Vehicle Multimodal Assistant for Reliable Passenger Intent Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle interaction techniques may not be optimal in certain situations, necessitating improved methods and systems for facilitating passenger interaction.

Innovation Solution

A vehicle system that utilizes a multimodal virtual assistant to receive and interpret passenger inputs through multiple sensor modalities, including speech and gesture recognition, with adaptive learning to determine optimal interaction strategies based on passenger history.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a single modality sensor is used for passenger input, then the device complexity is reduced, but the interaction reliability and precision are insufficient

Engineering Contradiction:
Improveinteraction reliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple sensor modalities (microphones for speech, cameras for gestures, touch sensors, steering wheel sensors) into a unified interaction system. The processor integrates inputs from different modalities to reliably determine passenger requests, resolving the contradiction by merging sensors rather than using a single modality.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The vehicle system is designed to handle multiple types of inputs (speech commands, gestures, touch inputs, steering wheel interactions) through a single multimodal processing framework. This universal approach allows the system to reliably interpret various input types without requiring separate dedicated systems for each modality.

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

2Measurement precision

If the system waits for passenger confirmation before executing actions, then the measurement precision of passenger intent is improved, but the loss of time increases

Engineering Contradiction:
Improvepassenger intent precisionVSAvoidinteraction time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system provides preliminary instructions to the passenger indicating what action will be taken based on their input. For example, when the passenger speaks a command, the system immediately displays or announces the interpreted action before execution, allowing the passenger to confirm or correct without significant delay.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by displaying or announcing the interpreted passenger intent before execution. This feedback loop allows the passenger to verify the system's understanding of their request, improving measurement precision of intent while minimizing time loss through efficient confirmation processes.

Inventive Principle:
Principle #23Feedback

3Ease of operation

If the system provides detailed instructions to the passenger, then the ease of operation is improved, but the loss of time increases

Engineering Contradiction:
Improveinteraction easeVSAvoidinstruction time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system provides instructions selectively rather than always. When the passenger's intent is clear from the initial input, the system may execute without additional instructions. Instructions are provided partially only when needed to clarify ambiguous situations, balancing ease of operation with time efficiency.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system prepares and displays instructions in advance of execution, allowing the passenger to quickly understand and confirm the intended action. This preliminary presentation of instructions minimizes the time required for the passenger to process and respond.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20250384879A1Multimodal virtual assistant
Publication Date: 2025.12.18 GM GLOBAL TECHNOLOGY OPERATIONS LLC
  • US20250384879A1 patent drawing
  • US20250384879A1 patent drawing
  • US20250384879A1 patent drawing

AI summary

Methods and systems are provided that include one or more first sensors, one or more second sensors, and a processor of a vehicle. The one or more first sensors have a first modality, and are configured to receive a first input from a passenger of the vehicle pertaining to a request. The processor is configured to at least facilitate providing instructions to the passenger for providing an additional input pertaining to the request within a predetermined amount of time. The one or more second sensors have a second modality that is different from the first modality, and are configured to receive a second input from the passenger pertaining to the request. The processor is further configured to at least facilitate interpreting the second input; and performing a vehicle action corresponding to the request based on the interpreting of the second input.