Learning control vehicle

• US 5,521,823 A
• Filed: 12/13/1994
• Issued: 05/28/1996
• Est. Priority Date: 09/03/1991
• Status: Expired due to Term

• Current Assignee: Mazda Motor Corporation
• Original Assignee: Mazda Motor Corporation
• Inventors: Miyamoto, Seiji, Akita, Ryuya, Sakamoto, Kiyoshi, Ohmura, Hiroshi, Hirabayashi, Shigefumi, Takehara, Shin, Shibata, Mineharu
• Primary Examiner(s): NOT, DEFINED
• Assistant Examiner(s): Walder, Jr., Stephen J.
• Application Number:
  US08/357,266
• Time in Patent Office: 532 Days
• Field of Search: 364/424.01, 364/424.05, 364/426.01, 364/425, 364/431.04, 364/431.06, 364/151, 364/160, 364/157, 364/449, 395/903, 395/905, 395/913, 340/901, 340/902, 340/903, 340/904, 180/170
• US Class Current: 701/36
• CPC Class Codes: B60G 17/0195 characterised by the regulation being combined with other vehicle control systems conjoint control of vehicle sub-units including control of suspension systems B60W10/22
• CPC Class Codes: B60T 2220/02 Driver type; Driving style; Driver adaptive features
• CPC Class Codes: B60T 8/174 characterised by using special control logic, e.g. fuzzy logic , neural computing
• CPC Class Codes: B60W 10/06 including control of combustion engines
• CPC Class Codes: B60W 10/10 including control of change-speed gearings
• CPC Class Codes: B60W 10/20 including control of steering systems
• CPC Class Codes: B60W 10/22 including control of suspension systems
• CPC Class Codes: B60W 2050/0022 Gains, weighting coefficients or weighting functions
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2050/0095 Automatic control mode change
• CPC Class Codes: B60W 2520/105 Longitudinal acceleration
• CPC Class Codes: B60W 2520/14 Yaw
• CPC Class Codes: B60W 2540/043 Identity of occupants
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/0098 Details of control systems ensuring comfort, safety or stability not otherwise provided for
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A vehicle having learning control includes a running condition detecting device for detecting a driving condition of the vehicle, a running characteristic control device for controlling a control gain to change a running characteristic of the vehicle and a gain control device for learning the running characteristic of the vehicle to change the control gain. The running characteristics of the vehicle can be controlled corresponding to various running conditions.

Claims

1. A learning control vehicle comprising:

running condition detecting means for detecting a running condition of a vehicle,

running characteristic control means for controlling a control gain to change a running characteristic of the vehicle,

gain control means for learning the running characteristic of the vehicle to change the control gain based on operation of the vehicle by a driver which is learned in a learning control program,

location detecting means for detecting a location of the vehicle, and

a driver identifying means for allowing the learning performed in said learning control program to change the control gain only when a specific driver is identified,

the gain control means controlling the running characteristic control means in accordance with the learning control program based on a location signal which is produced by the location detecting means.

2. A learning control vehicle as recited in claim 1 further comprising first program memory means for storing a standard program which learns and changes the control gain in accordance with the driver'"'"'s operation in a driving area classified in connection with the running condition of the vehicle, the gain control means controlling the running characteristic control means in accordance with the standard program based on a location signal which is produced by said location detecting means.

3. A learning control vehicle as recited in claim 1 and further comprising:

location detecting means for detecting a location of the vehicle,

program memory means for storing a designated program, in which the control gain is provided according to a driving area in which the vehicle runs, and a standard program, in which the control gain is changed depending on the driving area and the operation of the vehicle by the driver and learned corresponding to each driver,

the gain control means changing the control gain based on one of the designated and standard programs selected based on a signal from the driver identifying means.

4. A learning control vehicle comprising:

running condition detecting means for detecting a running condition of a vehicle,

running characteristic control means for controlling a control gain to change a running characteristic of the vehicle,

gain control means for learning the running characteristic of the vehicle to change the control gain based on operation of the vehicle by a driver which is learned in a learning control program,

a driver identifying means for allowing the learning performed in said learning control program to change the control gain when a specific driver is identified,

location detecting means for detecting a location of the vehicle,

program memory means for storing a designated program, in which the control gain is provided according to a driving area in which the vehicle runs, and a standard program, in which the control gain is changed depending on the driving area and the operation of the vehicle by the driver and learned corresponding to each driver,

the gain control means changing the control gain based on one of the designated and standard programs selected based on a signal from the driver identifying means,

first program memory means for storing a standard program which learns and changes the control gain in accordance with the driver'"'"'s operation in a driving area classified in connection with the running condition of the vehicle, the gain control means controlling the running characteristic control means in accordance with the standard program based on a location signal which is produced by said location detecting means, and

second program memory means for storing a designated program which provides uniform control gain in accordance with a driving area classified in connection with the running condition of the vehicle, the gain control means controlling the running characteristic control means in accordance with the designated program based on a location signal which is produced by the location detecting means.

5. A learning control vehicle as recited claim 4 wherein the program memory means further stores a learning control program including a terrain learning program which learns the terrain within a specific area and an operation learning program which learns the driver'"'"'s operation,

the gain control means selecting the learning control program to change the control gain when the driver identifying means identifies the specific driver and when the location detecting means detects that the vehicle runs within a specific area.

6. A learning control vehicle as recited in claim 5 wherein when the vehicle runs within the specific area even when the driver is not the specific driver, the gain control means may select the terrain learning program of the learning control program.

7. A learning control vehicle as recited in claim 5 wherein the gain control means selects the designated program when the driver is not the specific driver or when the vehicle does not run in the specific area.

8. A learning control vehicle as recited in claim 4 wherein the driver identifying means identifies the specific driver based on features of the driver'"'"'s operation.

9. A learning control vehicle as recited in claim 4 wherein the driver identifying means identifies the specific driver by a bodily feature.

10. A learning control vehicle as recited in claim 4 wherein the driver identifying means is provided with a manual input means for producing an identity signal when specific information about the driver is manually provided and identifies the specific driver when the identity signal is detected.

11. A learning control vehicle as recited in claim 4 wherein the driver identifying means identifies the specific driver by at least two articles belonging to the driver, the driver'"'"'s operation and a bodily feature.

12. A learning control vehicle as recited in claim 4 wherein when the specific driver changes to another and vice versa, the gain control means changes the learning control program a predetermined time period after the change of the driver.

13. A learning control vehicle as recited in claim 4 wherein terrain learning control is carried out by selecting the standard program in which the control gain varies depending on the driver and a classified area where the vehicle runs or by selecting the designated program in which a constant control gain is allotted depending on the classified area.

14. A learning control vehicle as recited in claim 4 wherein the running characteristic of the vehicle is controlled by changing the control gain in accordance with classified areas which include a city area, an urban area, a suburban area, a mountain area, and a free way.

15. A learning control vehicle as recited in claim 4 wherein the running characteristic is controlled by changing the control gain in accordance with the operation of the vehicle by utilizing the standard program to match a frequent driver'"'"'s personality.

16. A learning control vehicle as recited in claim 4 wherein the gain control means stops a learning control through the standard program and controls the running characteristic control means in accordance with the designated program under a specific running condition.

17. A learning control vehicle as recited in claim 16 wherein a program memory stores designated programs for a normal running condition of the vehicle and a stable running program for improving a running stability of the vehicle under the specific running condition.

18. A learning control vehicle as recited in claim 17 wherein when a lateral acceleration acting on the vehicle in a lateral direction is greater than a predetermined value, the gain control means stops the learning control and control the running characteristic control means in accordance with the stable running program.

19. A learning control vehicle as recited in claim 17 wherein when friction between a wheel and road surface on which the vehicle runs is lower than a predetermined value, the gain control means stops the learning control program and controls the running characteristic control means in accordance with the stable running program.

20. A learning control vehicle as recited in claim 17 wherein when the program is changed as the gain control means stops the learning control and controls the running characteristic control means in accordance with the stable running program, the gain control means controls the running characteristic control means to change the control gain gradually.

21. A learning control vehicle as recited in claim 4 wherein the location detecting means detects the location of the vehicle by a navigation system which provides the location of the vehicle automatically.

22. A learning control vehicle as recited in claim 4 wherein the location detecting means detects the location of the vehicle by a manual device through which the driver inputs the location of the vehicle manually.

53. A learning control vehicle as recited in claim 4 wherein the driver identifying means identifies the driver by an article belonging to the driver.

23. A learning control vehicle comprising:

running condition detecting means for detecting a running condition of a vehicle,

running characteristic control means for controlling a control gain to change a running characteristic of the vehicle,

gain control means for learning the running characteristic of the vehicle to change the control gain based on operation of the vehicle by a driver which is learned in a learning control program, and

a driver identifying means for allowing the learning performed in said learning control program to change the control gain when a specific driver is identified,

wherein the gain control means controls the running characteristic control means to change the control gain in accordance with a learning program which learns the specific driver'"'"'s operation in a specific area which is defined as an area within a predetermined distance from a base point and in accordance with a standard program which learns and changes the control gain in accordance with the specific driver'"'"'s operation in a driving area classified in connection with the running condition of the vehicle when the specific driver drives the vehicle outside of the specific area.

24. A learning control vehicle as recited in claim 23 wherein the gain control means controls the running characteristic to change the control gain in accordance with one of the learning and standard programs.

25. A learning control vehicle as recited in claim 23 wherein the learning program is produced as the gain control means learns the terrain and the driver'"'"'s operation within the specific area.

26. A learning control vehicle as recited in claim 25 wherein the gain control means learns the driver'"'"'s operation in a predetermined hourly period of a day in the specific area to produce the learning program.

27. A learning control vehicle as recited in claim 25 wherein the gain control means controls the running characteristic control means to change the control gain in accordance with the standard program before the learning program is produced.

28. A learning control vehicle as recited in claim 25 wherein the gain control means learns the driver'"'"'s operation in a unit zone defined in the specific area.

29. A learning control vehicle as recited in claim 28 wherein the unit zone is provided as a predetermined distance in the specific area, adjacent unit zones including an overlapped portion of a certain distance.

30. A learning control vehicle as recited in claim 28 wherein the unit zone is provided as a predetermined running time period in the specific area, adjacent unit zones including an overlapped portion of a certain running time of the vehicle.

31. A learning control vehicle as recited in claim 25 wherein the gain control means learns a terrain in a unit zone defined in the specific area.

32. A learning control vehicle comprising:

running condition detecting means for detecting a running condition of a vehicle,

running characteristic control means for controlling a control gain to change a running characteristic of the vehicle,

gain control means for learning the running characteristic of the vehicle to change the control gain based on operation of the vehicle by a driver which is learned in a learning control program, and

a driver identifying means for allowing the learning performed in said learning control program to change the control gain when a specific driver is identified,

wherein the gain control means controls the running characteristic control means to change the control gain in accordance with a learning program which learns the driver'"'"'s operation in a specific area determined by said location detecting means which is defined as an area within a predetermined distance from a base point.

33. A learning control vehicle as recited in claim 32 and further comprising location detecting means for detecting a location at which the vehicle runs, the gain control means suspending the learning control program when the gain control means does not receive a location signal from the location detecting means.

34. A learning control vehicle as recited in claim 32 and further comprising location detecting means for detecting a location at which the vehicle runs, the gain control means controlling the running characteristic control means in accordance with the designated program when the gain control means holds that a location signal from the location detecting means indicates that the vehicle is not running in the specific area.

35. A learning control vehicle as recited in claim 32 and further comprising location detecting means for detecting a location at which the vehicle runs, the gain control means controlling the running characteristic control means in accordance with the standard program when the gain control means holds that a location signal from the location detecting means indicates that the vehicle is not running in the specific area.

36. A learning control vehicle as recited in claim 32 and further comprising location detecting means for detecting a location at which the vehicle runs, the gain control means controls the running characteristic control means to learn and compensate the control gain based on the location of the vehicle, compensation of the control gain being changed in accordance with the number of control gain compensations.

37. A learning control vehicle as recited in claim 36 wherein the gain control means samples running data in the same hourly period in the same unit zone in the specific area and compensates the control gain based on the sampled running data in accordance with a learning control.

38. A learning control vehicle as recited in claim 37 wherein as the number of the renewal of the control gain as a result of the compensation is increased, the unit zone for the sampling is reduced.

39. A learning control vehicle as recited in claim 37 wherein as the number of the renewal of the control gain as a result of the compensation is increased, the hourly period for the sampling is reduced.

40. A learning control vehicle as recited in claim 36 wherein the gain control means compensates and renews the control gain by a learning control when the vehicle runs in the same area.

41. A learning control vehicle as recited in claim 36 wherein the compensation for the control gain is reduced when the driver'"'"'s operation does not change substantially in view of statistic data in spite of an increase of the number of the renewal of the control gain.

42. A learning control vehicle as recited in claim 41 wherein the control gain is reduced when the operation of the acceleration pedal is not changed statistically and substantially in spite of an increase of the number of the renewal of the control gain.

43. A learning control vehicle as recited in claim 41 wherein the control gain is reduced when the operation of a shift lever is not changed statistically and substantially in spite of an increase of the number of the renewal of the control gain.

44. A learning control vehicle as recited in claim 41 wherein the control gain is reduced when the operation of a steering wheel is not changed statistically and substantially in spite of an increase of the number of the renewal of the control gain.

45. A learning control vehicle as recited in claim 36 wherein the control gain is compensated so as to improve the running stability of the vehicle when the driver'"'"'s operation does not change substantially in view of statistic data in spite of an increase of the number of the renewal of the control gain.

46. A learning control vehicle as recited in claim 36 wherein the control gain is compensated to a predetermined value when the driver'"'"'s operation does not change substantially in view of statistic data in spite of an increase of the number of the renewal of the control gain.

47. A learning control vehicle as recited in claim 36 wherein the control gain is temporarily increased when the driver'"'"'s operation does not change statistically and substantially in spite of an increase of the number of the renewal of the control gain, and then the control gain is reduced eventually if the driver'"'"'s operation does not change irrespective of the temporary increase of the control gain.

48. A learning control vehicle as recited in claim 47 wherein the control gain is reduced gradually after the temporary increase thereof.

49. A learning control vehicle as recited in claim 36 wherein the control gain is temporarily increased when the driver'"'"'s operation does not change statistically and substantially in spite of an increase of the number of the renewal of the control gain, and then the control gain is reduced eventually if the operation of an acceleration pedal does not change irrespective of the temporary increase of the control gain.

50. A learning control vehicle as recited in claim 36 wherein the control gain is temporarily increased when the driver'"'"'s operation does not change statistically and substantially in spite of an increase of the number of the renewal of the control gain, and then the control gain is reduced eventually if the operation of a shift lever does not change irrespective of the temporary increase of the control gain.

51. A learning control vehicle as recited in claim 36 wherein the control gain is temporarily increased when the driver'"'"'s operation does not change statistically and substantially in spite of an increase of the number of the renewal of the control gain, and then the control gain is reduced eventually if the operation of a steering wheel does not change irrespective of the temporary increase of the control gain.

52. A learning control vehicle as recited in claim 36 wherein the gain control means suspends the learning control when the driver'"'"'s operation is substantially different from the driver'"'"'s operation obtained through the learning control.