Filters








29,945 Hits in 5.2 sec

Real-Time Trajectory Generation for Target Localization Using Micro Air Vehicles

Jeffrey B. Corbets, Jack W. Langelaan
2010 Journal of Aerospace Computing Information and Communication  
Thus, trajectory generation occurs in near-constant time, which allows for fast adaptation as the target state estimate is refined.  ...  This thesis presents an approach to near-optimal target localization for small and micro unmanned aerial vehicles using a family of pre-computed parameterized trajectories.  ...  Model A second order approximation is used to generate a discrete time model for vehicle kinematics with sample time T s .  ... 
doi:10.2514/1.47834 fatcat:3ohl466rcrhwncan2gefh4san4

Task Feasibility Maximization Using Model-Free Policy Search and Model-Based Whole-Body Control

Ryan Lober, Olivier Sigaud, Vincent Padois
2020 Frontiers in Robotics and AI  
Unfortunately, tasks are generally planned without close consideration for the underlying controller being used, or the other tasks being executed, and are often infeasible when executed on the robot.  ...  In this work, we develop a proof-of-concept optimization loop which automatically improves task feasibility using model-free policy search in conjunction with model-based whole-body control.  ...  The authors would like to thank Jorhabib Eljaik (Sorbonne Université) and Gabriele Nava, Stefano Dafarra, Francesco Romano, Daniele Pucci, Silvio Traversaro, Francesco Nori (IIT) for their great help and  ... 
doi:10.3389/frobt.2020.00061 pmid:33501229 pmcid:PMC7805637 fatcat:xg4ihr5caran5kdqzitwzxtigq

AVSS 2011 demo session: A systems level approach to perimeter protection

Peter Tu, Ting Yu, Dashan Gao, Ram Nevatia, Sung Chun Lee, Hale Kim, Phill Kyu Rhee, Joong-Hwan Baek
2011 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)  
The real time task consisted of a trajectory based event detection method that can process in real time.  ...  To support this requirement, we divided our system into two modules that perform both real time and semi-real time tasks.  ... 
doi:10.1109/avss.2011.6027396 dblp:conf/avss/TuYGNLKRB11 fatcat:sj2u43mfcff65lpevkfyumyz3y

A Survey on Learning-Based Model Predictive Control: Toward Path Tracking Control of Mobile Platforms

Kanghua Zhang, Jixin Wang, Xueting Xin, Xiang Li, Chuanwen Sun, Jianfei Huang, Weikang Kong
2022 Applied Sciences  
It is well known that the machine learning (ML) methods use the historical and real-time measurement data to build data-driven prediction models.  ...  Furthermore, some research challenges faced by LB-MPC for path tracking control in mobile platforms are discussed.  ...  Acknowledgments: The authors would like to thank all anonymous reviewers and editors for their helpful suggestions for the improvement of this paper.  ... 
doi:10.3390/app12041995 fatcat:hdy753pdbfhjvihdopaw6lip2u

Head-Tracking For Gestural And Continuous Control Of Parameterized Audio Effects

David Merrill
2003 Zenodo  
This paper describes a system which uses the output fromhead-tracking and gesture recognition software to drive aparameterized guitar effects synthesizer in real-time.  ...  This paper presents a working system that uses a modified real-time head-tracker to drive a parameterized guitar effects processor.  ...  A conceptual model for a similar system was proposed by Lyons [7] , and he built a system that used a visual mouth-tracker to drive parameterized audio effects [8] .  ... 
doi:10.5281/zenodo.1176530 fatcat:qdfrym5w6raftgxgejfwqjlclq

Encoding Physical Constraints in Differentiable Newton-Euler Algorithm [article]

Giovanni Sutanto, Austin S. Wang, Yixin Lin, Mustafa Mukadam, Gaurav S. Sukhatme, Akshara Rai, Franziska Meier
2020 arXiv   pre-print
We evaluate our method on real-time inverse dynamics control tasks on a 7 degree of freedom robot arm, both in simulation and on the real robot.  ...  The recursive Newton-Euler Algorithm (RNEA) is a popular technique for computing the dynamics of robots.  ...  Next, we evaluate model on tracking a) the sine motion itself (which the parameters were fitted for), and b) on a series of 5 operational space control tasks.  ... 
arXiv:2001.08861v4 fatcat:wsqwoq6tyvhffpfret3fg4ad3m

I-SENSE: A Light-Weight Middleware for Embedded Multi-Sensor Data-Fusion

Allan Tengg, Andreas Klausner, Bernhard Rinner
2007 2007 Fifth Workshop on Intelligent Solutions in Embedded Systems  
Due to the high onboard processing and communication power of the used hardware, our proposed architecture is designed to perform sophisticated data fusion tasks.  ...  In our I-SENSE project we demonstrate the combination the scientific research areas multi-sensor data fusion and pervasive embedded computing.  ...  Figure 2 : 2 A simple Fusion Model Figure 3 : 3 The main services of the I-SENSE middleware Figure 4 : 4 The I-SENSE middleware from the viewpoint of a fusion task Table 1: Time required to load  ... 
doi:10.1109/wises.2007.4408489 dblp:conf/wises/TenggKR07 fatcat:xyolfphw6nfc7nv2hjdqporbf4

Adaptive Optical Sensing in an Object Tracking DDDAS

Anthony Vodacek, John P. Kerekes, Matthew J. Hoffman
2012 Procedia Computer Science  
The generalized optical remote sensing tracking problem for an object moving in a dynamic urban environment is complex.  ...  Here we described our work on the creation of a modeling system for optical tracking in complex environments, with a focus on integrating an adaptive imaging sensor within the system framework.  ...  Thus, the cost function provides a means to make the critical step of a true DDDAS where the examination of the model state leads to the near real-time (rather than design-time) trade-off assessment of  ... 
doi:10.1016/j.procs.2012.04.125 fatcat:35h73i7dzrdlraz7a464qomj4q

Dynamic Active Contours for Visual Tracking

M. Niethammer, A. Tannenbaum, S. Angenent
2006 IEEE Transactions on Automatic Control  
It is based on a new energy minimization functional which, for the first time, puts dynamics into the geodesic active contour framework.  ...  A subsequent prediction step ensures good initial placement for the next frame. This approach is unnatural; the curve evolution gets decoupled from the actual dynamics of the objects to be tracked.  ...  Wake for some very helpful comments.  ... 
doi:10.1109/tac.2006.872837 pmid:23729836 pmcid:PMC3666594 fatcat:f77dixgc7fgkfnsf4p5tmvmyx4

Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations [article]

An T. Le, Meng Guo, Niels van Duijkeren, Leonel Rozo, Robert Krug, Andras G. Kupcsik, Mathias Buerger
2021 arXiv   pre-print
Task parameterized representations allow easy adaptation to new scenes and online observations.  ...  Furthermore, an online execution algorithm is proposed to adapt the skill execution to real-time observations of robot poses, measured forces, and changed scenes.  ...  modeled as a task parameterized Gaussian mixture model (TP-GMM).  ... 
arXiv:2109.04222v1 fatcat:zmips3cysbbyvjpwiqyzu6aune

Parametric Approach to Trajectory Tracking Control of Robot Manipulators

Shijie Zhang, Yi Ning
2013 Journal of Applied Mathematics  
The optimal control problem is first solved as an open loop optimal control problem by using a time scaling transform and the control parameterization method.  ...  The mathematic description of the trajectory of robot manipulators with the optimal trajectory tracking problem is formulated as an optimal control problem, and a parametric approach is proposed for the  ...  square sense.  ... 
doi:10.1155/2013/958597 fatcat:i535uwxrtjbhregse63diwzryq

ConFusion: Sensor Fusion for Complex Robotic Systems using Nonlinear Optimization

Timothy Sandy, Lukas Stadelmann, Simon Kerscher, Jonas Buchli
2019 IEEE Robotics and Automation Letters  
We present ConFusion, an open-source package for online sensor fusion for robotic applications.  ...  We demonstrate its performance in comparison to an iterated extended Kalman filter in visual-inertial tracking, and show its versatility through whole-body sensor fusion on a mobile manipulator.  ...  Andreas Wieser and Robert Presl for providing and operating the Leica Tracker for acquiring ground truth measurements.  ... 
doi:10.1109/lra.2019.2894168 fatcat:2uwaihj6jndrhcww4peev645xy

Using Driver Control Models to Understand and Evaluate Behavioral Validity of Driving Simulators

2018 IEEE Transactions on Human-Machine Systems  
For a driving simulator to be a valid tool for research, vehicle development, or driver training, it is crucial that it elicits similar driver behavior as the corresponding real vehicle.  ...  As a task-specific example, two parsimonious driver steering models of this nature are developed and tested on a dataset of real and simulated driving in near-limit, low-friction circumstances, indicating  ...  Qian for their assistance with data collection.  ... 
doi:10.1109/thms.2018.2848998 fatcat:43w5p3tbvbfwreo2j7js6d4paa

Constructing task visibility intervals for a surveillance system

Ser-Nam Lim, Anurag Mittal, Larry Davis
2005 Proceedings of the third ACM international workshop on Video surveillance & sensor networks - VSSN '05  
For this purpose, we describe an algorithm that constructs "task visibility intervals", which are tuples of information about what to sense (task-object pairs), when to sense (feasible future temporal  ...  intervals to start a task) and how to sense (the camera to use and the corresponding viewing angles and focal length).  ...  CONCLUSIONS We have described a multi-camera system that constructs (M)TVIs as the basis for deciding suitable time periods to capture moving objects in the scene.  ... 
doi:10.1145/1099396.1099421 fatcat:lnce6jehhfcrrolqbrnafkzag4

On Real-time Image Reconstruction with Neural Networks for MRI-guided Radiotherapy [article]

David E. J. Waddington, Nicholas Hindley, Neha Koonjoo, Christopher Chiu, Tess Reynolds, Paul Z. Y. Liu, Bo Zhu, Danyal Bhutto, Chiara Paganelli, Paul J. Keall, Matthew S. Rosen
2022 arXiv   pre-print
The gold-standard for reconstruction of undersampled MR data is compressed sensing (CS) which is computationally slow and limits the rate that images can be available for real-time adaptation.  ...  These findings imply that neural-network-based reconstruction is potentially superior to existing approaches for real-time image guidance applications.  ...  underutilized capacity in the over-parameterized model architecture.  ... 
arXiv:2202.05267v2 fatcat:hjx7zgddivee5ktgpruq5wrym4
« Previous Showing results 1 — 15 out of 29,945 results