International Symposium on Artificial Intelligence 

About: International Symposium on Artificial Intelligence is an academic conference. The conference publishes majorly in the area(s): Robot & Robotics. Over the lifetime, 897 publications have been published by the conference receiving 4683 citations.

Planning and Scheduling for Fleets of Earth Observing Satellites

Abstract: We address the problem of scheduling observations for a collection of earth observing satellites. This scheduling task is a difficult optimization problem, potentially involving many satellites, hundreds of requests, constraints on when and how to service each request, and resources such as instruments, recording devices, transmitters, and ground stations. High-fidelity models are required to ensure the validity of schedules; at the same time, the size and complexity of the problem makes it unlikely that systematic optimization search methods will be able to solve them in a reasonable time. This paper presents a constraint-based approach to solving the Earth Observing Satellites (EOS) scheduling problem, and proposes a stochastic heuristic search method for solving it.

Efficient Constrained Path Planning via Search in State Lattices

Abstract: An addressable subscription television decoder includes an input stage including an IF amplifier for converting a scrambled RF television signal to a composite baseband video signal. The baseband video signal comprises either a nominal sync component or a sync component having suppressed horizontal sync pulses during video fields and having non-suppressed sync pulses during vertical intervals, the vertical intervals also including selected encoded data signals. An AGC voltage for controlling the gain of the IF amplifier is developed by a circuit exhibiting a relatively short time constant whenever the composite baseband video signal is characterized by nominal level sync pulses, the time constant being increased in response to suppressed horizontal sync pulses. The sync pulses produced during the vertical intervals of the composite baseband video signal are thereby not subjected to excessive IF gain for facilitating processing of the data signals by the decoder.

Motion and Parameter Estimation of a Free-Floating Space Object from Range Data for Motion Prediction

Abstract: A method is investigated for the motion estima- tion and the model identification of a free-floating target in space Motion estimation relies on range data measurements, which are here simulated for analyzing the method The work is motivated by the necessity to provide an efficient long-term motion prediction algorithm, in the order of 100 seconds, to support planning of complex maneuvers or tracking during long phases without observation The method is evaluated for different scenarios of range measurements and for a series of target motions, including translation and rotation or pure rotation about different axes, which may represent typical scenarios for tumbling objects in orbit This work investigates a method for the motion estima- tion and for the dynamic model identification of a free- floating target in space The motion parater estimation is performed from range data as may be measured by stereo vision or a laser range sensor The goal of this procedure is to finally allow long-term motion prediction of the target, in the order of 100 seconds, with the identified dynamic model In the estimation procedure, it is assumed that nothing is initially known about the inertial properties, the geometry, or the motion of the target The present study is distinct from others aiming at short- term prediction to the next observation, parameter identi- fication, where the goal is the accuracy of the identified parameters, and pose estimation or tracking of a known object, where high-level model knowledge can be used Long-term prediction is useful for the case in which observation is not possible for a long time (eg occlusions, limited communication to ground) or in which a task which requires long-term planning is of interest (such as autonomous grasping) The task is divided into three subtasks: motion estimation from range data, parameter identification from the motion estimates, and prediction with the identified parameters Simulated range data will be used to analyze the method Different scenarios of range data measurements are con- sidered The computation time and the robustness to noise and to parameter excitation of the method are addressed An empirical error statistics is also presented

Inflatable robotics for planetary applications

Abstract: Space Inflatable vehicles have been finding popularity in recent years for applications as varied as spacecraft antennas, space-based telescopes, solar sails, and manned habitats [1]. Another branch of space inflatable technology has also considered developing ambient gasfilled, solar balloons for Mars as well as ambient gasfilled inflatable rovers [2]. More recently, some other intriguing space-inflatable vehicles have been proposed for the gas planets and Pluto, as well as for Saturn's moon, Titan, Neptune's moon, Triton, and Jupiter's moon, Io [3].

Robust watermarking scheme based on RDWT-SVD: Embedding data in all subbands

Abstract: In this paper, a new method for non-blind image watermarking presented that is robust against affine transformation and ordinary image manipulation. The proposed method presents a watermarking scheme based on redundant discrete wavelet transform (RDWT) and Singular Value Decomposition (SVD). After applying RDWT to cover image, we apply SVD to each subband. Then we modify singular values of the cover image using singular values of the visual watermark. The advantage of the proposed technique is its robustness against most common attacks. Analysis and experimental results show higher performance of the proposed method in comparison to the DWT-SVD method.