This paper addresses a number of issues concerning the integration of visual and physical constraints f o r the synthesis and execution of error-tolerant mot ion strategies. Object features and their projections onto the image plane of a supervisory camera are used t o define visual constraint surfaces. These visual constraint surfaces can be directly used t o enforce the following types of con...

We hypothesise that all electroweak symmetry breaking terms such as fermion masses and the W and Z gauge boson masses arise radiatively from just one explicit symmetry breaking term in the Lagrangian. Our hypothesis is motivated by the lack of experimental support and the lack of predictivity of the standard symmetry breaking scenario. We construct a simple model which illustrates our ideas. We...

We present a novel constraint-based motion interpolation algorithm to improve the performance of local planners in sample-based motion planning. Given two free-space configurations of a robot, our algorithm computes a one-dimensional trajectory subject to distance constraints between the closest features of the robot and the obstacles. We derive simple and closed form solutions to compute a pat...

A statistical model is described for the prediction of reaching motions using motion capture data on a variety of individuals performing reaches to a range of targets. The modeling approach allows for various inputs such as the stature, age and the location of the target to be specified and then computes the predicted trajectories of the kinematic chains of body markers necessary to place an ob...

The environment in which animal signals are generated has the potential to affect transmission and reliable detection by receivers. To understand such constraints, it is important to quantify both signals and noise in detail. Investigations of acoustic and color signals now utilize established methods, but quantifying motion-based visual signals and noise remains rudimentary. In this paper, we ...

A new technique is introduced to abstract and edit motion capture data with spatial constraints. Spatial proximities of end-e ectors with tagged objects during zero-crossings in acceleration space are used to isolate signi cant events and abstract constraints from an agent's action. The abstracted data is edited and applied to another agent of a di erent anthropometric size and a similar action...

Robots with many degrees of freedom (e.g., humanoid robots andmobile manipulators) have increasingly been employed to accomplish realistic tasks in domains such as disaster relief, spacecraft logistics, and home caretaking. Finding feasible motions for these robots autonomously is essential for their operation. Sampling-basedmotion planning algorithms have been shown to be effective for these h...

In this paper, we report a robust, efficient, and automatic method for matching infrared tracked markers for human motion analysis in computer-aided physical therapy applications. The challenges of this task stem from non-rigid marker motion, occlusion, and timing requirements. To overcome these difficulties, we use pair-wise distance constraints for marker identification. To meet the timing re...

Traditional methods of motion segmentation use powerful geometric constraints to understand motion, but fail to leverage the semantics of high-level image understanding. Modern CNN methods of motion analysis, on the other hand, excel at identifying well-known structures, but may not precisely characterize well-known geometric constraints. In this work, we build a new statistical model of rigid ...