Vehicle crash predictive and evasive operation system by neural networks

• US 5,541,590 A
• Filed: 01/19/1995
• Issued: 07/30/1996
• Est. Priority Date: 08/04/1992
• Status: Expired due to Fees

• Current Assignee: Takata Corporation (Ningbo Junsheng Investment Group Co., Ltd.)
• Original Assignee: Takata Corporation (Ningbo Junsheng Investment Group Co., Ltd.)
• Inventors: Nishio, Tomoyuki
• Primary Examiner(s): SWARTHOUT, BRENT
• Application Number:
  US08/375,249
• Time in Patent Office: 558 Days
• Field of Search: 340/435, 340/995, 340/903, 340/905, 348/170, 348/113, 348/148, 348/149, 364/424.01, 364/424.04, 364/424.05, 395/905.22, 395/11, 395/21, 395/23, 382/104, 382/157
• US Class Current: 340/903
• CPC Class Codes: B60K 28/14 responsive to accident or emergency, e.g. deceleration, tilt of vehicle
• CPC Class Codes: B60R 16/0231 Circuits relating to the driving or the functioning of the vehicle monitoring tyres B60C23/00; indicating overspeed B60K31/00; for dash boards B60K37/00, B60Q3/10; for indicating emergencies B60Q1/52; brake control systems B60T; registering or indicating the working of vehicles G07C5/00; measuring distance G01C, e.g. combinations of speed and distance G01C23/00; engine indicators G01L; measuring speed or acceleration G01P
• CPC Class Codes: B60T 7/22 initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle , or by means of contactless obstacle detectors mounted on the vehicle
• CPC Class Codes: B60W 10/04 including control of propulsion units
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/20 including control of steering systems
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: B60W 2710/0605 Throttle position
• CPC Class Codes: B60W 2710/18 Braking system
• CPC Class Codes: B60W 2710/20 Steering systems
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B62D 15/0265 Automatic obstacle avoidance by steering
• CPC Class Codes: B62D 6/00 Arrangements for automatically controlling steering depending on driving conditions sensed and responded to, e.g. control circuits means for initiating a change in direction B62D1/00; steering valves B62D5/06; combined with means for inclining the vehicle body or wheels on bends B62D9/00
• CPC Class Codes: Y10S 706/905 Vehicle or aerospace

Abstract

A system for predicting and evading crash of a vehicle includes an image pick-up device mounted on the vehicle for picking up images of actual ever-changing views when the vehicle is on running to produce actual image data, a crash predicting device associated with said image pick-up device, said crash predicting device being successively supplied with the actual image data for predicting occurrence of crash between the vehicle and potentially dangerous objects on the roadway to produce an operational signal when there is possibility of crash and a safety drive ensuring device connected to said crash predicting device for actuating, in response to the operational signal, an occupant protecting mechanism which is operatively connected thereto and equipped in the vehicle. The crash predicting device includes a neural network which is previously trained with training data to predict the possibility of crash, the training data representing ever-changing views previously picked-up from said image picking-up device during driving of the vehicle for causing actual crash.

Claims

1. A system for predicting and evading crash of a vehicle comprising:

image pick-up means mounted on the vehicle for picking up images of actual views in a direction of running of the vehicle while running of the vehicle,

crash predicting means having a neural network, said neural network containing previously taken image data formed of successive scenes for causing accidents and being trained by a back propagation method for recognizing conditions in image data which cause said accidents, said neural network having an input layer formed of processing elements arranged parallel to each other, said input layer continuously receiving actual image data obtained from the image pick-up means, said neural network receiving the actual image data obtained from the image pick-up means while running of the vehicle, evaluating the actual image data by comparing it to said previously taken image data for causing the accidents, judging if the vehicle is predicted to crash based on the comparison of said previously taken image data with an object noticed in the actual image data of the image pick-up means, and outputting an operational signal in case of prediction of occurrence of a crash with said object, and

safety drive ensuring means connected to said crash predicting means, said safety drive ensuring means, in response to the operational signal, operating to evade the crash between the vehicle and the object for protecting an occupant of the vehicle.

2. A system as claimed in claim 1, wherein said neural network further includes an output layer formed of a single processing element and connected to the processing elements of the input layer in series, said input layer instantaneously receiving said actual image data from the image pick-up means, and said output layer outputting a binary signal for indicating if said crash is predicted to occur in response to the actual image data inputted to the input layer.

3. A system as claimed in claim 2, wherein in a training of the neural network by the back propagation method, said input layer receives the previously taken image data formed of successive scenes for causing the accidents and receives said binary signal from said output layer indicating that the accidents occurred in said successive scenes, said neural network, during the driving of the vehicle after the training, evaluating said actual image data obtained from the image pick-up means to determine if it corresponds to said previously taken image data for causing accidents.

4. A system as claimed in claim 3, wherein said neural network containing trained data is memorized in a ROM for constituting the crash predicting means, said ROM being included in a circuit for the safety drive ensuring means.