By Nisarg Pandya

Artificial intelligence (AI) is changing the automotive industry, especially when it comes to improving road safety and reducing the number of accidents. In India, where only 2.5 percent of the world’s vehicles contribute to 13 percent of global traffic accidents, the need for innovative solutions is pressing. AI-powered technologies are emerging as important tools to meet this challenge, improving both safety and efficiency in transportation.

One of the most important contributions of AI to road safety is its predictive ability. AI systems can analyze data from various sources, including telematics and driver behavior, to predict potential accidents. The details of perception are basically similar to how humans operate with natural intelligence by continuously answering three questions – where am I? What do I see? And how do I proceed?

The first question defines locating information about the exact location based on geography and lane position, the second question is perception i.e. understanding the surroundings and the third question is decision making whether to brake or accelerate. AI solutions use localization and perception to understand the environment and driver behavior data and assert drivers in case of risk to brake or accelerate. AI solutions with such intelligence use cameras, radar-like sensors and a computer on the edge to make decisions in real time.

Identify accident-prone areas and contribute to the design of safer road infrastructure

The identification of accident affected areas is a result of historical behavioral data analysis. By deploying telematics devices across regions, AI can collect data about the surrounding environment, such as high-traffic areas, accident-prone locations with pedestrian or animal crossings, road conditions from potholes to new construction, which can affect driving. By consistently analyzing such data points, AI can over time identify such areas and notify drivers with necessary voice assistance as they approach them.

AI for safer driving

AI devices equipped with ADAS and DMS capabilities use voice assistance to warn drivers in their preferred language about unsafe driving practices, such as using a phone while driving or not wearing a seat belt. These alerts are the first level of training for drivers to proactively improve behavior in real time to avoid impact. The second level of training is when drivers receive personal training from their fleet managers by reviewing videos of their driving behavior and the potential consequences of unsafe driving. By consistently participating in this training for at least six months, drivers can significantly improve their behavior. They can become more likely, following real-time guidance from ADAS/DMS devices, leading to proactive decisions and a reduction in risky driving situations.

To be effective, ADAS/DMS devices using AI must accurately identify areas of risk for drivers. Incorrect warnings can reduce the driver’s confidence in the technology, leading to a potential disregard of warnings even in dangerous situations. This can hinder behavioral improvements.

Challenges & strategies for implementing road safety

The biggest challenge in implementing AI for road safety, especially with systems like ADAS, is its ability to generalize across different geographic regions. For example, for ADAS to work effectively, it must first recognize important regional differences, such as whether the driving system is left- or right-handed, the types of vehicles on the road, variations in traffic lights and signs, differences in pavements, and lane markers. The AI ​​must be trained to handle these variations and evolve to become sufficiently generalized to detect and respond appropriately, despite such differences.

To implement DMS driver behavior monitoring, it needs to be able to recognize a variety of facial features, such as build, height, tattoos, glasses, etc. Additionally, DMS systems must be adaptable to different cultural and geographic factors that may affect facial expressions as well as orientations, and AI must constantly evolve across all such variations.

The best strategy to overcome any such challenges is to work with two specific performance measures of AI accuracy and precision, which is to identify the false positives and correct them, and to identify the true negatives and improvise. To achieve both parameters with higher values, one needs a large variety of data to account for the variation in cases involving different contexts.

Future trends and research directions in AI applications for road safety

AI’s role in road safety extends from driver assistance systems such as ADAS and DMS to systems such as L4/L5 autonomy where AI decisions are used to control vehicles. While the world is moving towards autonomous driving, the complexity and context-dependent nature of driving makes it a challenging task for AI. Human drivers, with their different experiences and decision-making abilities, can handle different situations in different ways, sometimes leading to accidents or successful navigation. Achieving the same level of precision and adaptability in AI systems remains a significant challenge, limiting the deployment of fully autonomous vehicles to specific areas and controlled environments.

AI can proactively predict the likelihood of accidents by identifying potential risk factors, such as drowsy driving, tailgating or distracted driving. While sensors can detect accidents after they occur, AI’s ability to anticipate potential incidents enables preventative measures and faster emergency response.

(The author is CEO of DrivebuddyAI)

Disclaimer: The views, beliefs and opinions expressed by the various authors and forum participants on this website are personal and do not reflect the views, beliefs and opinions of ABP Network Pvt. Ltd.