One factor that limits the range of tasks that robots can perform robustly is the scarcity of useful sensors available to provide feedback to the robot control system. While much progress has been made with vision sen...
详细信息
One factor that limits the range of tasks that robots can perform robustly is the scarcity of useful sensors available to provide feedback to the robot control system. While much progress has been made with vision sensors and force/torque sensors, tactile sensing systems have fallen behind, and so general-purpose tactile sensing systems are not commercially available. The aim of this work is therefore to produce a tactile sensing system that could be manufactured inexpensively, could be used on a wide variety of robotic systems, and would provide the kind of output typically required in dexterous manipulation applications. Such a tactile sensing system will be presented in this paper. The tactile transducers used in this system are based on semiconductive ink technology that allows transducers of any size, shape, and resistance range to be produced merely by altering the ink printing process and substrate geometry. Each sensor outputs three pieces of information that are useful in robotic manipulation-two parameters indicating the location of a contact point on the transducer and one parameter specifying the amount of force being exerted at the contact point. So that the sensing system could support transducers of different shapes and sizes, the analog interface circuitry of this system has been designed to be fully programmable, and also includes circuitry to enable self-calibration with appropriate software.< >
This paper presents an algorithm for finding a kinematically feasible path which satisfies a given set of nonholonomic constraints while enforcing both equality and inequality constraints on the configuration vector. ...
详细信息
This paper presents an algorithm for finding a kinematically feasible path which satisfies a given set of nonholonomic constraints while enforcing both equality and inequality constraints on the configuration vector. The path planning problem is transformed from a finite time nonlinear control problem into a static root finding problem which is iteratively solved. By using an exterior penalty function method, the constrained root finding problem is converted to an unconstrained problem. Convergence of the algorithm depends upon a certain gradient operator being full rank. It has recently been shown that, in the absence of any configuration inequality constraints, the full rank condition is generic. In this paper, we show the full rank condition for a special inequality constraint case. An experiment in which the algorithm is applied to an actual double tractor-trailer vehicle is presented.< >
A general approach to model-based multisensor data fusion using a minimal representation size criterion is described. Each sensor is modeled by a general constraint equation which defines a data constraint manifold (D...
详细信息
A general approach to model-based multisensor data fusion using a minimal representation size criterion is described. Each sensor is modeled by a general constraint equation which defines a data constraint manifold (DCM), and observed sensor data populate the measurement space according to these constraints. The choice of multisensor interpretations is based on a minimal representation size criterion which evaluates the complexity through correspondence and encoded errors weighted by relative sensor accuracy and precision. This general framework automatically selects subsets of data features called constraining data feature sets (CDFS) and chooses the CDFS corresponding to a minimal representation interpretation of the observed data. The resulting procedure fuses heterogeneous sensor readings into a single estimation method. The method is illustrated for a visual and tactile data fusion example. The approach generalizes to problems with non-geometric models, and can be used for multisensor system identification in other domains such as process control.< >
There are numerous applications in which robots are needed to assist rather than replace human operators. These applications typically involve either work in a dangerous environment or performing tasks that are physic...
详细信息
There are numerous applications in which robots are needed to assist rather than replace human operators. These applications typically involve either work in a dangerous environment or performing tasks that are physically impossible for humans to accomplish by themselves. Robots used in this mode do not need to be autonomous because they can essentially be controlled by the operator. Nonetheless, it is difficult for an operator to flawlessly control a robot with a large number of degrees of freedom. Therefore, an intelligent control system is needed to correct and improve the operator's input to the robot. In this paper the authors discuss a central component in this control system known as the variably-autonomous trajectory generator (VATG). The VATG combines input from the operator with input from one or more autonomous control modules (CM) to generate the robot trajectory. The amount of impact the autonomous CMs will have on the overall trajectory will depend on a number of factors such as the task being performed and the sensing modalities available, hence the authors refer to this type of control as being variably-autonomous.< >
This paper presents one kind of modified backpropagation algorithm for training the multilayer feedforward neural networks with hard-limiting neurons. Adaptive steepness factors in the analog sigmoidal neuron activati...
详细信息
This paper presents one kind of modified backpropagation algorithm for training the multilayer feedforward neural networks with hard-limiting neurons. Adaptive steepness factors in the analog sigmoidal neuron activation functions are updated in the training process. With the decrease of the sum-square error, these steepness factors are varied from a small positive value to infinite. It makes the sigmoidal neuron transferred to hard-limiting one after the training process complete. Thus, a multilayer feedforward neural network can be trained with the resultant architecture is only composed of hard-limiting neurons. The learning algorithm is similar to the conventional backpropagation algorithm, only the derivatives of the hidden neural activation functions are modified according to the proposed idea. Extensive numerical simulations are presented to show the feasibility of the proposed algorithm. In addition, the numerical properties of the proposed algorithm are also discussed in detail. Comparisons of the proposed algorithm with algorithms are given, and some useful conclusions are drawn.< >
This paper introduces a new structure to compute the digit-reversal permutation in the radix-B fast Fourier or Hartley transform. By studying the property of base-B numbers, we find that any base-B number, k, can be r...
详细信息
This paper introduces a new structure to compute the digit-reversal permutation in the radix-B fast Fourier or Hartley transform. By studying the property of base-B numbers, we find that any base-B number, k, can be represented as the sum of three numbers: one base-B number, i;digital reverse of another base-B number, j;and a constant, z, in which the two base-B numbers i and j are no greater than square-root N, where N is the number of data points to be transformed. Then, the digital reverse of k is just the sum of j and the digital reverse of i plus the constant z. Using this property we have developed a new algorithm to compute the digital reverse of any index very efficiently. Since it uses fewer arithmetic operations, the new algorithm is faster than other algorithms known to the authors and the program storage requirements are no greater than Evans' and Walker's algorithms.
Nonholonomic vehicles are shown to be kinematically equivalent to unicycles. A dynamic model for mobile vehicles moving on planar surfaces under nonholonomic constraints is derived. The model is decomposed into a kine...
详细信息
Nonholonomic vehicles are shown to be kinematically equivalent to unicycles. A dynamic model for mobile vehicles moving on planar surfaces under nonholonomic constraints is derived. The model is decomposed into a kinematic and a dynamic subsystem. The kinematic subsystem is shown to be globally stabilizable by using continuous control laws on reference trajectories that are nonstationary and continuously differentiable with respect to time. The continuity of the kinematic control inputs allows the extension of the vehicle control at the dynamic level. Stability of the overall closed loop system is examined using singular perturbation theory. Simulations verify all theoretical derivations.
General-purpose CAD-based inspection of a manufactured workpiece often involves comparing a part model created using intensity or range images of the part to a toleranced reference model of the part. Before this compa...
详细信息
General-purpose CAD-based inspection of a manufactured workpiece often involves comparing a part model created using intensity or range images of the part to a toleranced reference model of the part. Before this comparison can be made, however, the sensed object model must be registered to the reference object model. Most registration approaches assume that it is possible to identify and match features in the models and that the object models represent very similar geometries. A registration approach that deals with featureless dissimilar models is presented, and experimental results are demonstrated. Although the need for such an approach was motivated by needs in inspection, the approach is very general and can be used in a variety of other applications.< >
A class of Newton-type algorithms is effective in solving the kinematic path planning problem for a system with nonholonomic equality constraints. A key result in this approach has been the generic full rank condition...
详细信息
A class of Newton-type algorithms is effective in solving the kinematic path planning problem for a system with nonholonomic equality constraints. A key result in this approach has been the generic full rank condition of a certain gradient operator. We have extended this method to path planning problems with inequality constraints and shown its efficacy in solving some challenging problems, but a similar genericity result is not currently available. In this paper, we present some extension of our algorithm for nonholonomic path planning with equality and inequality constraints and show the generic full rank condition for a special case. Simulation examples involving a steerable tractor-trailer vehicle and experiment results of a quarter-scale car with a trailer are presented.< >
A robust polynomial-time algorithm for model-based pose estimation from tactile grasp data is presented. A minimal representation criterion is used to formulate the matching problem as a global optimization. The hypot...
详细信息
A robust polynomial-time algorithm for model-based pose estimation from tactile grasp data is presented. A minimal representation criterion is used to formulate the matching problem as a global optimization. The hypothesize-and-test paradigm is invoked to search for the optimal solution. A three-on-three match of model features to data features is used to reduce the transform search space to polynomial size. A polynomial-time assignment algorithm is used to compute the optimal correspondence for each hypothesized pose. The strength of the algorithm lies in its ability to perform with noisy or incomplete data and with missing or spurious features. It is capable of rejecting outliers and finding partial matches, and it produces sensible results even in the presence of large noise. The algorithm has been implemented and tested on actual data.< >
暂无评论