Case Study
Project DIAL– Driver Interaction Analytics and Learning: Enhancing the Driving Experience through Data-driven Insights.
Project DIAL– Driver Interaction Analytics and Learning: Enhancing the Driving Experience through Data-driven Insights.
Introduction
The leading automotive manufacturer team in charge of in-vehicle display technology faced a challenge in capturing driver interactions and vehicle data for analysis and enhancing the driving experience. By leveraging these insights, they aimed to gain valuable knowledge about driver behavior and optimize the utilization of various vehicle features. To address this need, People Tech Group collaborated with AWS to develop an innovative solution known as Project DIAL (Driver Interaction Analytics and Learning).
Problem
A leading automotive manufacturer team required a comprehensive method to capture and analyze driver interactions and vehicle diagnostic data. They sought to understand how drivers interacted with the in-vehicle display technology and gain insights that could drive improvements in the human-machine interface (HMI) and overall performance. Additionally, they wanted to identify patterns and preferences to personalize the driving experience.
Solution
In partnership with AWS, People Tech Group devised a robust solution to extract driver interactions and vehicle diagnostic information, and securely transmit it to the cloud for processing. The following components were integrated to enable data analysis and generate actionable insights:
AWS IoT Core: Captures driver interaction data and vehicle diagnostic information, securely sending it to the cloud.
Kinesis Fire Hose: Receives data from IoT Core and directs it into an S3 bucket for storage.
Lambda Functions: Process the data stored in the S3 bucket, facilitating extraction, transformation, and loading into AWS DynamoDB.
Athena: Enables data querying from both S3 and DynamoDB, facilitating the generation of analytical reports in Quicksight.
AWS Sagemaker: Utilizes custom machine learning models for specific use cases, enabling further analysis and insights extraction.
Kinesis Fire Hose: Receives data from IoT Core and directs it into an S3 bucket for storage.
Lambda Functions: Process the data stored in the S3 bucket, facilitating extraction, transformation, and loading into AWS DynamoDB.
Athena: Enables data querying from both S3 and DynamoDB, facilitating the generation of analytical reports in Quicksight.
AWS Sagemaker: Utilizes custom machine learning models for specific use cases, enabling further analysis and insights extraction.
Results
The implementation of Project DIAL has yielded several significant results:
Raw Usage Data: The HMI analytics team now possesses comprehensive raw usage data, empowering them to make informed decisions and enhancements to the HMI and driver experience. This data serves as a foundation for continuous improvement and optimization.
Feature Implementation: Product planning teams can leverage the data to determine the optimal implementation of features as either hard keys or soft keys within the vehicle. This decision-making process leads to improved usability and user satisfaction.
Personalization: By analyzing driver usage patterns, personalized features can be developed. These may include personalized vehicle settings based on the driver’s preferences and the availability of a favorites bar on the home screen. Such personalization enhances the overall driving experience and tailors it to individual drivers.
Feature Implementation: Product planning teams can leverage the data to determine the optimal implementation of features as either hard keys or soft keys within the vehicle. This decision-making process leads to improved usability and user satisfaction.
Personalization: By analyzing driver usage patterns, personalized features can be developed. These may include personalized vehicle settings based on the driver’s preferences and the availability of a favorites bar on the home screen. Such personalization enhances the overall driving experience and tailors it to individual drivers.
Conclusion
Project DIAL, in collaboration with AWS, has successfully addressed the challenges faced by a leading automotive manufacturer team in capturing and analyzing driver interactions and vehicle data. The solution provides valuable insights into driver behavior, leading to enhancements in the HMI, feature implementation, and personalization. By leveraging data-driven insights, GM can continuously improve the driving experience, resulting in increased driver satisfaction and improved efficiency and performance of vehicle applications.
