Vehicle-Centric AI

Project: Vehicle Data Analysis and Future Mobility

Duration: 03.2022 - 02.2024

Industry: MtoV and COIKOSITY

Description: This project aims to analyze data from vehicles in order to understand and predict their movements and behaviors. By collecting and analyzing data on factors such as location, speed, and acceleration, we hope to gain insights into how vehicles are used and how they may be used in the future. This information may be used to improve the efficiency and safety of transportation systems, as well as to inform the development of new technologies and mobility solutions.

Project: Internet of Vehicles: Data Collection, Prediction, Traffic Management, Incentive/Punishment Scheme, Driver Safety,

Duration: 03.2019 - 02.2024

Industry: VEStellaLab and COIKOSITY Private Limited

Description: The Internet of Vehicles (IoV) refers to the interconnectedness of vehicles through the use of sensors and communication technologies, such as GPS, wireless networks, and the internet. Data collection and analysis are key components of the IoV, as they allow for the tracking of vehicle movements, the prediction of traffic patterns, and the management of transportation systems. Additionally, the IoV may be used to implement incentive/punishment schemes to encourage safe driving and traffic compliance, and to improve driver safety through the use of advanced warning systems and other safety features. Overall, the IoV has the potential to significantly improve the efficiency and safety of transportation systems, and to inform the development of new technologies and mobility solutions.

Project: Smart Streetlight Framework for Collision Prediction of Vehicles

Duration: 03.2019 - 02.2021


Description: In this project, we have designed a framework for a smart vehicle monitoring system that utilizes roadside units such as streetlights to provide smooth mobility for vehicles. This system aims to eliminate the need for each vehicle to be equipped with expensive smart sensors, which can be a burden for developing and underdeveloped countries. To predict vehicle collisions, we have based our system on scientific and engineering concepts such as relative motion and vectors and implemented it using a machine learning-based model. We have used these concepts to generate datasets for training the prediction model, and have simulated the performance of the proposed model using the software Virtual Crash. Overall, our goal is to provide a cost-effective solution for smooth and safe vehicle mobility.

Paper: Sudhanshu Tripathi, Dhananjay Singh*, "Smart Streetlight Framework for Collision Prediction of Vehicles, Expert Systems with Applications, July 2022 [SCIE: 8.665]

Project: Smart City: Autonomous Vehicle Parking Lot

Duration: 03.2020 - 02.2021

Industry: VEStellaLab (

Description: In this project, we have developed artificial intelligence (AI) and deep learning algorithms for autonomous driving. These algorithms utilize cutting-edge technologies such as RFID, wireless sensor networks (WSN), NFC, cloud networks, and smartphones to enable the automatic monitoring and management of parking spaces. The goal of this system is to assist vehicles in entering and exiting parking spaces and to provide automatic billing/booking of parking spots. By using these innovative technologies, we aim to improve the efficiency and convenience of parking services and to reduce the time and effort required for individuals to park their vehicles.

Project: VERO: EV parking lot detection Apps

Duration: 03.2019 - 02.2020

Industry: VEStellaLab (

Description: VERO is a Mobile application that utilizes sensor technologies and real-time communication systems to detect and manage electric vehicle (EV) parking spaces. This system aims to optimize the utilization of EV parking spaces, allowing individuals to easily locate and reserve parking spots for their EVs. By providing this service, cities can encourage the adoption of EVs and improve the overall flow of traffic within a city. The system may also be integrated into a smart city infrastructure, allowing for the automation of parking services and the optimization of parking space utilization. Overall, VERO has the potential to significantly improve the efficiency and convenience of EV parking services.

Project: SafeDrive: Hybrid Recommondation System for Early Safety Prediction

Duration: 03.2018 - 02.2020

Industry: Deputy for Research and Innovation RDO in the Ministry of Education in Saudi Arabia

Description: In this project, we have developed a dynamic driver profile (DDP) that utilizes deep learning methods to predict and address risky driver behavior. The DDP is based on three major sets of attributes that accurately predict motion and enable automatic interventions for driver safety. The DDP is digitally implemented and behaviorally designed to minimize the number of high-risk drivers on the road. We have also conducted a road data study of all risky drivers, using the STPSR model for risk analysis to improve the overall performance of our prevention platform. Additionally, we have implemented a feedback-based update system to increase the accuracy of our recommendations. Overall, our goal is to improve driver safety through the use of advanced technology and data analysis.

Project: Realtime Vehicle Data Collection, Analysis and Prediction

Duration: 03.2016 - 02.2018

Industry: MtoV Inc.

Description: A vehicle data open platform is a system that allows individuals and organizations to share car-related data on the internet. This platform can be used to collect, store, and analyze data on a wide range of car-related topics, including vehicle performance, driving habits, and maintenance. By sharing this data, individuals and organizations can gain valuable insights into the operation and performance of their vehicles, as well as contribute to the overall knowledge base on car-related topics. The platform may also be used to facilitate communication and collaboration between car owners and other stakeholders, such as car manufacturers, repair shops, and insurance companies. Overall, a vehicle data open platform has the potential to improve the efficiency and safety of transportation systems, as well as to inform the development of new technologies and mobility solutions.

Project: Onboard Diagonisis Device (OBD-II) Realtime Vehicle Data Collection

Duration: 11.2013 - 02.2015

Industry: MtoV Inc., (MTOV)

Description: In this project we have design and developed a OBD-II (On-Board Diagnostics II) device for monitoring and diagnosing vehicles' engine performance and emissions. It is a diagnostic system that is installed in most vehicles manufactured since 1996 and is designed to help mechanics and technicians diagnose problems with a vehicle's engine, transmission, and other systems. OBD-II is connected to a vehicle's on-board computer, which is responsible for monitoring the performance of various systems and components. When the computer detects a problem with the vehicle, it will trigger a fault code and store it in the OBD-II system's memory. Mechanics and technicians can then use a diagnostic tool to access this fault code and use it to diagnose and fix the problem. OBD-II is a useful tool for diagnosing problems with a vehicle and can help mechanics and technicians identify issues and fix them quickly and efficiently.