Reports de recerca
http://hdl.handle.net/2117/2252
2015-08-04T22:12:17ZCompetitive function approximation for reinforcement learning
http://hdl.handle.net/2117/28454
Competitive function approximation for reinforcement learning
Agostini, Alejandro Gabriel; Celaya Llover, Enric
The application of reinforcement learning to problems with continuous domains requires representing the value function by means of function approximation. We identify two aspects of reinforcement learning that make the function approximation process hard: non-stationarity of the target function and biased sampling. Non-stationarity is the result of the bootstrapping nature of dynamic programming where the value function is estimated using its current approximation. Biased sampling occurs when some regions of the state space are visited too often, causing a reiterated updating with similar values which fade out the occasional updates of infrequently sampled regions.
We propose a competitive approach for function approximation where many different local approximators are available at a given input and the one with expectedly best approximation is selected by means of a relevance function. The local nature of the approximators allows their fast adaptation to non-stationary changes and mitigates the biased sampling problem. The coexistence of multiple approximators updated and tried in parallel permits obtaining a good estimation much faster than would be possible with a single approximator. Experiments in different benchmark problems show that the competitive strategy provides a faster and more stable learning than non-competitive approaches.
2014-01-01T00:00:00ZTeaching grasping points using natural movements
http://hdl.handle.net/2117/27630
Teaching grasping points using natural movements
Isleyici, Yalim; Alenyà Ribas, Guillem
A common strategy to teach a robot certain skills involves demonstration. While the demonstrations are best made by directly manipulating the robot, in hazardous conditions the only choice is teleoperation. Even though haptic devices offer fairly good results, using natural movements would give a better feeling of control.
Leap Motion sensor (Leap Motion Inc., USA) is a device that detects hands and it can be used to control the robot arm in a more natural way. In this work, a system that will control the WAM arm (Barret Technology Inc., USA) using the Leap Motion sensor will be explained. Later this system will be tested in order to grasp a polo shirt which will be used to train grasping points on the shirt.
2014-01-01T00:00:00ZHybrid linear sewer network model
http://hdl.handle.net/2117/22803
Hybrid linear sewer network model
Joseph Duran, Bernat; Ocampo-Martínez, Carlos; Cembrano Gennari, Gabriela
This technical report presents a novel control-oriented hybrid linear sewer network model. It also provides the mathematical details of the Mixed Logical Dynamic (MLD) systems reformulation of the system equations to turn all the involved hybrid/logical statements into linear inequalities by means of the definition of binary variables. Using this reformulation a compact hybrid linear delayed expression is obtained to be used for simulation or optimal control purposes.
2013-01-01T00:00:00ZThe MoveIt motion planning framework configuration for the IRI WAM robot
http://hdl.handle.net/2117/22502
The MoveIt motion planning framework configuration for the IRI WAM robot
Gonzàlez Esteve, Adrià; Alenyà Ribas, Guillem
Perform the setup and prepare WAM robots to use the the motion planning and obstacle avoid-
ance facilities present at the MoveIt! framework. In particular, determine the configurations
and API function calls to set the target of the robot arm with joint state and add collision
objects programatically, without using the graphical interface. Supporting page with videos:
http://www.iri.upc.edu/groups/perception/MoveItForIRIWam
2013-01-01T00:00:00ZRobot de telepresencia: imatge i so
http://hdl.handle.net/2117/20196
Robot de telepresencia: imatge i so
Serra Ortega, Joan; Alenyà Ribas, Guillem
El robot Helena està dissenyat per ser un robot de telepresència que ha de servir per
comunicar diferents persones d'un edifici sense necessitat de moure's.
2013-01-01T00:00:00ZBranch switching from singular points in higher-dimensional continuation
http://hdl.handle.net/2117/15641
Branch switching from singular points in higher-dimensional continuation
Bohigas Nadal, Oriol
We explain here how to perform branch switching when a singular point is found during higherdimensional continuation on a k-dimensional variety. This document is based on the information given in [1, 2, 3].
2011-01-01T00:00:00ZStochastic approximations of average values using proportions of samples
http://hdl.handle.net/2117/14112
Stochastic approximations of average values using proportions of samples
Agostini, Alejandro Gabriel; Celaya Llover, Enric
In this work we explain how the stochastic approximation of the average of a random variable is carried out when the observations used in the updates consist in proportion of samples rather than complete
samples.
IRI Technical Report
2011-01-01T00:00:00ZA general strategy for interactive decision-making in robotic platforms
http://hdl.handle.net/2117/13951
A general strategy for interactive decision-making in robotic platforms
Agostini, Alejandro Gabriel; Torras, Carme; Wörgötter, Florentin
This work presents an intergated strategy for planning and learning suitable to execute tasks with robotic platforms without any previous task specification. The approach rapidly learns planning operators from few action experiences using a competitive strategy where many alternatives of cause-effect explanations are evaluated in parallel, and the most successful ones are used to generate the operators. The system operates without task interruption by integrating in the planning-learning loop a human teacher that supports the planner in making decisions. All the mechanisms are integrated and synchronized in the robot using a general decision-making framework.
2011-01-01T00:00:00ZRegistration of 3d point clouds for urban robot mapping
http://hdl.handle.net/2117/13936
Registration of 3d point clouds for urban robot mapping
Teniente Avilés, Ernesto; Andrade-Cetto, Juan
We consider the task of mapping pedestrian urban areas for a robotic guidance and surveillance application. This mapping is performed by registering three-dimensional laser range scans acquired with two different robots.
To solve this task we will use the Iterative Closes Point (ICP) algorithm proposed in [8],
but for the minimization step we will use the metric proposed by Biota et al. [10] trying to get advantage of the compensation between translation and rotation they mention. To reduce computational cost in the original ICP during matching, the correspondences search is done with the library Approximate Nearest Neighbor (ANN). Finally we propose a hierarchical new
correspondence search strategy, using a point-to-plane strategy at the highest level and the point-to-point metric at finer levels. At the highest level the adjust error between a plane and it’s n adjacent points describing the plane is computed, if this error is bigger than a threshold then we change the level.
2008-01-01T00:00:00ZPath planning with pose SLAM
http://hdl.handle.net/2117/12449
Path planning with pose SLAM
Valencia Carreño, Rafael; Andrade-Cetto, Juan; Porta Pleite, Josep Maria
The probabilistic belief networks that result from standard feature-based simultaneous localization and map building (SLAM) approaches cannot be directly used to plan trajectories. The reason is that they
produce a sparse graph of landmark estimates and their probabilistic relations, which is of little value to find collision free paths for navigation. In contrast, we argue in this paper that Pose SLAM graphs can be directly used as belief roadmaps (BRMs). The original BRM algorithm assumes a known model of the environment from which probabilistic sampling generates a roadmap. In our work, the roadmap is built on-line by the Pose SLAM algorithm. The result is a hybrid BRM-Pose SLAM method that devises optimal navigation strategies on-line by searching for the path with lowest accumulated uncertainty for the robot pose. The method is validated over synthetic data and standard SLAM datasets.
2010-01-01T00:00:00Z