We study neural network strategies for the control of a dynamic, locomotive system using as a model of a one-legged hopping robot. The control task is to make corrections to the motion of the robot that serve to maint...
详细信息
We study neural network strategies for the control of a dynamic, locomotive system using as a model of a one-legged hopping robot. The control task is to make corrections to the motion of the robot that serve to maintain a fixed level of energy (and minimize energy losses), which yields a stable periodic limit cycle in the system's state space corresponding to periodic hopping to a prespecified height. The studied models are Michie and Chambers' BOXES system (1962), the ASE/ACE configuration of Barto and his coworkers (1983), and Anderson/Sutton's two-layered Connectionist model (1986.) Results are demonstrated through numerical simulations, and quantitatively compared to performance obtained by Raibert (1984) for the robotic leg, using full-state feefback. The main difference between Raibert's solution and the `neural' strategies presented here is that our system is not aware of the dynamical model of the plant which it is to control. It has to discover how to control the plant through a long sequence of trial and error experiments.
Results are presented on two neural network strategies for the control of dynamic locomotive systems, in particular a one-legged hopping robot. The control task is to make corrections to the motion of the robot that s...
详细信息
Results are presented on two neural network strategies for the control of dynamic locomotive systems, in particular a one-legged hopping robot. The control task is to make corrections to the motion of the robot that serve to maintain a fixed level of energy (and minimize energy losses), which yields a stable periodic limit cycle in the system's state space. Control of the robot is achieved by the use of artificial neural networks (ANNs) with a continuous learning memory. Through continuous reinforcement for past successes and failures, the control system develops a stable strategy for accomplishing the desired control objectives. The results are presented in the form of computer simulation that demonstrate the ability of two different ANNs to devise proper control signals that will develop a stable hopping strategy, and hence a stable limit cycle in the robot's state space, using imprecise knowledge of both the current state and the mathematical model of the robot leg.< >
This paper proposes two simple schemes for adaptive control of robot manipulator, to achieve trajectory tracking. The state feedback controller consists of feedforward from the reference position trajectory, feedback ...
详细信息
This paper proposes two simple schemes for adaptive control of robot manipulator, to achieve trajectory tracking. The state feedback controller consists of feedforward from the reference position trajectory, feedback from the actual trajectory, and an auxiliary input. The feedforward/feedback controller is different from the state feedback controller in that it consists of feedforward from the reference position, velocity, and acceleration trajectory based on “inverse” dynamics of robot manipulator. The feedforward and feedback gains and the auxiliary input are adapted using adaptive control theory based on Lyapunov's direct method, and using only the local information of the corresponding joint. The proposed control schemes are computationally fast and do not require a priori knowledge of the parameter of the manipulator or the payload. Simulation results are presented in support of the proposed schemes.
The authors investigate the use of a priori knowledge about a scene to coordinate and control bilevel image segmentation, interpretation, and shape inspection of different objects in the scene. The approach is compose...
详细信息
The authors investigate the use of a priori knowledge about a scene to coordinate and control bilevel image segmentation, interpretation, and shape inspection of different objects in the scene. The approach is composed of two main steps. The first step consists of proper segmentation and labeling of individual regions in the image for subsequent ease in interpretation. General as well as scene-specific knowledge is used to improve the segmentation and interpretation processes. Once every region in the image has been identified, the second step proceeds by testing different regions to ensure they meet the design requirements, which are formalized by a set of rules. Morphological techniques are used to extract certain features from the previously processed image for rule verification purposes. As a specific example, results for detecting defects in printed circuit boards are presented.
A new fast transform from curve samples to least-squares normalized B-spline control points is developed and their relation to Fourier descriptors is established. Contour control point sequence scale, translation, and...
详细信息
A new fast transform from curve samples to least-squares normalized B-spline control points is developed and their relation to Fourier descriptors is established. Contour control point sequence scale, translation, and rotation are known to produce identical shape model variations. It is shown that under the conditions of our transform, such sequences are also directly applicable to efficient computation of many useful shape features or characteristics. First, methods for computing boundary curvature and mean contour sample from control points are presented. Then, transforms from contour control points to shape moments and projections are developed and tested.
This paper describes a method for computing Gaussian and mean curvature maps from range data and a modification to this method aimed at facilitating its implementation as a VLSI circuit. The curvature computations con...
详细信息
This paper summarizes the design of a convolution processor card that is very low in cost, easy to use and most importantly, performs a 9 × 9 convolution in less than a second. Its high-performance is attributed ...
详细信息
If an autonomous vehilce is to operate in an environment of arbitrary complexity, it must be able to perceive the locations of the obstacles in its environment and store this information in a world model. It is import...
详细信息
We present a scheme of extracting edge information from parallel spatial frequency bands. From these we create an integrated image of most significant edges of different scales. The frequency bands are realized using ...
详细信息
暂无评论