In this paper we present the results of biological observation on jumping insects, and how to relate them to legged robots. In particular, by observing jumping Leafhoppers with a high speed camera, we found out how th...
详细信息
ISBN:
(纸本)9783642001956
In this paper we present the results of biological observation on jumping insects, and how to relate them to legged robots. In particular, by observing jumping Leafhoppers with a high speed camera, we found out how the legs' configuration during take-off let the insect map muscle-like force into constant force, which represents all optimal design for jumping. We then implemented the same design in a 20 grams jumping prototype, verifying the optimality of such bio-inspired solution for locomotion of a small robot.
In this paper a method is proposed for shape recognition and grasping of unknown objects using a robotic hand with two soft fingers and one omnidirectional camera. For shape recognition, we propose to use a simple 2D ...
详细信息
ISBN:
(纸本)9783642001956
In this paper a method is proposed for shape recognition and grasping of unknown objects using a robotic hand with two soft fingers and one omnidirectional camera. For shape recognition, we propose to use a simple 2D version of the visual volume intersection method to obtain the visual bull of the object in a, horizontal plane from multiple images taken from different positions around the object. For grasping we propose a simple grasp quality criterion to obtain the best grasping position for the two soft fingers based on the obtained visual hull. We conducted several experiments to show the validity of the proposed method.
This paper presents a methodology for the control of robots, in position and force, using electromyographic (EMG) signals recorded from muscles of the shoulder and elbow. A switching model is used for decoding muscula...
详细信息
ISBN:
(纸本)9783642001956
This paper presents a methodology for the control of robots, in position and force, using electromyographic (EMG) signals recorded from muscles of the shoulder and elbow. A switching model is used for decoding muscular activity to both, joint angles and force exerted from the human upper limb to the environment. The proposed method is able to estimate those variables in cases where no force is exerted to the environment (unconstrained motion), as well as in cases where motion is accompanied with force exertion (constrained motion). The switching model is trained to each subject, a procedure that take's only a few minutes, using a torque-controlled robot arm coupled with the human arm. After training, the system can decode position and force using only EMG signals recorded from 7 muscles. The system is tested in a, orthosis-like scenario, in planar movements, through various experiments covering the cases aforementioned. The experimental results prove the system efficiency, making the proposed methodology a strong candidate for an EMG-based controller for robotic exoskeletons.
Robotic control of flexible devices can enhance and simplify many medical procedures. We present a method for controlling the distal tip motion of a tendon driven cardiac catheter. The catheter's shape is specifie...
详细信息
ISBN:
(纸本)9783642001956
Robotic control of flexible devices can enhance and simplify many medical procedures. We present a method for controlling the distal tip motion of a tendon driven cardiac catheter. The catheter's shape is specified by a mechanics model which includes coupling of multiple. sections. Shape is then transformed to end-effector location rising a D-H kinematics model. The combined models are then inverted to translate desired tip motion to tendon displacement. The inversion optimizes positive tendon tension for n-arbitrarily located tendons. To validate the method, we present a bench-top experiment of a cardiac catheter emulating a circular ablation as a 6-DOF task. To reduce error, we present the first known experiments of sensor feedback control on the tip position of a continuum manipulator. The resulting system performs with sub-millimeter accuracy.
The terrain classification is a very important subject to the all-terrain robotics community. The knowledge of the type of terrain allows a rover to deal with its environment;more efficiently, The work presented in th...
详细信息
ISBN:
(纸本)9783642001956
The terrain classification is a very important subject to the all-terrain robotics community. The knowledge of the type of terrain allows a rover to deal with its environment;more efficiently, The work presented in this paper shows that it;is possible to differentiate terrains based on their aspects, using exteroceptive sensors, as well as based on their influence on the rover's behavior, using proprioceptive sensors. Using a boosting method (AdaBoost), these two sets of classifiers are trained and applied independently. The resulting dual algorithm identifies offline the nature of the terrain on which the vehicle is virtually driving and classifies it according to categories previously labeled, such as sand or grass. Due to the good results obtained for the classification based solely on each type of sensor, this paper concludes that the correlation between data from proprioceptive and exteroceptive sensors could be used for further applications. This paper is a, summarized version of the one presented at the ISER conference.
We present an application of the ensemble learning algorithm in the area, of visual tracking and servoing. In particular;we investigate an approach based on the Boosting technique for robust visual tracking of color o...
详细信息
ISBN:
(纸本)9783642001956
We present an application of the ensemble learning algorithm in the area, of visual tracking and servoing. In particular;we investigate an approach based on the Boosting technique for robust visual tracking of color objects in ail underwater environment. To this end, we rise AdaBoost, the most common variant of the Boosting algorithm, to select a number of low-complexity but moderately accurate color feature trackers and we combine their outputs. From a significantly large number of "weak" color trackers, the training process selects those which exhibit reasonably good performance (in terms of mistracking and false positives), and assigns positive weights to these trackers. The tracking process applies these trackers on the input video frames, and the final tracker output is chosen based on the weights of the final array of trackers. By using computationally inexpensive but somewhat accurate trackers as members of the ensemble, the system is able to run at quasi-real time, and thus, is deployable on-board our underwater robot. We present quantitative cross-validation results of our visual tracker, and conclude by pointing out some difficulties faced and subsequent shortcomings in the experiments we performed, along with directions of future research on the area of ensemble tracking in real-time.
We consider the problem of online planning for a mobile robot among obstacles, where it is impractical to test, all possible future paths. One approach is for the runtime task to test some subset of the possible paths...
详细信息
ISBN:
(纸本)9783642001956
We consider the problem of online planning for a mobile robot among obstacles, where it is impractical to test, all possible future paths. One approach is for the runtime task to test some subset of the possible paths and select, a path that does not collide with obstacles while advancing the robot toward it's goal. Performance depends on the choice of path set. In this paper we assume the path set is fixed and chosen offline. By randomly sampling the space of path sets we discover effective path sets-comparable or superior to the best previously suggested approaches. In addition, testing large numbers of randomly generated path sets yields some insights on the relation of robot performance to the choice of path set.
The inherent uncertainty associated with unstructured grasping tasks makes establishing a successful grasp difficult. Traditional approaches to this problem involve hands that are complex, fragile, require elaborate s...
详细信息
ISBN:
(纸本)9783642001956
The inherent uncertainty associated with unstructured grasping tasks makes establishing a successful grasp difficult. Traditional approaches to this problem involve hands that are complex, fragile, require elaborate sensor suites, and are difficult to control. Alternatively, by carefully designing the mechanical structure of the hand to appropriately incorporate features such as compliance and adaptability, the uncertainty inherent in unstructured grasping tasks can be more easily accommodated. These features can reduce the need for complicated sensing and control by passively adapting to the object properties and positioning, making the hand easier to operate and with greater reliability. In this paper, we demonstrate a novel adaptive and compliant grasper that is both simple and robust. The four-fingered hand is driven by a single actuator, yet can grasp objects spanning a wide range of size, shape, and mass. The hand is constructed using polymer-based Shape Deposition Manufacturing (SDM), with joints formed by elastomeric flexures and actuator and sensor components embedded in tough rigid polymers. The hand has superior robustness properties, able to withstand large impacts without damage and capable of grasping objects in the presence of large positioning errors.
Pure appearance based visual maps can be constructed without considering any 3-D spatial information, nevertheless they can be used for robot localization and navigation. This paper proposes a topological framework ca...
详细信息
ISBN:
(纸本)9783642001956
Pure appearance based visual maps can be constructed without considering any 3-D spatial information, nevertheless they can be used for robot localization and navigation. This paper proposes a topological framework capable of coordinate multi-agent navigation through an appearance based topological map using only grabbed images as sensory data. A novel image based optimal feature planner is presented, that allows optimal vehicle trajectories. The planner uses a pure visual-based control with a calibrated visual sensor that takes into-account the field-of-view (FOV) constraint of low-cost monocular cameras in order to keep the tracked features in sight;while the robot manoeuvres.
We present a sensorless method for localizing a, robotic catheter inside the left atrium using intracardiac echo (ICE) ultrasound. As the robotic catheter navigates inside the anatomy, its kinematics provide a rough e...
详细信息
ISBN:
(纸本)9783642001956
We present a sensorless method for localizing a, robotic catheter inside the left atrium using intracardiac echo (ICE) ultrasound. As the robotic catheter navigates inside the anatomy, its kinematics provide a rough estimate of change in pose. At the same time, an ICE catheter inserted through the robotic catheter's lumen acquires images to refine this estimate. Our algorithm is based on the Unscented Particle Filter (UPF) for stochastic state estimation. We iteratively determine the catheter's pose by comparing newly acquired ICE images to segmented Computed Tomography (CT) images of the left atrium. After considering less than fifteen second's worth of ICE data, the algorithm converges to an accurate pose estimate despite significant deviations from the kinematic model, and unmodeled movements in the anatomy.
暂无评论