Institut de Robòtica i Informàtica Industrial, CSIC-UPC
http://hdl.handle.net/2117/2249
2015-08-04T16:08:49ZClosed-loop inverse kinematics for redundant robots: comparative assessment and two enhancements
http://hdl.handle.net/2117/76480
Closed-loop inverse kinematics for redundant robots: comparative assessment and two enhancements
Colomé Figueras, Adrià; Torras, Carme
Motivated by the need of a robust and practical Inverse Kinematics (IK) algorithm for the WAM robot arm, we reviewed the most used Closed-Loop IK (CLIK) methods for redundant robots, analysing their main points of concern: convergence, numerical error, singularity handling, joint limit avoidance, and the capability of reaching secondary goals. As a result of the experimental comparison, we propose two enhancements. The first is a new filter for the singular values of the Jacobian matrix that guarantees that its conditioning remains stable, while none of the filters found in literature is successful at doing so. The second is to combine a continuous task priority strategy with selective damping to generate smoother trajectories. Experimentation on the WAM robot arm shows that these two enhancements yield an IK algorithm that improves on the reviewed state-of-the-art ones, in terms of the good compromise it achieves between time step length, Jacobian conditioning, multiple task performance, and computational time, thus constituting a very solid option in practice. This proposal is general and applicable to other redundant robots.
2015-01-01T00:00:00ZContinuous real time POMCP to find-and-follow people by a humanoid service robot
http://hdl.handle.net/2117/76344
Continuous real time POMCP to find-and-follow people by a humanoid service robot
Goldhoorn, Alex; Garrell Zulueta, Anais; Alquézar Mancho, René; Sanfeliu Cortés, Alberto
2014-01-01T00:00:00ZRobust surface tracking in range image sequences
http://hdl.handle.net/2117/76255
Robust surface tracking in range image sequences
Husain, Syed Farzad; Dellen, Babette Karla Margarete; Torras, Carme
A novel robust method for surface tracking in range-image sequences is presented which combines a clustering method based on surface models with a particle-filter-based 2-D affine-motion estimator. Segmented regions obtained at previous time steps are used to create seed areas by comparing measured depth values with those obtained from surface-model fitting. The seed areas are further refined using a motion-probability region estimated by the particle-filter-based tracker through prediction of future states. This helps resolving ambiguities that arise when surfaces belonging to different objects are in physical contact with each other, for example during hand-object manipulations. Region growing allows recovering the complete segment area. The obtained segmented regions are then used to improve the predictions of the tracker for the next frame. The algorithm runs in quasi real-time and uses on-line learning, eliminating the need to have a priori knowledge about the surface being tracked. We apply the method to in-house depth videos acquired with both time-of-flight and structured-light sensors, demonstrating object tracking in real-world scenarios, and we compare the results with those of an ICP-based tracker. (C) 2014 Elsevier Inc. All rights reserved.
2014-01-01T00:00:00ZLocalization in highly dynamic environments using dual-timescale NDT-MCL
http://hdl.handle.net/2117/28567
Localization in highly dynamic environments using dual-timescale NDT-MCL
Valencia Carreño, Rafael; Saarinen, Jari; Andreasson, Henrik; Vallvé Navarro, Joan; Andrade-Cetto, Juan; Lilienthal, Achim
Industrial environments are rarely static and often their configuration is continuously changing due to the material transfer flow. This is a major challenge for infrastructure free localization systems. In this paper we address this challenge by introducing a localization approach that uses a dual- timescale approach. The proposed approach - Dual-Timescale Normal Distributions Transform Monte Carlo Localization (DT- NDT-MCL) - is a particle filter based localization method, which simultaneously keeps track of the pose using an apriori known static map and a short-term map. The short-term map is continuously updated and uses Normal Distributions Transform Occupancy maps to maintain the current state of the environment. A key novelty of this approach is that it does not have to select an entire timescale map but rather use the best timescale locally. The approach has real-time performance and is evaluated using three datasets with increasing levels of dynamics. We compare our approach against previously pro- posed NDT-MCL and commonly used SLAM algorithms and show that DT-NDT-MCL outperforms competing algorithms with regards to accuracy in all three test cases.
2014-01-01T00:00:00ZDimensionality reduction for probabilistic movement primitives
http://hdl.handle.net/2117/28553
Dimensionality reduction for probabilistic movement primitives
Colomé Figueras, Adrià; Neumann, Gerhard; Peters, Jan; Torras, Carme
Humans as well as humanoid robots can use a large number of degrees of freedom to solve very complex motor tasks. The high-dimensionality of these motor tasks adds difficulties to the control problem and machine learning algorithms. However, it is well known that the intrinsic dimensionality of many human movements is small in comparison to the number of employed DoFs, and hence, the movements can be represented by a small number of synergies encoding the couplings between DoFs. In this paper, we want to apply Dimensionality Reduction (DR) to a recent movement representation used in robotics, called Probabilistic Movement Primitives (ProMP). While ProMP have been shown to have many benefits, they suffer with the high-dimensionality of a robotic system as the number of parameters of a ProMP scales quadratically with the dimensionality. We use probablistic dimensionality reduction techniques based on expectation maximization to extract the unknown synergies from a given set of demonstrations. The ProMP representation is now estimated in the low-dimensional space of the synergies. We show that our dimensionality reduction is more efficient both for encoding a trajectory from data and for applying Reinforcement Learning with Relative Entropy Policy Search (REPS).
2014-01-01T00:00:00ZSingle-layer economic model predictive control for periodic operation
http://hdl.handle.net/2117/28547
Single-layer economic model predictive control for periodic operation
Limón Marruedo, Daniel; Pereira Martin, Mario; Muñoz de la Peña, David; Álamo Cantarero, Teodoro; Grosso Pérez, Juan Manuel
In this paper we consider periodic optimal operation of constrained periodic linear systems. We propose an economic model predictive controller based on a single layer that unites dynamic real time optimization and control. The proposed controller guarantees closed-loop convergence to the optimal periodic trajectory that minimizes the average operation cost for a given economic criterion. A priori calculation of the optimal trajectory is not required and if the economic cost function is changed, recursive feasibility and convergence to the new periodic optimal trajectory is guaranteed. The results are demonstrated with two simulation examples, a four tank system, and a simplified model of a section of Barcelona's water distribution network.
2014-01-01T00:00:00ZOutput-feedback model predictive control of sewer networks through moving horizon estimation
http://hdl.handle.net/2117/28546
Output-feedback model predictive control of sewer networks through moving horizon estimation
Joseph Duran, Bernat; Ocampo-Martínez, Carlos; Cembrano Gennari, Gabriela
Based on a simplified control-oriented hybrid linear delayed model, model predictive control (MPC) of a sewer network designed to reduce pollution during heavy rain events is presented. The lack of measurements at many parts of the system to update the initial conditions of the optimal control problems (OCPs) leads to the need for estimation techniques. A simple modification of the OCP used in the MPC iterations allows to formulate a state estimation problem (SEP) to reconstruct the full system state from a few measurements. Results comparing the system performance under the MPC controller using full-state measurements and a moving horizon estimation (MHE) strategy solving a finite horizon SEP at each time instant are presented. Closed-loop simulations are performed by using a detailed physically-based model of the network as virtual reality.
2014-01-01T00:00:00ZConsistent depth video segmentation using adaptive surface models
http://hdl.handle.net/2117/28476
Consistent depth video segmentation using adaptive surface models
Husain, Syed Farzad; Dellen, Babette Karla Margarete; Torras, Carme
We propose a new approach for the segmentation of 3-D point clouds into geometric surfaces using adaptive surface models. Starting from an initial configuration, the algorithm converges to a stable segmentation through a new iterative split-and-merge procedure, which includes an adaptive mechanism for the creation and removal of segments. This allows the segmentation to adjust to changing input data along the movie, leading to stable, temporally coherent, and traceable segments. We tested the method on a large variety of data acquired with different range imaging devices, including a structured-light sensor and a time-of-flight camera, and successfully segmented the videos into surface segments. We further demonstrated the feasibility of the approach using quantitative evaluations based on ground-truth data.
2014-01-01T00:00:00ZCompetitive 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.
2014-01-01T00:00:00ZSocial robots: a meeting point between science and fiction
http://hdl.handle.net/2117/28382
Social robots: a meeting point between science and fiction
Torras, Carme
Industrial robots and androids in science fiction were worlds apart until recently, but now begin to merge with the rapid development of social robotics. Given the growing need for labour in the healthcare and service sectors, robots are being designed to interact with the disabled and elderly people, or to take the place of receptionists or shop assistants in shopping malls, or even to act as support teachers or nannies. Within this context, efforts have grown to facilitate mutual inspiration between techno-science and humanities. Ethical issues such as the influence of robotic nannies on child psyche, previously within the realms of literary works, are now being discussed in scientific forums.
2015-01-01T00:00:00Z