Abstract

Solving Challenges in Future Mobility Solutions Using AI

Advances in AI and machine learning present new challenges in the form of supporting and operating the future mobility solutions. We need to actually train these future mobility solutions to overcome real-world challenges and operational workflow. The industry needs to ensure the reliable functionality for the increasing automatic and future mobility solutions. ...


Session No: SIL8125
Speakers: Amir Hever, David Oren
Type:

Intelligent Machines, IoT & Robotics

Date: Thursday - October 18, 2018 05:00 PM - 05:45 PM
Location: Hall F/G
Topics: Autonomous Machines and IoT, Deep Learning and AI
Industry: Automotive / Transportation

Advances in AI and machine learning present new challenges in the form of supporting and operating the future mobility solutions. We need to actually train these future mobility solutions to overcome real-world challenges and operational workflow. The industry needs to ensure the reliable functionality for the increasing automatic and future mobility solutions. In this presentation, we will describe the steps we took to solve this problem, including deep learning models for representations of vehicles, similarity metrics, segmentation, and anomaly detection. We will explain how GPU's combines these models into a singular system that analyzes a vehicle in just a few seconds. We will also show how models trained for security purpose have great value in the automotive industry, whereby using similar systems helps detect various types of mechanical problems and damages to the exterior of any vehicle. By using such technologies for anomaly detection in vehicles in automotive/civilian context, we can enable and streamline predictive maintenance practices, and consequently ensure safe and reliable mobility.