# US 10,768,614 B2 · Robot speech control system and method thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,768,614 B2
- Document ID: US10768614B2
- Status: Granted
- Kind: B2
- Application number: 15/904,435
- Filed: 2018-02-26
- Published: 2019-04-11
- Granted: 2020-09-08
- Earliest claimed: 2017-10-05
- Assignees: National Chiao Tung University
- Applicants: National Chiao Tung University
- Inventors: Kai-Tai Song; Yao-Hsang Chen
- Web page: https://patentgrep.com/patent/US10768614B2

## CPC

- G05D 1/0016: {characterised by the operator's input device (input arrangements for computing systems in general G06F3/00)}
- G05D 1/0022: {characterised by the communication link (data switching networks in general H04L12/00)}
- G05D 1/024: {in combination with a laser (lasers per se H01S)}
- G05D 1/0246: {using a video camera in combination with image processing means}
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 2015/223: {Execution procedure of a spoken command}
- Y10S 901/01: Mobile robot
- Y10S 901/09: Closed loop, sensor feedback controls arm movement
- Y10S 901/47: Optical
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- Y10S: TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS

## Abstract

The present disclosure illustrates a robot speech control system including a robot body, a handheld device, a command receiver, an ambient sensor, a processor and a controller. The handheld device includes a display interface and a speech input interface, and the speech input interface is configured to input a speech command which is then converted, by a speech recognition program, into a speech control instruction. An auto-dodge program converts the information into an auto-dodge instruction. The processor receives the speech control instruction and the information associated with the environment, and use Bayesian regression algorithm to calculate a free space probability, so as to obtain weights of a speech command and a dodge command. The processor integrates the speech control instruction and the weight of the speech command, and the auto-dodge instruction and the weight of the dodge command, to generate a movement control instruction.

## Claims

### Claim 1

A robot speech control system, comprising:
a robot body comprising a movement device, wherein the movement device comprises a plurality of turning wheels configured to control the robot body to turn or move;
a handheld device comprising a display interface and a speech input interface, and the speech input interface configured to input a speech command which is then converted, by a speech recognition program, into a speech control instruction;
a command receiver disposed in the robot body and electrically connected to the handheld device through a wireless transmission manner, to receive the speech control command;
an ambient sensor disposed on the robot body and configured to detect information associated with environment around the robot body, wherein an auto-dodge program converts the information into an auto-dodge instruction;
a processor electrically connected to the command receiver and the ambient sensor, and configured to receive the speech control instruction and the information associated with the environment, and use Bayesian regression algorithm to calculate a free space probability, so as to let the free space probability serve as a weight Pf of speech command and obtain a weight Pc, of a dodge command by Pc=1−Pf, wherein the processor integrates the speech control instruction Uh and the weight Pf of the speech command, and the auto-dodge instruction Uc and the weight Pc of the dodge command by Us=Pf×Uh+Pc×Uc, to generate a movement control instruction Us; and
a controller electrically connected to the processor and the movement device, and receive the movement control instruction to drive the movement device.

### Claim 2 (depends on 1)

The robot speech control system according to claim 1, wherein the handheld device comprises a smartphone, a tablet computer or a notebook computer, and the wireless transmission manner comprises a manner of using Wi-Fi or wireless communication network.

### Claim 3 (depends on 1)

The robot speech control system according to claim 1, wherein the ambient sensor comprises a laser scanner configured to measure a distance between the robot body and an obstacle.

### Claim 4 (depends on 1)

The robot speech control system according to claim 1, wherein the ambient sensor is configured to divide the information associated with the environment into a plurality of moving spaces, and the plurality of moving spaces are served as prior probabilities to obtain posterior probabilities of the plurality of moving spaces based on Bayesian regression algorithm, and a maximum of the plurality of posterior probabilities is selected as the free space probability.

### Claim 5 (depends on 4)

The robot speech control system according to claim 4, wherein the plurality of moving spaces comprises a left front space, a front space and a right front space, and the left front space is in a range of angle from a left horizontal line of the robot body to 75 degrees forward, the front space is in a range of angle from 15 degrees left to 15 degrees right, and the right front space is in a range of angle from a right horizontal line of the robot body to 75 degrees forward.

### Claim 6 (depends on 1)

The robot speech control system according to claim 1, further comprising a comparator electrically connected to the processor and configured to compare whether the speech control instruction is equal to a free space instruction corresponding to the free space probability, and the comparator outputs the speech control instruction as an output instruction when the speech control instruction is equal to the free space instruction, and the comparator outputs the free space instruction as the output instruction when the speech control instruction is not equal to the free space instruction.

### Claim 7 (depends on 1)

The robot speech control system according to claim 1, further comprising a camera disposed on the robot body and configured to capture a vision image, and a self-positioning mark of the robot body is displayed on an environment map, and the vision image is transmitted to the handheld device through the wireless transmission manner, for display on the display interface.

### Claim 8

A robot speech control method, configured to control a robot body to move or turn, and the robot body comprising a command receiver, an ambient sensor, a processor, a controller and a movement device, and the robot speech control method comprising:
inputting, through a speech input interface of a handheld device, a speech command, and using a speech recognition program to convert the speech command into a speech control instruction;
transmitting the speech control instruction to a command receiver through a wireless transmission manner;
using an ambient sensor to detect information associated with environment around the robot body, and using an auto-dodge program to convert the information into an auto-dodge instruction;
using the processor to receive the speech control instruction and the information associated with environment, and using Bayesian regression algorithm to calculate a free space probability, so as to let the free space probability serve as a weight Pf of speech command and obtain a weight Pc of dodge command by Pc=1−Pf;
using the processor to integrate the speech control instruction Uh, the weight Pf of speech command, the auto-dodge instruction Uc and the weight Pc of dodge command by Us=Pf×Uh+Pc×Uc, to obtain a movement control instruction Us; and
transmitting the movement control instruction to the controller, and using the controller to drive the movement device to turn or move the robot body.

### Claim 9 (depends on 8)

The robot speech control method according to claim 8, wherein the handheld device comprises a smartphone, a tablet computer or a notebook computer, and the wireless transmission manner comprises a manner of using Wi-Fi or wireless communication network.

### Claim 10 (depends on 8)

The robot speech control method according to claim 8, wherein the ambient sensor uses a laser scanner to measure a distance between the robot body and an obstacle.

### Claim 11 (depends on 8)

The robot speech control method according to claim 8, wherein the ambient sensor is configured to divide the information associated with the environment into a plurality of moving spaces, and the plurality of moving spaces are served as prior probabilities to obtain posterior probabilities of the plurality of moving spaces based on Bayesian regression algorithm, and a maximum of the plurality of posterior probabilities is selected as the free space probability.

### Claim 12 (depends on 11)

The robot speech control method according to claim 11, wherein the plurality of moving spaces comprises a left front space, a front space and a right front space, and the left front space is in a range of angle from a left horizontal line of the robot body to 75 degrees forward, the front space is in a range of angle from 15 degrees left to 15 degrees right in front of the robot body, and the right front space is in a range of angle from a right horizontal line of the robot body to 75 degrees forward.

### Claim 13 (depends on 8)

The robot speech control method according to claim 8, further comprising a step of using a comparator to compare whether the speech control instruction is equal to a free space instruction corresponding to the free space probability, wherein the comparator outputs the speech control instruction as an output instruction when the speech control instruction is equal to the free space instruction, and the comparator outputs the free space instruction as the output instruction when the speech control instruction is not equal to the free space instruction.

### Claim 14 (depends on 8)

The robot speech control method according to claim 8, further comprising a step of using a camera to capture a vision image, and displaying a self-positioning mark of the robot body on an environment map, and transmitting the vision image to the handheld device through the wireless transmission manner, for display on the display interface.