Mobile object control device, mobile object control method, and storage medium
A mobile object control device acquires a captured image obtained by capturing an image of surroundings of the mobile object by a camera mounted on a mobile object and an input directive sentence input by a user of the mobile object, inputs, when an image and a directive sentence are input, the captured image and the input directive sentence into a learned model learned to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty, sequentially selects the one or more objects based on at least the degree of certainty and makes an inquiry to a user of the mobile object, and causes the mobile object to travel to an indicated position in the input directive sentence, which is specified based on a result of the inquiry.
1. A mobile object control device of a mobile object, comprising:
a storage medium configured to store an instruction readable by a computer, and
a processor connected to the storage medium,
wherein the processor executes the instruction readable by the computer, thereby
acquiring a captured image obtained by capturing an image of surroundings of the mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object,
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty,
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object, and
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry,
wherein the processor selects, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and makes an inquiry to the user of the mobile object, and
wherein the processor selects objects in descending order of score values further considering a horizontal position of the acquired one or more objects in the captured image, and makes an inquiry to the user of the mobile object.
2. The mobile object control device of the mobile object according to claim 1 ,
wherein the processor classifies the acquired one or more objects into one or more classes, selects objects in descending order of score values further considering a classification ratio of the one or more classes, and makes an inquiry to the user of the mobile object.
3. The mobile object control device of the mobile object according to claim 1 ,
wherein the processor selects objects in descending order of score values further considering a moving tendency of the acquired one or more objects, and makes an inquiry to the user of the mobile object.
4. A mobile object control method for controlling a mobile object, comprising:
by a computer,
acquiring a captured image obtained by capturing an image of surroundings of the mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object;
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty;
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object;
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry,
selecting, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and making an inquiry to the user of the mobile object, and
selecting objects in descending order of score values further considering a horizontal position of the acquired one or more objects in the captured image, and making an inquiry to the user of the mobile object.
5. A computer-readable non-transitory storage medium that stores a program causing a computer to execute;
acquiring a captured image obtained by capturing an image of surroundings of a mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object,
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty,
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object,
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry,
selecting, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and making an inquiry to the user of the mobile object, and
selecting objects in descending order of score values further considering a horizontal position of the acquired one or more objects in the captured image, and making an inquiry to the user of the mobile object.
6. A mobile object control device of a mobile object, comprising:
a storage medium configured to store an instruction readable by a computer, and
a processor connected to the storage medium,
wherein the processor executes the instruction readable by the computer, thereby
acquiring a captured image obtained by capturing an image of surroundings of the mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object,
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty,
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object, and
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry,
wherein the processor selects, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and makes an inquiry to the user of the mobile object, and
wherein the processor classifies the acquired one or more objects into one or more classes, selects objects in descending order of score values further considering a classification ratio of the one or more classes, and makes an inquiry to the user of the mobile object.
7. A mobile object control method for controlling a mobile object, comprising:
by a computer,
acquiring a captured image obtained by capturing an image of surroundings of the mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object;
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty;
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object;
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry;
selecting, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and making an inquiry to the user of the mobile object; and
classifying the acquired one or more objects into one or more classes, selecting objects in descending order of score values further considering a classification ratio of the one or more classes, and making an inquiry to the user of the mobile object.
8. A computer-readable non-transitory storage medium that stores a program causing a computer to execute:
acquiring a captured image obtained by capturing an image of surroundings of a mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object,
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty,
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object,
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry,
selecting, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and making an inquiry to the user of the mobile object, and
classifies the acquired one or more objects into one or more classes, selects objects in descending order of score values further considering a classification ratio of the one or more classes, and makes an inquiry to the user of the mobile object.
9. A mobile object control device of a mobile object, comprising:
a storage medium configured to store an instruction readable by a computer, and
a processor connected to the storage medium,
wherein the processor executes the instruction readable by the computer, thereby
acquiring a captured image obtained by capturing an image of surroundings of the mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object,
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty,
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object, and
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry,
wherein the processor selects, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and makes an inquiry to the user of the mobile object, and
wherein the processor selects objects in descending order of score values further considering a moving tendency of the acquired one or more objects, and makes an inquiry to the user of the mobile object.
10. A mobile object control method for controlling a mobile object, comprising:
by a computer,
acquiring a captured image obtained by capturing an image of surroundings of the mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object;
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty;
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object;
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry;
selecting, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and making an inquiry to the user of the mobile object; and
selecting objects in descending order of score values further considering a moving tendency of the acquired one or more objects, and making an inquiry to the user of the mobile object.
11. A computer-readable non-transitory storage medium that stores a program causing a computer to execute:
acquiring a captured image obtained by capturing an image of surroundings of a mobile object via a camera mounted on the mobile object and an input directive sentence input by a user of the mobile object,
inputting the captured image and the input directive sentence into a machine learning model trained to output one or more objects corresponding to the directive sentence in the image together with corresponding degrees of certainty to detect the one or more objects and the corresponding degrees of certainty,
sequentially selecting the one or more objects on the basis of at least the degree of certainty and making an inquiry to the user of the mobile object,
causing the mobile object to travel to an indicated position in the input directive sentence, which is specified on the basis of a result of the inquiry,
selecting, among the acquired one or more objects, objects in descending order of score values considering at least the degree of certainty, and making an inquiry to the user of the mobile object, and
selecting objects in descending order of score values further considering a moving tendency of the acquired one or more objects, and making an inquiry to the user of the mobile object.