A computational framework for an accurate, robust, and efficient stereo approach is developed. Most of the deficiencies prevailing in current computational models of stereo can be attributed to their use of a single, ...
详细信息
A computational framework for an accurate, robust, and efficient stereo approach is developed. Most of the deficiencies prevailing in current computational models of stereo can be attributed to their use of a single, typically edge-element-based, primitive for stereo analysis and to their use of a single-level control strategy. The multi-primitive hierarchical (MPH) framework for stereo analysis presented is directed toward overcoming these deficiencies. In the MPH model, stereo analysis is performed in multiple stages, incorporating multiple primitives and utilizing a hierarchical control strategy. The higher levels of the hierarchical system are based on primitives containing more semantic information, and the results of stereo analysis at higher levels are used for guidance at the lower levels. It is shown that such a stereo system is superior to a single-level, single-primitive system.< >
The authors describe a simulation environment which can be of utility in the design, development, and operation of sensor-driven robotic systems. This environment incorporates the ability to simulate sensory inputs an...
详细信息
The authors describe a simulation environment which can be of utility in the design, development, and operation of sensor-driven robotic systems. This environment incorporates the ability to simulate sensory inputs and their effects on the planning and control functions. A detailed design of the simulator is presented. The simulator is integrated within an entire robotic system, and is utilized for automatic robot programming. Alternatively, the simulated system operation flow can be controlled through either a teach mode or a program mode. Five sensing modalities can be simulated: proximity, point laser range, ultrasonic range, laser range depth imagery, and edge-based intensity imagery. The simulation and animation of a particular robot is described. The unique features of the simulator are that it simulates and utilizes sensory information feedback, it integrates planning and simulation, and it makes the switching between real and simulation mode in the robotic system transparent to the user.< >
Intelligent robotic systems should be capable of performing a range of complex tasks in unstructured and dynamic environments. This chapter discusses a number of important items associated with intelligent robots, rol...
详细信息
Intelligent robotic systems should be capable of performing a range of complex tasks in unstructured and dynamic environments. This chapter discusses a number of important items associated with intelligent robots, role of vision sensing in intelligent robotics, and architecture for the design of an intelligent robot. The chapter also describes the computational task hierarchy that governs a model-based robot vision system, and presents a detailed tutorial on two important components of this hierarchy: image segmentation and matching. The main capabilities that intelligent robotic systems should possess include ability for perception of their environment, planning of their actions, and execution of the planned action. The two important components of a model-based vision system are image segmentation and the matching module. A procedure that allows transformation of 2D image coordinates into 3D world coordinates is also discussed in the chapter. The architecture and control aspects of an integrated sensor-based robotic system consist of six modules: supervisor, task planner, perception, motor, user interface, and knowledge-base. Intelligent, sensor-driven systems pose many challenging basic-research problems from a broad range of scientific and technological disciplines; however, there are many important application areas where such systems would be of significant value and utility, including hazardous environments such as nuclear plants, underwater, and space as well as many industrial-automation tasks. Recent advancements in the VLSI, computer-architectures, sensor-and robot-hardware, and artificial-intelligence fields may aid to the development of robust, practical, and cost-effective intelligent robotic systems for a wide variety of applications.
The purpose of this paper is to present the basic ideas of the theory of stochastic complexity with rigorous asymptotic results in the field of time-series analysis and system identification, which demonstrate the app...
详细信息
A description is given of research efforts directed towards the development of an active exploration system performing acquisition, processing, and integration of sensory inputs from vision, point laser range, tactile...
详细信息
A description is given of research efforts directed towards the development of an active exploration system performing acquisition, processing, and integration of sensory inputs from vision, point laser range, tactile, and force/torque sensors. An attempt is made to bring out the rationale that robotic workcell exploration can benefit by utilizing noncontact (e.g., vision, range, and proximity) as well as contact (e.g., tactile and force/torque) sensors while accomplishing tasks such as object identification, object localization, object grasping and object manipulation. The experimental results presented indicate that the rationale utilized in the design of the multisensory robotic active exploration scheme can work successfully.< >
The authors present a systematic comparison of three commonly used least-squares based methods that describes the relationship between noise levels, patch sizes and reliability of surface classification in computer vi...
详细信息
The authors present a systematic comparison of three commonly used least-squares based methods that describes the relationship between noise levels, patch sizes and reliability of surface classification in computervision. The different methods were tested on several sets of synthetic and real data. Complete sets of quadric surfaces were tested. In each case the standard deviation of the Gaussian noise ranged from 0 to 0.05. Four different patch sizes were tested in each case representing data from the entire surface, half surface, quarter surface and from a small patch of the surface. Similar tests were made for two different types of real range data, a sphere and a cylinder. Both synthetic and real data showed improvement in the results obtained by using the M-estimate method in the case of gross outlying points.< >
This paper presents the basic ideas of the theory of stochastic complexity with rigorous asymptotic results in the field of time-series analysis and system identification, which demonstrate the applicability of stocha...
详细信息
This paper presents the basic ideas of the theory of stochastic complexity with rigorous asymptotic results in the field of time-series analysis and system identification, which demonstrate the applicability of stochastic complexity to these difficult statistical problems.< >
The authors ask what is the complexity of computing equilibria for physically realizable analog networks like those of J.J. Hopfield (1984) and T.J. Sejnowski (1981) with arbitrary connectivity. It is shown that, if t...
详细信息
The authors ask what is the complexity of computing equilibria for physically realizable analog networks like those of J.J. Hopfield (1984) and T.J. Sejnowski (1981) with arbitrary connectivity. It is shown that, if the amplifiers are piecewise-linear, then such networks are instances of a game-theoretic model known as polymatrix games. Equilibria for the latter may be computed by vertex pivoting algorithms similar to the simplex method for linear programming, which are in practice of low order polynomial complexity. These algorithms appear to be the only ones both guaranteed to work and which are polynomial in practice. These results suggest that networks with few nonstable equilibria would be computationally attractive.< >
暂无评论