The ability to follow specific and task-relevant paths is an essential feature for legged humanoid robots. In this paper, we describe a technique for programming walking paths for humanoid robots based on imitation. D...
详细信息
ISBN:
(纸本)9783540767282
The ability to follow specific and task-relevant paths is an essential feature for legged humanoid robots. In this paper, we describe a technique for programming walking paths for humanoid robots based on imitation. Demonstrated paths are synthesized as NURBS (Non Uniform Rational B-Spline), and can be adapted by the robot based on local and dynamic information. We report simple experiments performed with a Robosapien V2 low-cost humanoid toy which has been suitably enhanced to support imitation-based programming. We show that despite robot limitations rather complex navigational tasks can be achieved through visual guidance. The system combines inputs from multiple sensory devices, including a motion tracker and a monocular vision system for landmark recognition.
This paper presents a hybrid formation controller approach for non-holonomic mobile robots. This approach is based on the stable switching between a leader-following formation controller and an orientation controller....
详细信息
ISBN:
(纸本)9783540767282
This paper presents a hybrid formation controller approach for non-holonomic mobile robots. This approach is based on the stable switching between a leader-following formation controller and an orientation controller. The switching attempts to maintain low values of formation errors during specific leader movements that otherwise will produce a significant increment on such errors. Experimental results on commercial unicycle-like mobile robots are provided to show the feasibility and performance of the proposed control strategy.
This paper presents a robust neural network motion tracking control methodology for piezoelectric actuation systems employed in micro/nano manipulation. This control methodology is proposed for tracking desired motion...
详细信息
ISBN:
(纸本)9783540767282
This paper presents a robust neural network motion tracking control methodology for piezoelectric actuation systems employed in micro/nano manipulation. This control methodology is proposed for tracking desired motion trajectories in the presence of unknown system parameters, non-linearities including the hysteresis effect, and external disturbances in the control systems. In this paper, the control methodology is established including the neural networks and a sliding scheme. In particular, the radial basis function neural networks are chosen in this study for function approximations. The stability of the closed-loop systems and convergence of the position and velocity tracking errors to zero are assured by the control methodology in the presence of the aforementioned conditions. Simulation results of the control methodology for tracking of a desired motion trajectory is presented. With the capability of motion tracking, the proposed control methodology can be utilised to realise high performance piezoelectric actuated micro/nano manipulation systems.
A particle filter framework of multiple evidence fusion and model matching in a sequence of images is presented for robust recognition and pose estimation of 3D objects. It attempts to challenge a long-standing proble...
详细信息
ISBN:
(纸本)9783540767282
A particle filter framework of multiple evidence fusion and model matching in a sequence of images is presented for robust recognition and pose estimation of 3D objects. It attempts to challenge a long-standing problem in robot vision, so called, how to ensure the dependability of its performance under the large variation in visual properties of a scene due to changes in illumination, texture, occlusion, as well as camera pose. To ensure the dependability, we propose a behavioral process in vision, where possible interpretations are carried probabilistically in space and time for further investigations till they are converged to a credible decision by additional evidences. The proposed approach features 1) the automatic selection and collection of an optimal set of evidences based on in-situ monitoring of environmental variations, 2) the derivation of multiple interpretations, as particles representing possible object poses in 3D space, and the assignment of their probabilities based on matching the object model with evidences, and 3) the particle filtering of interpretations in time with the additional evidences obtained from a sequence of images. The proposed approach has been validated by the stereo-camera based experimentation of 3D object recognition and pose estimation, where a combination of photometric and geometric features are used for evidences.
This paper proposes a switched visual feedback control method for a micro helicopter under occlusions. Two stationary cameras are placed on the ground. They track four black balls attached to rods connected to the bot...
详细信息
ISBN:
(纸本)9783540767282
This paper proposes a switched visual feedback control method for a micro helicopter under occlusions. Two stationary cameras are placed on the ground. They track four black balls attached to rods connected to the bottom of the helicopter. The control input is computed by using the errors between the positions of the tracked objects and pre-specified reference values for them. The multi-camera configuration enables us to design a switched controller which is robust against occlusions. The proposed controller selects a camera which correctly measures all of the tracked object positions at each time. If a camera loses a tracked object, then the camera searches for the four tracked objects by using an image data captured from the other camera. The proposed controller can keep the helicopter in a stable hover even when one of the cameras loses tracked objects due to occlusions.
This paper presents a novel tripedal mobile robot STriDER (Self-excited Tripedal Dynamic Experimental Robot) and considerations for gait planning strategies based on kinematics. To initiate a step, two of the robot...
详细信息
ISBN:
(纸本)9783540767282
This paper presents a novel tripedal mobile robot STriDER (Self-excited Tripedal Dynamic Experimental Robot) and considerations for gait planning strategies based on kinematics. To initiate a step, two of the robot's legs are oriented to push the center of gravity outside the support triangle formed by the three foot contact points, utilizing a unique abductor joint mechanism. As the robot begins to fall forward, the middle leg or swing leg, swings in between the two stance legs and catches the fall. Simultaneously, the body rotates 180 degrees around a body pivot line preventing the legs from tangling up. In the first version of STriDER the concept of passive dynamic locomotion was emphasized;however for the new version, STriDER 2.0, all joints are actively controlled for robustness. Several kinematic constraints are discussed as the robot takes a step including;stability, dynamics, body height, body twisting motion, and the swing leg's path. These guidelines will lay the foundation for future gait generation developments utilizing both the kinematics and dynamics of the system.
Object recognitions are challenging tasks, especially partially or fully occluded object recognition in changing and unpredictable robot environments. We propose a novel approach to construct semantic contexts using o...
详细信息
ISBN:
(纸本)9783540767282
Object recognitions are challenging tasks, especially partially or fully occluded object recognition in changing and unpredictable robot environments. We propose a novel approach to construct semantic contexts using ontology inference for mobile robots to recognize objects in real-world situations. By semantic contexts we mean characteristic information abstracted from robot sensors. In addition, ontology has been used for better recognizing objects using knowledge represented in the ontology where OWL (Web Ontology Language) has been used for representing object ontologies and contexts. We employ a four-layered robot-centered ontology schema to represent perception, model, context, and activity for intelligent robots. And, axiomatic rules have been used for generating semantic contexts using OWL ontologies. Experiments are successfully performed for recognizing partially occluded objects based on our ontology-based semantic context model without contradictions in real applications.
A paracatadioptric camera consists of the coupling of a parabolic mirror with a telecentric lens which realizes an orthographic projection to the image sensor. This type of camera provides large field of view images a...
详细信息
ISBN:
(纸本)9783540767282
A paracatadioptric camera consists of the coupling of a parabolic mirror with a telecentric lens which realizes an orthographic projection to the image sensor. This type of camera provides large field of view images and has therefore potential applications for mobile and aerial robots. This paper is concerned with visual servoing using paracatadioptric cameras. A new optimal combination of visual features is proposed for visual servoing from spheres. Using this combination, a classical control law is proved to be globally stable even in the presence of modeling error. Experimental and simulation results validate the proposed theoretical results.
Object search is a very common task we perform each time we need an object. Humanoid robots are multipurpose platforms and will need to use generic tools to extend their capacities. It must thus be able to look for ob...
暂无评论