This paper presents a novel approach of using stereovision or pseudo-stereovision to generate touch screen experience. A pair of digital cameras or a set of a digital camera and a mirror is mounted at the corners of a computer display. Algorithms are presented to generate the positions of the pointers when they are close to the screen. The paper also proposes to use positions, velocities and accelerations of a pointer to generate virtual forces in the active space of the touch screen. The user interface will be friendlier by applying the rich information obtained from the input methods presented in this paper.

This paper presents a novel framework for image-based motion planning, which we term Visual Motion Planning. The method skips the step of transferring image features back to robot pose, and hence makes motion plans directly in the image plane. Analogous to visual servo control, the visual motion planning concept takes advantage of the image features to achieve a direct and fast motion planning solution. It provides a "virtual" trajectory in the image plane for the robot to track with standard visual servoing techniques. In this paper, we show the result of applying the idea to simulated 2-D and 3-D mobile robot systems. Within this motion planning paradigm, we also discuss the mechanisms for taking advantage of surplus features and incorporating image-based constraints, such as requiring that the images remain in the field of view. Experimental results using a Pioneer AT ground mobile robot are presented, showing excellent agreement with theory.

We present a control algorithm to control underactuated mechanical systems that evolve in the configuration space with the fiber bundle structure. We show that by using the geometric tools such as symmetric product and small amplitude periodic forcing, we can develop unique techniques to control the underactuated dynamic system, such as an unmanned blimp.

This paper presents a novel approach to image-based visual servoing by making motion plans directly in the image plane. By skipping the step of transferring image features back to robot pose, we are able to utilize the image features for a direct and fast motion planning solution. Standard visual servoing techniques can then be applied to tract the given trajectory. In this paper, we have applied the idea to 2D and 3D (kinematic) motion planning and discussed the mechanisms for taking advantage of surplus features and incorporating other image-based constraints, such as that the targets always remain in the field of view.

Image-based control of free-flying mechanical systems is addressed, with application to an indoor vision-guided blimp. A methodology is developed for incorporating the physical parameters of a mechanical system into the image plane for performing visual servoing. It is noted that under suitable conditions, namely the existence of a diffeomorphism between image features and robot pose, many tools from mechanical system control theory can be used directly when applied in the image plane. It is shown that when a suitable Jacobian map exists between pose and features, dynamics for vision-based control of aerial and underwater vehicles can easily be formulated. Experimental results show initial success at spatial tracking of simple objects.

We present a general framework for motion planning of robots in the presence of obstacles and other robots. We use variational calculus and optimization to find optimal open loop and closed loop plans in the presence of uncertainty. The plans are based on world models with set-valued uncertainty associated with the positions and shape of the obstacles. The open loop plans are generated by an efficient method that allows successive refinements of a nominal motion plan and accommodates finer levels of granularity as additional information becomes available. The closed loop plans are control policies that are based on given sensor models. The optimal plan is a control policy that performs the best in the worst-case situation. We discuss how the open loop and closed loop plans can be viewed as optimal strategies in the framework of two-person, zero-sum, non-cooperative games.