Overview

AIP accelerates the R&D prototype and enhances the material learnings from in-field vehicle drives. AIP can interpret written or spoken comments from drivers in the prototype stage, spot any performance issues, and connect these problems to data from the vehicle's sensors. By bringing together product lifecycle (PLM), parts lists (BoM), and connected device data (IoT), engineers benefit from a holistic view of each test case, while also applying lessons learned from past tests on similar models — resulting in less time spent on physical prototypes.

Features

• Parsing Driver Feedback: Turn spoken comments and detailed notes from test drivers into clear, organized information, highlighting any issues found in the unstructured data and linking that information to the underlying audio and text files to allow further follow-up and interrogation
• AI-Suggested Issue Identity: Use AIP to sift through the unstructured feedback and surface to the operator issues performance problems, arranging them in order of importance for further action.
• Linking to Sensor Data: Contextualize issues identified by the Human and/or AI with data coming from the vehicle's sensors. AIP's Ontology speeds up investigations and makes the prototype testing process more efficient.