Unmanned vehicle remote voice interaction system

By designing a remote voice interaction system for unmanned vehicles, two-way voice interaction between the back-end and on-site personnel and the acquisition of ambient sound were realized. This solved the problems of one-way communication and insufficient acquisition of ambient sound in existing unmanned vehicle voice interaction systems, and provided personalized voice prompts and reduced power consumption.

CN121838804APending Publication Date: 2026-04-10JIUZHI (SUZHOU) INTELLIGENT TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-31
Publication Date
2026-04-10

AI Technical Summary

Technical Problem

Existing voice interaction systems for autonomous vehicles cannot enable voice interaction between back-end operators and on-site personnel, nor can they obtain real-time ambient sound information about the vehicle's surroundings. The voice broadcasts are one-way and cannot provide personalized reminders based on user needs.

Method used

Design an unmanned vehicle remote voice interaction system, including a sound pickup device, a speaker, a voice control module, an unmanned vehicle controller, a gateway device, and a cloud platform. It supports voice broadcasting, sound pickup, shouting, and intercom modes. The cloud platform enables switching between multiple working modes and data transmission, and realizes two-way voice interaction between the back-end and the field.

Benefits of technology

It enables real-time voice interaction between back-end and on-site personnel and real-time acquisition of ambient sound, supports personalized voice prompts, and is particularly suitable for communication in areas with severe dialects or language barriers, while reducing power consumption and storage requirements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121838804A_ABST
    Figure CN121838804A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of voice interaction, in particular to an unmanned vehicle remote voice interaction system which comprises a pickup device, a loudspeaker, a voice control module, an unmanned vehicle controller, a gateway device and a cloud platform. The pickup device and the loudspeaker are both connected with the voice control module, and the voice control module is connected with the unmanned vehicle controller; the unmanned vehicle controller is connected with the cloud platform through the gateway device. The voice control module has four working modes: a voice broadcast mode, wherein the voice control module carries out automatic voice broadcast through a loudspeaker; in the pickup mode, the voice control module picks up sound of the surrounding environment of the vehicle through pickup equipment; in the calling mode, background personnel turn on the loudspeaker through the voice control module to execute a calling function; in the talkback mode, the voice control module turns on the pickup device and the loudspeaker, and the talkback requirement of the background personnel and the field personnel is met. According to the invention, voice broadcast and voice interaction scenes required by operation of the unmanned vehicle can be satisfied, and the operation condition of the unmanned vehicle can be known in time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of voice interaction technology, and more specifically to a remote voice interaction system for unmanned vehicles. Background Technology

[0002] With the development of AI technology and new energy vehicles, the integration of the two is becoming increasingly close. Whether it's passenger cars or freight vehicles, they are steadily moving towards unmanned applications. Vehicle driving and operation scenarios are becoming increasingly complex and diverse, especially in labor-intensive scenarios such as express delivery and supermarket delivery. Unmanned vehicle applications are gradually entering the public eye. As a new type of vehicle or equipment, unmanned vehicles have appeared in the public eye with their significant unmanned characteristics, arousing curiosity and attention from users and the public. However, given that unmanned driving technology is not yet fully mature, and considering its unmanned nature, some unexpected situations or scenarios requiring interaction between on-site personnel and back-end operations staff are inevitable. Therefore, unmanned vehicles need to be equipped with remote voice interaction systems.

[0003] Common voice interaction or safety prompts for autonomous vehicles are usually text-based voice broadcasts. That is, the vehicle controller controls the voice broadcast content based on preset broadcast content and driving status to prompt people and other vehicles outside the vehicle.

[0004] In current autonomous vehicle voice interaction systems, the control system broadcasts voice messages according to pre-defined rules based on the vehicle's operating status. For example, when the vehicle turns left or right, the controller recognizes the turning behavior and sends the desired voice message via TTS (Text-to-Speech) to be amplified and played through a speaker. However, TTS typically only plays pre-set or pre-defined content and cannot provide personalized reminders to people around the vehicle. Furthermore, text-based audio transmission is unidirectional, failing to enable voice interaction between back-end operators and on-site personnel, and also preventing the acquisition of ambient sound information about people and the surrounding environment. Summary of the Invention

[0005] This invention proposes a remote voice interaction system for unmanned vehicles, addressing the voice broadcasting and voice interaction scenarios required for unmanned vehicle operation.

[0006] Terminology Explanation: Unless otherwise defined, all technical terms used herein have the same meanings as commonly understood by one of ordinary skill in the art. Unless otherwise stated, all patents, patent inventions, and disclosures cited throughout this document are incorporated herein by reference in their entirety. If multiple definitions exist for terms herein, the definitions provided in this chapter shall prevail.

[0007] It should be understood that the above brief description and the following detailed description are exemplary and for illustrative purposes only, and do not limit the subject matter of the invention in any way. In this invention, the singular is used in conjunction with the plural unless otherwise specifically stated. It should also be noted that, unless otherwise stated, the use of “or” or “or” means “and / or”. Furthermore, the use of the term “comprising” and other forms such as “including,” “containing,” and “contains” are not limiting.

[0008] To achieve the above objectives, the technical solution of the present invention is as follows: An unmanned vehicle remote voice interaction system includes: a sound pickup device, a speaker, a voice control module, an unmanned vehicle controller, a gateway device, and a cloud platform; Both the sound pickup device and the speaker are connected to the voice control module, which is connected to the unmanned vehicle controller; the unmanned vehicle controller is connected to the cloud platform through a gateway device. The voice control module has four operating modes: The first working mode: voice broadcast mode, in which the voice control module automatically broadcasts voice information through the speaker; The second working mode: sound pickup mode, in which the voice control module picks up the sounds of the surrounding environment of the vehicle through the sound pickup device; The third working mode: the announcement mode, where back-end staff use the voice control module to turn on the speaker and execute the announcement function; The fourth working mode: intercom mode, where the voice control module turns on the microphone and speaker to enable intercom between back-office staff and on-site staff.

[0009] Furthermore, the cloud platform is equipped with buttons that can be used to send demand commands to the unmanned vehicle controller, thereby enabling the switching of different working modes.

[0010] Furthermore, the unmanned vehicle controller and the voice control module communicate via Ethernet.

[0011] Furthermore, the sound pickup device is a microphone or a pickup unit.

[0012] Furthermore, when in intercom mode, the unmanned vehicle controller defaults to turning on the microphone for a set time. If continuous voice input is detected at the vehicle site during this time, the microphone's on-time will be refreshed.

[0013] Furthermore, the microphone is switched off when the vehicle does not require intercom communication.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention allows for real-time acquisition and recording of sound information about personnel and the surrounding environment at the vehicle location, as needed. Additionally, it enables real-time voice alerts to nearby personnel or vehicles via a broadcast system. Furthermore, it allows for real-time voice interaction between remote monitoring personnel and on-site staff, with the recording of relevant audio. This is particularly beneficial in areas with severe dialect differences or language barriers, where local operators can utilize voice interaction or intercom to communicate with local personnel at the vehicle location in real-time as needed.

[0015] When in voice intercom mode, if continuous voice input is detected at the vehicle location, the microphone activation time will be refreshed. This ensures the intercom mode continues while also turning off the microphone to reduce power consumption and storage when there is no intercom need in the vicinity. Attached Figure Description

[0016] Figure 1 This is a system architecture diagram of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are not all embodiments of the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0018] It should be noted that, unless otherwise specifically stated, the relative arrangement and numerical expressions of the components and steps described in these embodiments should not be construed as limiting the scope of the invention.

[0019] The following description of exemplary embodiments is merely illustrative and is not intended to limit the invention or its application or use in any way. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail herein, but where applicable, such techniques, methods, and apparatus should be considered part of this specification.

[0020] This embodiment provides a remote voice interaction system for unmanned vehicles, such as... Figure 1 As shown, it includes: a sound pickup device, a speaker, a voice control module, an unmanned vehicle controller, a gateway device, and a cloud platform; After the system is powered on, the voice control module defaults to text and voice broadcast mode. At this time, the unmanned vehicle controller will broadcast reminders according to the vehicle's driving status and the set rules and content.

[0021] When it is necessary to obtain the sound status of people or the environment at the vehicle site, the back-end personnel send a command to the voice control module via the autonomous vehicle controller through a setting button, which then activates the microphone. The button is located on the cloud platform. After the button is pressed, the cloud sends a command to the autonomous vehicle controller, which then controls the operation of the voice control module via Ethernet or other means.

[0022] The microphone detects ambient sound. Once the voice control module receives the corresponding sound signal, it samples and quantizes it using an ADC (typically, the microphone emits an analog signal, requiring sampling and encoding in later processing; if it's a digital microphone, no additional sampling is needed), and then transmits it to the autonomous vehicle controller. The microphone is connected to the voice controller via hardwired connections, such as for analog signals or I2C digital signals.

[0023] After the unmanned vehicle controller collects the coded sound information, it stores the data and uploads it to the cloud platform through the gateway device. Back-end operations or monitoring personnel can then obtain the corresponding sound information from the cloud platform.

[0024] When special voice prompts are needed for people or vehicles in the vicinity of the vehicle, the back-end personnel can use a setting button to send a message to the voice control module via the autonomous vehicle controller, activating the speaker and executing the announcement function. The back-end personnel's voice prompts are then sampled by their own microphone (a back-end microphone, such as a computer or mobile phone microphone) and transmitted to the cloud platform via the terminal device. The cloud platform communicates with the vehicle in real time and sends the sound to the autonomous vehicle controller through a gateway.

[0025] For example, after a vehicle stops, if a remote monitoring person notices that the vehicle has stopped moving, they can use the loudspeaker function to remind people around the vehicle to give way or to check on the vehicle's status.

[0026] The autonomous vehicle controller then sends the encoded data to the voice control module. Upon receiving the data, the voice control module restores the sound signal according to the encoding rules (such as PCM encoding), and after DAC conversion and analog amplification, it is played through the speaker to provide voice reminders to people around the vehicle.

[0027] When back-end operations or monitoring personnel need to interact with people around the vehicle via voice, they can use a setting button to send a command to the voice control module through the autonomous vehicle controller. This activates the speaker and microphone, enabling remote voice communication. The personnel's voice is then captured and encoded by their terminal device and transmitted to the voice control module via the cloud platform, gateway, and autonomous vehicle controller. The voice control module reconstructs the received data according to specified encoding rules, amplifies it using a DAC, and outputs it to the speaker.

[0028] On the other hand, the voices of on-site personnel are collected by the vehicle's audio pickup device, sampled and encoded by the voice control module, and then transmitted via the autonomous vehicle controller, gateway device, and cloud platform to the terminal device of the back-end personnel. This enables voice interaction between remote back-end personnel and on-site personnel. During voice communication, the controller records and stores the conversation between back-end personnel and on-site personnel in real time for subsequent understanding of the surrounding situation.

[0029] When in voice intercom mode for remote voice interaction, the autonomous vehicle controller will turn on the microphone for a certain period of time by default. When continuous voice input is detected at the vehicle site, the microphone on time will be refreshed to ensure that the microphone can work continuously in intercom mode. At the same time, when there is no intercom need in the vicinity, the microphone can be turned off to reduce power consumption and storage.

[0030] The need for intercom depends on the vehicle's operating status, which is obtained through information exchange between the vehicle's own sensors or control modules and the back-end monitoring equipment. Back-end monitoring personnel can use the back-end monitoring equipment to understand whether the vehicle is abnormal. When the vehicle is unable to drive or in other abnormal situations, the intercom mode is switched on.

[0031] The above specific embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to examples, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the protection scope of the present invention.

Claims

1. A remote voice interaction system for unmanned vehicles, characterized in that, include: Sound pickup devices, speakers, voice control modules, unmanned vehicle controllers, gateway devices, and cloud platforms; Both the sound pickup device and the speaker are connected to the voice control module, which is connected to the unmanned vehicle controller; the unmanned vehicle controller is connected to the cloud platform through a gateway device. The voice control module has four operating modes: The first working mode: voice broadcast mode, in which the voice control module automatically broadcasts voice information through the speaker; The second working mode: sound pickup mode, in which the voice control module picks up the sounds of the surrounding environment of the vehicle through the sound pickup device; The third working mode: the announcement mode, where back-end staff use the voice control module to turn on the speaker and execute the announcement function; The fourth working mode: intercom mode, where the voice control module turns on the microphone and speaker to enable intercom between back-office staff and on-site staff.

2. The unmanned vehicle remote voice interaction system according to claim 1, characterized in that, The cloud platform is equipped with buttons that can be used to send demand commands to the unmanned vehicle controller, thereby enabling the switching of different working modes.

3. The unmanned vehicle remote voice interaction system according to claim 1, characterized in that, The unmanned vehicle controller and the voice control module communicate via Ethernet.

4. The unmanned vehicle remote voice interaction system according to claim 1, characterized in that, The sound pickup device is a microphone or a pickup unit.

5. The unmanned vehicle remote voice interaction system according to claim 1, characterized in that, When in intercom mode, the autonomous vehicle controller defaults to turning on the microphone for a set time. If continuous voice input is detected at the vehicle location within this time, the microphone's on time will be refreshed.

6. The unmanned vehicle remote voice interaction system according to claim 5, characterized in that, When there is no need for intercom communication in the vehicle, the microphone is turned off.