Vehicle Sensor Fusion for Cabin Interaction and External Object Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current vehicles are poorly configured to handle new types of interactions in semi-autonomous or fully-autonomous vehicles, lacking systems for sensing and control inside the vehicle and integrating these with external environment sensing and vehicle navigation.

Innovation Solution

The implementation of vehicle sensing and control systems using neural networks, which capture sensor data from both inside and outside the vehicle to detect user interactions and items of interest, allowing for enhanced sensing and control capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If vehicles are equipped with sensors to sense the external environment for autonomous navigation, then the autonomous driving capability is improved, but the system complexity and resource consumption increase

Engineering Contradiction:
Improveautonomous driving capabilityVSAvoidsystem complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The system divides sensing functions into two independent modules: external environment sensing (for navigation and obstacle detection) and internal cabin environment sensing (for user interaction detection). This segmentation allows each module to be optimized independently, reducing overall system complexity while maintaining autonomous driving capability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The sensing system is designed to perform multiple functions: external environment perception for autonomous navigation, internal cabin monitoring for user interaction detection, and integration of both data streams for comprehensive vehicle control. This multi-functionality reduces the need for separate dedicated systems.

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

2Adaptability or versatility

If vehicles are equipped with sensors to sense the internal cabin environment for user interaction detection, then the user interaction capability is improved, but the device complexity increases

Engineering Contradiction:
Improveuser interaction capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system merges external environment sensing data with internal cabin environment sensing data into a unified processing framework. This combination allows the system to handle both autonomous navigation and user interaction detection using a single integrated system, reducing device complexity while improving versatility.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The sensing system is designed to perform multiple functions: external environment perception for autonomous navigation, internal cabin monitoring for user interaction detection, and integration of both data streams for comprehensive vehicle control. This multi-functionality reduces the need for separate dedicated systems.

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

3Measurement precision

If neural networks are used to process sensor data for detecting user interactions and items of interest, then the sensing precision and interaction detection accuracy are improved, but the computational resource consumption increases

Engineering Contradiction:
Improveinteraction detection accuracyVSAvoidcomputational resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary processing of sensor data by organizing it into structured formats (e.g., combining external and internal sensor data into unified data structures) before feeding it to neural networks. This preliminary organization reduces the computational burden on neural networks while maintaining detection accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system applies neural networks selectively to specific aspects of sensor data processing rather than processing all data uniformly. For example, neural networks are used for detecting user interactions and items of interest in the cabin environment, while other processing tasks may use simpler algorithms, reducing overall computational resource consumption.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12330660B2Vehicle sensing and control systems
Publication Date: 2025.06.17 ALPINE ELECTRONICS OF SILICON VALLEY INC
  • US12330660B2 patent drawing
  • US12330660B2 patent drawing
  • US12330660B2 patent drawing

AI summary

Vehicle sensing and control systems are provided. The vehicle sensing and control systems may use various sensors to capture sensor data from and interior of the vehicle and/or the exterior of the vehicle. The sensor data from the interior of the vehicle may be used to detect interactions by the user. The sensor data from the exterior of the vehicle may be used to detect items of interest for the occupants of the vehicle based further on the sensor data from the interior of the vehicle.