User adaptive control of object having pseudo-emotions by learning adjustments of emotion generating and behavior generating algorithms

• US 6,175,772 B1
• Filed: 04/13/1998
• Issued: 01/16/2001
• Est. Priority Date: 04/11/1997
• Status: Expired due to Fees

• Current Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation)
• Original Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation)
• Inventors: Kamiya, Tsuyoshi, Sakaue, Masaya
• Primary Examiner(s): Lee, Thomas C.
• Assistant Examiner(s): WANG, ALBERT C
• Application Number:
  US09/059,278
• Time in Patent Office: 1,009 Days
• Field of Search: 700/245, 700/1, 700/19, 700/259, 700/31, 701/1, 701/59, 382/104
• US Class Current: 700/31
• CPC Class Codes: F24F 11/30 for purposes related to the operation of the system, e.g. for safety or monitoring
• CPC Class Codes: F24F 11/62 characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
• CPC Class Codes: F24F 2110/10 Temperature
• CPC Class Codes: F24F 2110/12 of the outside air
• CPC Class Codes: F24F 2110/20 Humidity
• CPC Class Codes: F24F 2110/22 of the outside air
• CPC Class Codes: F24F 2110/32 of the outside air
• CPC Class Codes: F24F 2110/50 Air quality properties
• CPC Class Codes: F24F 2120/10 Occupancy
• CPC Class Codes: F24F 2120/20 Feedback from users
• CPC Class Codes: G06N 3/008 based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
• CPC Class Codes: Y02B 30/70 Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating

Abstract

A control method for controlling operation of an object used by a user in an environment includes the steps of: defining pseudo-emotions of the object for deciding output of the object, in relation to the user'"'"'s state; formulating emotion generation algorithms to establish the relationship between the user'"'"'s state and the pseudo-emotions; formulating behavior decision algorithms to establish the relationship between input, including the pseudo-emotions, and the behavior of the object; detecting the user'"'"'s state; generating a pseudo-emotion of the object based on the user'"'"'s state using the emotion generation algorithms; making the object behave based on the user'"'"'s state and the pseudo-emotion using the behavior decision algorithms; evaluating reaction of the user in response to the behavior of the object; and if the reaction of the user does not match the pseudo-emotion of the object in the emotion generation algorithms, adjusting at least either of the emotion generation algorithms or the behavior decision algorithms, followed by learning the adjustment. The object can detect the user'"'"'s state in a visual, tactile, and auditory manner as do humans, and can act upon generation of pseudo-emotions based thereon. Thus, natural communication between the user and the object can be performed, i.e., more human like communication can be established.

Claims

1. A control method for controlling operation of an object used by a user in an environment, said object capable of receiving signals of variable conditions which represent at least a state of the user and which are associated with operation of the object, said object capable of being programmed to behave in response to the received signals, and method comprising the steps of:

(a) defining pseudo-emotions of the object, which are elements for deciding output of the object, in relation to the signals;

(b) formulating emotion generation algorithms to establish the relationship between the signals and the pseudo-emotions;

(c) formulating behavior decision algorithms to establish the relationship between input, including the pseudo-emotions, and the behavior of the object;

(d) detecting signals of variable conditions and inputting the signals into the object;

(e) generating a pseudo-emotion of the object based on the signals using the emotion generation algorithms;

(f) determining the variable conditions from the signals;

(g) making the object behave based on the variable conditions and the pseudo-emotion using the behavior decision algorithms;

(h) evaluating reaction of the user in response to the behavior of the object;

(i) if the reaction of the user does not match the pseudo-emotion of the object in the emotion generation algorithms, adjusting and updating at least either of the emotion generation algorithms or the behavior decision algorithms, followed by learning the adjustment; and

(j) repeating steps (d) through (i).

2. The control method according to claim 1, further comprising the steps of:

recognizing an intention/emotional expression of the user based on the signals of variable conditions, and using the intention/emotional expression of the user as the signals for formulating the emotion generation algorithms and for generating the pseudo-emotion of the object.

3. The control method according to claim 1, further comprising the steps of:

recognizing an intention/emotional expression of the user based on the signals of variable conditions, and using the intention/emotional expression of the user as the input for formulating the behavior decision algorithms and for deciding the behavior of the object.

4. The control method according to claim 2, further comprising the steps of:

recognizing an intention/emotional expression of the user based on the signals of variable conditions, and using the intention/emotional expression of the user as the input for formulating the behavior decision algorithms and for deciding the behavior of the object.

5. The control method according to claim 2, further comprising the steps of deducing preference/habit of the user from the recognized intention/emotional expression of the user, learning the deduced result, and using the learned deduced result for recognizing the intention/emotional expression of the user.

6. The control method according to claim 3, further comprising the steps of deducing preference/habit of the user from the recognized intention/emotional expression of the user, learning the deduced result, and using the learned deduced result for recognizing the intention/emotional expression of the user.

7. The control method according to claim 3, wherein the behavior decision algorithms output at least a decision of target-achievement action corresponding to the recognized intention/emotional expression of the user and a decision of emotional behavior corresponding to the pseudo-emotion of the object, wherein the order of priority is set for each decision based on the pseudo-emotion of the object, and the behavior decision algorithms output either decision based on the order of priority.

8. The control method according to claim 1, wherein the signals of variable conditions are detected using sense-based detecting means.

9. The control method according to claim 1, wherein the signals of variable conditions are selected from the group consisting of the user'"'"'s facial expression, gesture, manner of touching, and voice condition.

10. The control method according to claim 1, wherein the emotion generation algorithms are formulated using basic emotional models corresponding to plural emotional patterns, and output at least one emotional model as the pseudo-emotion.

11. The control method according to claim 10, wherein the emotion generation algorithms are formulated to select one emotional model from the basic emotional models based on the signals of variable conditions, and to output the emotional model as the pseudo-emotion.