https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

An imaging system for a vehicle includes an imaging device having a field of view exteriorly and forward of the vehicle in its direction of travel, and an image processor operable to process the captured images in accordance with an algorithm. The algorithm comprises a sign recognition routine and a character recognition routine. The image processor processes the image data captured by the imaging device to detect signs in the field of view of the imaging device and applies the sign recognition routine to determine a sign type of the detected sign. The image processor is operable to apply the character recognition routine to the image data to determine information on the detected sign. The image processor applies the character recognition routine to the captured images in response to an output of the sign recognition routine being indicative of the detected sign being a sign type of interest.

Imaging system for vehicle

GPS satellite (4) ranging signals (6) received (32) on comm1, and DGPS auxiliary range correction signals and pseudolite carrier phase ambiguity resolution signals (8) from a fixed known earth base station (10) received (34) on comm2, at one of a plurality of vehicles/aircraft/automobiles (2) are computer processed (36) to continuously determine the one's kinematic tracking position on a pathway (14) with centimeter accuracy. That GPS-based position is communicated with selected other status information to each other one of the plurality of vehicles (2), to the one station (10), and/or to one of a plurality of control centers (16), and the one vehicle receives therefrom each of the others' status information and kinematic tracking position. Objects (22) are detected from all directions (300) by multiple supplemental mechanisms, e.g., video (54), radar/lidar (56), laser and optical scanners. Data and information are computer processed and analyzed (50,52,200,452) in neural networks (132, FIGS. 6-8) in the one vehicle to identify, rank, and evaluate collision hazards/objects, an expert operating response to which is determined in a fuzzy logic associative memory (484) which generates control signals which actuate a plurality of control systems of the one vehicle in a coordinated manner to maneuver it laterally and longitudinally to avoid each collision hazard, or, for motor vehicles, when a collision is unavoidable, to minimize injury or damage therefrom. The operator is warned by a heads up display and other modes and may override. An automotive auto-pilot mode is provided.

GPS vehicle collision avoidance warning and control system and method

Survey of advanced suspension developments and related optimal control applications

A forward-facing vision system for a vehicle includes a forward-facing camera disposed in a windshield electronics module attached at a windshield of the vehicle and viewing through the windshield. A control includes a processor that, responsive to processing of captured image data, detects taillights of leading vehicles during nighttime conditions and, responsive to processing of captured image data, detects lane markers on a road being traveled by the vehicle. The control, responsive to lane marker detection and a determination that the vehicle is drifting out of a traffic lane, may control a steering system of the vehicle to mitigate such drifting, with the steering system manually controllable by a driver of the vehicle irrespective of control by the control. The processor, based at least in part on detection of lane markers via processing of captured image data, determines curvature of the road being traveled by the vehicle.

Vision system for vehicle

A standardized microcontroller-based fuzzy logic processing module (101) for generating control signal values in response to variable input signal values in accordance with constraints imposed by propositions or "rules" stored in memory (117) in a standardized format. Each rule consists of one or more input conditions and an output directive. Each input signal (110) and the output signal (112) values are characterisable by their degree of membership in a predetermined number of fuzzy sets, each fuzzy set being defined by a membership function (119). Each input condition is composed of a reference to a particular input variable, which has been preprocessed into integer (whole number) normalised form and a reference to a membership function. Each output directive includes a reference to a further membership function. Each membership function is implemented by one of a three possible forms of standard membership data structures: a triangular function represented by three data points, a table lookup function represented by a two end data points and the points between these two end points, and an standard shape function composed of a set of data points and a set of reference points used to form a similar shape function by interpolation. Fuzzy logic processing is accomplished by determining the extent to which the input conditions are satisfied by the current values of the input signals in order to develop a rule strength value, and then performing a "centre-of-gravity" determination based on the output membership function values (118) of each satisfied rule integrated over the range of possible output signal values.

Electronic control system

We present a framework for the training of time-lagged recurrent networks that has been used for a wide variety of both abstract problems and practical applications Our method is based on rigorous computation of dynamic derivatives, using various forms of backpropagation through time (BPTT), a second-order weight update scheme that uses the extended Kaiman filter, and data delivery mechanics designed for sequential weight updates with broad coverage of the available data We extend our previous discussions of this framework by discussing various alternative forms of BPTT In addition, we consider explicitly the issue of dealing with and optimizing network initial states We discuss the initial state problem from the standpoint of making time-series predictions

Enhanced Multi-Stream Kalman Filter Training for Recurrent Networks

Describes the preliminary research on and implementation of a fuzzy logic controller to control wheel slip for an antilock brake system. The dynamics of braking systems are highly nonlinear and time-variant. Simulation was used to derive an initial rule base, which was then tested on an experimental brake system. The rules were further refined by analysis of the data acquired from vehicle braking maneuvers on a surface with a high coefficient of friction. The robustness of the fuzzy logic slip regulator was further tested by varying operating conditions and external environmental variables. >

Fuzzy logic anti-lock brake system for a limited range coefficient of friction surface

The authors have previously described neural-network-based methods for modeling automotive systems and training near-optimal controllers. These methods are based on the premise that the physical system can be sufficiently instrumented during network training so that accurate evaluation of the effect of control actions is possible. In certain systems, such a automotive anti-lock braking (ABS), it may be costly to obtain the detailed data that would be required to exploit the full capabilities of neural methods. The present paper reports an initial simulation-based study to determine the performance potential of controllers designed with these methods. Such studies will help determine whether the cost of carrying out neural training methods on actual systems is justified. >

http://ieeexplore.ieee.org/iel2/673/6442/00252253.pdf

Neural network modeling and control of an anti-lock brake system

The use of dynamic gradient-based training of neural controllers for automotive systems is illustrated The authors use a recurrent structure that embeds an identification network and a neural controller and that properly treats both short- and long-term effects of controller weight changes This results in an approximately optimal control strategy Feedforward and hybrid feedforward-feedback neural controllers trained by dynamic backpropagation and a dynamic decoupled extended Kalman filter (DDEKF) are investigated A quarter-car active suspension model is considered in both linear and nonlinear forms, and representative results are presented Methods using higher-order information, eg, DDEKF are very effective in comparison to methods based exclusively upon gradient descent, eg, dynamic backpropagation (DBP) The use of a recurrent structure for obtaining derivatives for controller training is illustrated >

Fumin Yuan

Papers

Electronic control system

Enhanced Multi-Stream Kalman Filter Training for Recurrent Networks

Fuzzy logic anti-lock brake system for a limited range coefficient of friction surface

Neural network modeling and control of an anti-lock brake system

Neural control systems trained by dynamic gradient methods for automotive applications