Abstract:
An arming signal for enabling deployment of rollover safety devices (28) by a vehicle rollover detection apparatus (20, 26) is based on an off-axis measure of vehicle acceleration. A low-g accelerometer (22) mounted perpendicular to the longitudinal axis of the vehicle (10) but at an angle with respect to Earth's ground plane detects components of both lateral and vertical vehicle accelerations. The measurement angle is selected to apportion the lateral vs. vertical measurement sensitivity in accordance with calibrated lateral and vertical acceleration thresholds, and an arming signal is generated when a filtered version of the measured acceleration exceeds an arming threshold (40, 42, 44, 48).
Abstract:
An elastomeric seat bladder (30) for a vehicle occupant weight estimation system (10) includes a plurality of elastomeric tethers (38) defined by bands or sheets of elastomeric material coupling upper and lower layers (30a, 30b) of the bladder within a peripheral weld (36) in order to reduce fluid pooling and distention or bulging of the bladder (30) due to localized loading. The elastomeric tethers (38) are spot or seam welded to upper and lower sheets (30a, 30b) of the bladder (30); they extend to limit distension where required, and otherwise partially or fully collapse to minimize vertical shunting of occupant weight through the bladder (30).
Abstract:
A vehicle rollover detection apparatus and method are provided for detecting an overturn condition of the vehicle. The rollover detection apparatus includes an angular rate sensor (12) sensing angular rate of the vehicle, and a vertical accelcrometer (14) for sensing vertical acceleration of the vehicle. A controller (20) processes the sensed angular rate signal and integrates it to produce an attitude angle. The vertical acceleration signal is processed to determine an inclination angle of the vehicle. The rollover detection apparatus adjusts the attitude angle as a function of the inclination angle and compares the adjusted attitude angle and the processed angular rate signal to a threshold level to provide a vehicle overturn condition output signal. Additionally, the rollover detection apparatus detects a near-rollover event and adjusts the variable threshold in response thereto to prevent deployment of a vehicle overturn condition, thus providing immunity to such events.
Abstract:
An iterative process involving both genetic programming (18) and adaptive boosting (22, 24) is used to develop a classification algorithm (24) using a series of training examples. A genetic programming process (18) is embedded within an adaptive boosting loop (22, 24) to develop a strong classifier (24) based on combination of genetically produced classifiers.
Abstract:
An object recognition method analyzes an imaged object based on its contour. Extracted contours are characterized by wavelets and slope sequence, and compared to sets of stored contours to recognize a known feature. If a match of sufficiently high confidence is not found, the image is distorted to simulate an incrementally different perspective of the imaged object, and the process of contour identification, characterization and comparison is repeated until a match of sufficiently high confidence is found. The cycle of image distortions allow two-dimensional images obtained from a monocular vision system to be analyzed for three-dimensional motion for optimal recognition performance.
Abstract:
Impending rollover events are detected based on vehicle roll rate, roll angle and lateral acceleration, and an assessment of the relative polarities of vehicle roll rate and lateral acceleration. When the vehicle roll rate and lateral acceleration are opposite in polarity, the roll rate vs. roll angle thresholds used to distinguish between rollover events and non-rollover events are more sensitive than for conditions for which the vehicle roll rate and lateral acceleration are of the same polarity (64, 66, 68). Additionally, the roll rate vs. roll angle thresholds are adaptively modified based on roll angle and lateral acceleration to provide increased detection sensitivity under conditions that typically precede a rollover event (80), and reduced detection sensitivity under conditions for which a rollover event is unlikely (86).
Abstract:
A reconfigurable rollover event detection methodology utilizes an existing body of vehicle sensor data. A number of different algorithms (36, 38, 40, 42, 44) or look-up modules develop rollover detection outputs based on different sets of sensor data, and a meta-algorithm (90) combines the various rollover detection outputs to form a single rollover detection output (93). The number of individual rollover detection outputs is configurable depending on the extent of the available sensor data in a given vehicle and changes in sensor availability that occur due to sensor and communication failures.
Abstract:
An event discrimination methodology executes multiple versions of the same or different event discrimination algorithms (36-42) and logically or arithmetically combines their outputs to distinguish between specified events and non-events (46). One given algorithm is repeatedly executed with different sets of calibration data, or alternately, a number of different algorithms are executed. In cases where the algorithm results are arithmetically combined (60), the weights accorded to each algorithm result are dynamically adjusted based on driver input or vehicle dynamic behavior data to accord highest weight to the algorithm(s) calibrated to identify events associated with the detected driver input or vehicle dynamic behavior (68, 70).
Abstract:
A rollover detection apparatus (20) and method (60) are provided for anticipating a potential vehicle rollover event. The apparatus (20) includes an input (30 or 32) for receiving a plurality of input signals including sensed parameters of the vehicle. A first memory buffer (46) stores data representative of one or more predetermined driving scenarios that represent possible rollover scenarios. A second memory buffer (48) stores data representative of a history of recent conditions of the vehicle based on the plurality of sensed vehicle parameters. The apparatus (20) further includes a processor (22) for comparing the data representative of a history of recent driving events to the data representative of one or more predetermined driving scenarios. The processor (22) further determines a possible rollover event of the vehicle based on the comparison and generates an output signal (36) indicative thereof.