Reconfigurable and morphing structures have attracted attention for potentially providing a range of new functionalities including system optimization over broad operational conditions and multi-mission capability. One promising approach for creating large deformation morphing structures uses variable stiffness components to provide large deformation without large energy input to the system. In this paper, we present an automated approach to design shape morphing strategies for reconfigurable surfaces composed of variable stiffness components. Variable stiffness components create an ill-posed control problem and generally have multiple solutions for any given morphing task. We formulate this problem as an optimization search using genetic algorithms (GA) to efficiently search the design space and rapidly arrive at a family of plausible solutions. Our novel approach can simultaneously satisfy a broad range of design constraints including structural properties, mechanical loading, boundary conditions and shape. Critical to GA searching is an accurate and computationally efficient variable stiffness surface model. Computer simulation of the reconfigurable surface was performed using a physics based model of the variable stiffness surface. The surface is modeled as a thin elastic plate in which the stretching and bending elastic moduli are treated separately and as arbitrary functions defined over the surface. This allows for large deformations including complete foldings. The resulting non-linear difference equations are solved using various preconditioned global search based relaxation algorithms. The results of our simulations show that our approach not only allows us to verify the feasibility of morphing tasks of variable stiffness surfaces, but also enables us to efficiently explore much larger design spaces resulting in unique and non-obvious morphing strategies.
Good pedestrian classifiers that analyze static images for presence of pedestrians are in existence. However, even a low false positive error rating is sufficient to flood a real system with false warnings. We address the problem of pedestrian motion (gait) modeling and recognition using sequences of images rather than static individual frames, thereby exploiting information in the dynamics. We use two different representations and corresponding distances for gait sequences. In the first a gait is represented as a manifold in a lower dimensional space corresponding to gait images. In the second a gait image sequence is represented as the output of a dynamical system whose underlying driving process is an action like walking or running. We examine distance functions corresponding to these representations. For dynamical systems we formulate distances derived based on parameters of the system taking into account both the structure of the output space and the dynamics within it. Given appearance based models we present results demonstrating the discriminative power of the proposed distances
Active vision refers to a purposeful change in the camera setup to aid the processing of visual information. An important issue in using active vision is the need to represent the 3D environment in a manner that is invariant to changing camera configurations. Conventional methods require precise knowledge of various camera parameters in order to build this representation. However, these parameters are prone to calibration errors. This motivates us to explore a neural network based approach using Vector Associative Map to learn the invariant representation of 3D point targets for active vision. An efficient learning scheme is developed that is suitable for robotic implementation. The representation thus learned is also independent of the intrinsic parameters of the imaging system, making it immune to systematic calibration errors. To evaluate the effectiveness of this scheme, computer simulations were first performed using a detailed model of the University of Illinois Active Vision System (UIAVS). This is followed by an experimental verification on the actual UIAVS. Several robotic applications are then explored that utilize the invariance property of the learned representation. These applications include motion detection, active vision based robot control, robot motion planning, and saccade sequence planning.