The dataset consists of events from. vehicles about possible collision alerts and driver monitoring. The dataset consists of more than 10 types of alert events with over 1000 data points with location and time stamps.

Quick facts about the problem

We at INAI have been involved in the iRASTE projects, aimed at improving road-safety through AI-based collision avoidance systems.

INAI has been instrumental in deploying the largest ADAS Pilot in India with over 450 vehicles plying in Nagpur city, and on the National highways of Telangana.

Did you know

🚗 INAI has been instrumental in deploying the largest ADAS Pilot in India with over 450 vehicles plying in Nagpur city, and on the National highways of Telangana.

🚕 The Government of India is aiming for a 50% reduction in road fatalities on Indian roads by 2030 that paves the path towards VISION ZERO.

Application deadline

September 3, 2023
To application page


Application Deadline: 3 September 2023

Challenge Kick-off: 4 September 2023

Midterm Presentations: 2 October 2023

Final Presentations: 13 November 2023

A little more