Apparatus for recognizing driving environment of vehicle

• US 5,285,523 A
• Filed: 09/24/1991
• Issued: 02/08/1994
• Est. Priority Date: 09/25/1990
• Status: Expired due to Fees

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan Motor Co., Ltd.
• Inventors: Takahashi, Hiroshi
• Primary Examiner(s): MacDonald, Allen R.
• Application Number:
  US07/764,735
• Time in Patent Office: 868 Days
• Field of Search: 395/11, 395/21, 395/22, 395/905, 364/424.05, 364/424.1, 364/424.01, 74/866
• US Class Current: 706/20
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2530/00 Input parameters relating to vehicle conditions or values, not covered by groups B60W2510/00 or B60W2520/00
• CPC Class Codes: B60W 2540/10 Accelerator pedal position
• CPC Class Codes: B60W 2540/12 Brake pedal position
• CPC Class Codes: B60W 2540/16 Ratio selector position
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: F16H 2059/003 Detecting or using driving style of a driver, e.g. for adapting shift schedules
• CPC Class Codes: F16H 2061/0084 Neural networks
• CPC Class Codes: F16H 59/18 dependent on the position of the accelerator pedal
• CPC Class Codes: F16H 59/24 dependent on the throttle opening
• CPC Class Codes: F16H 59/44 dependent on machine speed of the machine, e.g. the vehicle
• CPC Class Codes: F16H 59/54 dependent on signals from the brakes, e.g. parking brakes
• CPC Class Codes: F16H 59/66 Road conditions, e.g. slope, slippery
• CPC Class Codes: F16H 61/0213 characterised by the method for generating shift signals
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: Y10S 706/905 Vehicle or aerospace

Abstract

An apparatus for recognizing driving environments of a vehicle including a plurality of sensors for detecting various parameters relating to driving conditions of the vehicle such as throttle valve open angle, vehicle running speed, brake pedal depression amount and gear shift range of an automatic transmission, first and second neuron interfaces for converting parameter values detected by the sensors into a plurality of input patterns having predetermined configuration, first and second neural networks having input layers to which corresponding input patterns are applied, hidden layers and output layers for producing recognition results, and a multiplexer for selecting one of the recognition results produced on the output layers of the first and second neural networks. The first neural network has a superior separating or recognizing and learning faculty, while the second neural network has a superior associating faculty. A accelerating pedal depression amount is detected by a sensor and a variation of the thus detected amount is compared with a reference value. When the variation is larger than the reference value, the recognition result produced by the first neural network is selected and when the variation is smaller than the reference value, the recognition result from the second neural network is selected.

Claims

1. An apparatus for recognizing driving environments of a vehicle comprising:

detecting means including a plurality of sensors for detecting parameters which represent operating conditions of the vehicle to produce a set of detected parameter values;

converting means including a plurality of neuron interfaces, each of which receives said set of detected parameter values and produces an input pattern of detected parameters;

recognizing means including a plurality of neural networks having different recognizing and learning faculties and different associating faculties, each of said neural networks comprising an input layer for receiving an input pattern of detected parameters produced by a corresponding neuron interface, an output layer for producing a recognition result, and a hidden layer for coupling said input and output layers with each other; and

selecting means including sensing means for detecting driving conditions of the vehicle directly indicative of vehicle control apparatus positional information within the vehicle to produce a driving condition signal, a signal processing means for processing said driving condition signal to produce a switching signal, and switching means for selecting one of recognition results produced by said plurality of neural networks in accordance with said switching signal.

2. An apparatus according to claim 1, wherein said recognizing means comprises first and second neural networks a recognizing and learning faculty of said first neural network being higher than that of said second neural network, but no associating faculty of said first neural network being lower than that of said second neural network;

and said signal processing means of the selecting means produces a first switching signal for selecting a recognition result produced by said first neural network when said driving condition signal fluctuates largely and produces a second switching signal for selecting a recognition result produced by said second neural network when said driving condition signal fluctuates slightly.

3. An apparatus according to claim 2, wherein said sensing means of the selecting means comprises a sensor for detecting an accelerating pedal depression amount, said signal processing means includes a judging circuit for calculating a variation of the accelerating pedal depression amount and for comparing the thus calculated variation with a predetermined reference value to produce said switching signal, and said switching means comprises a multiplexer for responding to said switching signal such that when said variation is larger than said reference value, the recognition result produced by said first neural network is selected and when said variation is smaller than said reference value, the recognition result produced by said second neural network is selected.

4. An apparatus according to claim 3, wherein said signal processing means of said selecting means produces said variation of the accelerating pedal depression amount by calculating one of dispersion, average spectrum and unbiased dispersion of the detected accelerating pedal depression amount.

5. An apparatus according to claim 4, wherein said detecting means comprises a first sensor for detecting a throttle valve open angle, a second sensor for detecting a vehicle running speed, a third sensor for detecting a brake pedal depression amount and a fourth sensor for detecting a gear shift range of an automatic transmission.

6. An apparatus according to claim 5, further comprising a control circuit for generating an associating command at a constant time interval, in response to which said neural networks initiate the associating operation.

7. An apparatus according to claim 6, wherein said control circuit produces an associating command in response to said switching signal supplied by said judging circuit.