3D Vehicle Model Orientation for Ridesharing Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing tools for identifying vehicles in ridesharing are inadequate as they rely on generic pictures, which are not sufficient for distinguishing between similar vehicles and do not account for the rider's perspective, leading to potential errors in vehicle recognition.

Innovation Solution

A system that generates a 3D model of a vehicle based on its make, model, and color, allowing drivers to capture images from multiple angles, extracts distinguishing features, and displays the model at an angle consistent with the rider's view, ensuring accurate vehicle recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If generic pictures are used to identify vehicles, then storage space and bandwidth requirements are reduced, but vehicle recognition accuracy deteriorates due to inability to distinguish between similar vehicles

Engineering Contradiction:
Improvestorage spaceVSAvoidvehicle recognition accuracy
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The system creates a 3D digital model (copy) of the vehicle that can be rotated and viewed from multiple angles. This virtual copy contains all the visual details of the actual vehicle without requiring storage of multiple physical photographs, thus maintaining recognition accuracy while optimizing storage space.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system transitions from 2D generic pictures to a 3D interactive model. This dimensional change allows the rider to view the vehicle from any angle (front, side, rear, top) by rotating the model, providing comprehensive visual verification without storing multiple 2D images from different perspectives.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Loss of energy

If generic pictures from side angle are used, then data transmission bandwidth is reduced, but usability deteriorates because vehicles often approach riders with only the front visible

Engineering Contradiction:
Improvebandwidth consumptionVSAvoidvehicle verification usability
Core Design Contradiction:
Loss of energyVSEase of operation

Solution Approach 1:

The system implements a dynamic 3D model that can be rotated and reoriented in real-time based on the rider's viewing needs. Unlike static generic pictures, the interactive model adapts to show the vehicle from the appropriate angle (front, side, rear) depending on how the rider rotates it, greatly improving verification usability.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

A single 3D model serves multiple viewing functions that would otherwise require multiple separate images. The same model can be rotated to show front view, side view, rear view, or any intermediate angle, making it a universal solution that replaces numerous angle-specific photographs.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Reliability

If unique photographs from multiple angles of every vehicle are stored, then vehicle recognition accuracy is improved, but storage space and bandwidth requirements increase prohibitively

Engineering Contradiction:
Improvevehicle recognition accuracyVSAvoidstorage space
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

Instead of storing multiple physical photograph copies of each vehicle from different angles, the system creates a single 3D digital model that can generate any viewing angle on-demand. This virtual copying mechanism provides unlimited view perspectives without proportionally increasing storage requirements.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system stores a 3D representation rather than multiple 2D images. This dimensional transformation allows the system to maintain high recognition accuracy by providing complete vehicle geometry and surface details, while the single 3D model occupies far less storage space than the collection of multiple angle-specific photographs would require.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS11151882B2Providing a model of a vehicle to a rider at an accurate orientation
Publication Date: 2021.10.19 UBER TECHNOLOGIES INC
  • US11151882B2 patent drawing
  • US11151882B2 patent drawing
  • US11151882B2 patent drawing

AI summary

Systems and methods are disclosed herein for providing a model of a vehicle to a rider. In an embodiment, the systems and methods determine that a driver has accepted a task to operate a vehicle from a first location to a rider location. The systems and methods then access a model corresponding to the vehicle, determine a direction of movement of the vehicle, and determine a relative orientation of the vehicle with respect to the rider based on the first location, the direction of movement of the vehicle, and the rider location. The systems and methods generate for display, on a client device of the rider, the model at an angle determined based on the relative orientation.