Autonomous and Intelligent Systems (A/IS, to adhere to the terminology of the IEEE Ethically Alig... more Autonomous and Intelligent Systems (A/IS, to adhere to the terminology of the IEEE Ethically Aligned Design report) can gather their knowledge by different means and from different sources. In principle, learning algorithms are neutral; rather, it is the data they are fed during the learning period that can introduce biases or a specific ethical orientation. Human control over the learning process is more straightforward in learning from demonstration, where data sources are restricted to the choices of the demonstrator (or teacher), but even in unsupervised versions of reinforcement learning, biases are present via the definition of the reward function. In this paper we provide an overview of learning paradigms of artificial systems: supervised and unsupervised methods, with the most striking examples in each category, without too much technical detail. Furthermore, we describe the types of data sources that are presently available and in use by the robotics community. We also focu...
Summary. Landmark-based navigation in unknown unstructured environments is far from solved. The b... more Summary. Landmark-based navigation in unknown unstructured environments is far from solved. The bottleneck nowadays seems to be the fast detection of reliable visual references in the image stream as the robot moves. In our research, we have decoupled the navigation issues from this visual bottleneck, by first using artificial landmarks that could be easily detected and identified. Once we had a navigation system working, we developed a strategy to detect and track salient regions along image streams by just performing on-line pixel sampling. This strategy continuously updates the mean and covariances of the salient regions, as well as creates, deletes and merges regions according to the sample flow. Regions detected as salient can be considered as potential landmarks to be used in the navigation task. 1
The textbook on Motion Planning “Principles of Robot Motion: Theory, Algorithms, and Implementati... more The textbook on Motion Planning “Principles of Robot Motion: Theory, Algorithms, and Implementations”, by H. Choset et al., MIT Press, appeared on June 2005, is reviewed and compared to other two textbooks on the same subject, from 1991 and 2006 respectively. The ground-breaking developments over the last decade justify the necessity of the newer textbooks, that appear to be complementary, despite some overlap in the contents. Peer Reviewed
2011 15th International Conference on Advanced Robotics (ICAR), 2011
A learning framework with a bidirectional communication channel is proposed, where a human perfor... more A learning framework with a bidirectional communication channel is proposed, where a human performs several demonstrations of a task using a haptic device (providing him/her with force-torque feedback) while a robot captures these executions using only its force-based perceptive system. Our work departs from the usual approaches to learning by demonstration in that the robot has to execute the task blindly, relying only on force-torque perceptions, and, more essential, we address goal-driven manipulation tasks with multiple solution trajectories, whereas most works tackle tasks that can be learned by just finding a generalization at the trajectory level. To cope with these multiple-solution tasks, in our framework demonstrations are represented by means of a Hidden Markov Model (HMM) and the robot reproduction of the task is performed using a modified version of Gaussian Mixture Regression that incorporates temporal information (GMRa) through the forward variable of the HMM. Also, we exploit the haptic device as a teaching and communication tool in a human-robot interaction context, as an alternative to kinesthetic-based teaching systems. Results show that the robot is able to learn a container-emptying task relying only on force-based perceptions and to achieve the goal from several non-trained initial conditions.
Nonconvex polyhedral models of workpieces or robot parts can be directly tested for interference,... more Nonconvex polyhedral models of workpieces or robot parts can be directly tested for interference, without resorting to a previous decomposition into convex entities. We show that this interference detection, based on the elemental edge face intersection test, can be performed efficiently: a strategy based on applicability constraints reduces drastically the set of edge - face pairings that have to be considered for intersection. This is accomplished by using an appropriate representation, the spherical face orientation graph, developed by the authors, as well as feature pairing algorithms based on the plane sweep paradigm that have been adapted to work on that representation. Furthermore, the benefits of such a strategy extend to the computation of a lower distance bound between the polyhedra, both lowering the computational effort and improving the quality of the bound. Experimental results confirm the expected advantages of this strategy
Los sistemas autónomos e inteligentes (A/IS por sus siglas en inglés, en concordancia con el info... more Los sistemas autónomos e inteligentes (A/IS por sus siglas en inglés, en concordancia con el informe del IEEE sobre diseño alineado con la ética) pueden obtener sus conocimientos a través de diferentes procedimientos y de fuentes diversas. Los algoritmos de aprendizaje son neutros en principio, son más bien los datos con los que se alimentan durante el período de aprendizaje que pueden introducir sesgos o una orientación ética específica. El control humano sobre el proceso de aprendizaje es más directo en aprendizaje por demostración, donde las fuentes de datos están restringidas a las elecciones del demostrador (o profesor), pero incluso en las versiones no supervisadas del aprendizaje por refuerzo los sesgos están presentes a través de la definición de la función de recompensa. En este artículo proporcionamos una visión general de los paradigmas de aprendizaje de los sistemas artificiales: métodos supervisados y no supervisados, con los ejemplos más destacados de cada categoría, s...
Trabajo presentado en el 11th Scientific-Professional Symposium Textile Science and Economy, cele... more Trabajo presentado en el 11th Scientific-Professional Symposium Textile Science and Economy, celebrado en Zagreb (Croacia), el 24 de enero de 2018
2014 IEEE International Conference on Robotics and Automation (ICRA), 2014
We describe a system allowing a robot to learn goal-directed manipulation sequences such as steps... more We describe a system allowing a robot to learn goal-directed manipulation sequences such as steps of an assembly task. Learning is based on a free mix of exploration and instruction by an external teacher, and may be active in the sense that the system tests actions to maximize learning progress and asks the teacher if needed. The main component is a symbolic planning engine that operates on learned rules, defined by actions and their pre-and postconditions. Learned by model-based reinforcement learning, rules are immediately available for planning. Thus, there are no distinct learning and application phases. We show how dynamic plans, replanned after every action if necessary, can be used for automatic execution of manipulation sequences, for monitoring of observed manipulation sequences, or a mix of the two, all while extending and refining the rule base on the fly. Quantitative results indicate fast convergence using few training examples, and highly effective teacher intervention at early stages of learning.
9th International Workshop on Robot Motion and Control, 2013
Robot learning from demonstration faces new challenges when applied to tasks in which forces play... more Robot learning from demonstration faces new challenges when applied to tasks in which forces play a key role. Pouring liquid from a bottle into a glass is one such task, where not just a motion with a certain force profile needs to be learned, but the motion is subtly conditioned by the amount of liquid in the bottle. In this paper, the pouring skill is taught to a robot as follows. In a training phase, the human teleoperates the robot using a haptic device, and data from the demonstrations are statistically encoded by a parametric hidden Markov model, which compactly encapsulates the relation between the task parameter (dependent on the bottle weight) and the force-torque traces. Gaussian mixture regression is then used at the reproduction stage for retrieving the suitable robot actions based on the force perceptions. Computational and experimental results show that the robot is able to learn to pour drinks using the proposed framework, outperforming other approaches such as the classical hidden Markov models in that it requires less training, yields more compact encodings and shows better generalization capabilities.
In many applications, it suffices to know a lower bound on the distance between objects, instead ... more In many applications, it suffices to know a lower bound on the distance between objects, instead of the exact distance itself, which may be more difficult to compute. Such an easy-to-compute lower bound on the distance between two nonconvex polyhedra is presented here, which doesn't require a decomposition of the original polyhedra into convex entities. Furthermore, a suitable preprocessing of the polyhedra permits lowering the effort needed to compute this lower bound, and improves its quality. Experimental evidence is presented of the promise of this approach for assembly applications.
Orientation-related problems in geometric design can be naturally expressed on the spherical surf... more Orientation-related problems in geometric design can be naturally expressed on the spherical surface S 2. A wide subset of such problems can be solved directly on the sphere by adapting well-known planar data structures and algorithms. This paper shows that the detection of feasible contacts between two translating polyhedral models can be formulated as a problem of this type. First, a dual spherical representation of polyhedra is introduced, which reduces the contact detection above to nding intersections between two sets of spherical polygons. Next, the red-blue blocks plane sweep algorithm is adapted to obtain both edge intersections and pointin-polygon inclusions in the spherical setting. An experimental comparison of this algorithm against a na ve one shows an increasing advantage of the former as the complexity of the setting grows. The obtained edge-edge and vertex-face polyhedral contacts provide the relevant feature pairs to be tested for interference, leading to considerable savings in collision detection between polyhedral models, as shown in the experimental test performed.
Researchers are becoming aware of the importance of other information sources besides visual data... more Researchers are becoming aware of the importance of other information sources besides visual data in robot learning by demonstration (LbD). Forcebased perceptions are shown to convey very relevant information-missed by visual and position sensors-for learning specific tasks. In this paper, we review some recent works using forces as input data in LbD and Human-Robot interaction (HRI) scenarios, and propose a complete learning framework for teaching force-based manipulation skills to a robot through a haptic device. We suggest to use haptic interfaces not only as a demonstration tool but also as a communication channel between the human and the robot, getting the teacher more involved in the teaching process by experiencing the force signals sensed by the robot. Within the proposed framework, we provide solutions for treating force signals, extracting relevant information about the task, encoding the training data and generalizing to perform successfully under unknown conditions.
This paper proposes an end-to-end learning from demonstration framework for teaching forcebased m... more This paper proposes an end-to-end learning from demonstration framework for teaching forcebased manipulation tasks to robots. The strengths of this work are many-fold: first, we deal with the problem of learning through force perceptions exclusively. Second, we propose to exploit haptic feedback both as a means for improving teacher demonstrations and as a human-robot interaction tool, establishing a bidirectional communication channel between the teacher and the robot, in contrast to works using kinesthetic teaching. Third, we address the well-known what to imitate? problem from a different point of view, based on the mutual information between perceptions and actions. Lastly, the teacher's demonstrations are encoded using a Hidden Markov Model, and the robot execution phase is developed by implementing a modified version of Gaussian Mixture Regression that uses implicit temporal information from the probabilistic model, needed when tackling tasks with ambiguous perceptions. Experimental results show that the robot is able to learn and reproduce two different manipulation tasks, with a performance comparable to the teacher's one.
Robots are becoming safe and smart enough to work alongside people not only on manufacturing prod... more Robots are becoming safe and smart enough to work alongside people not only on manufacturing production lines, but also in spaces such as houses, museums or hospitals. This can be significantly exploited in situations where a human needs the help of another person to perform a task, because a robot may take the role of the helper. In this sense, a human and the robotic assistant may cooperatively carry out a variety of tasks, therefore requiring the robot to communicate with the person, understand his/her needs and behave accordingly. To achieve this, we propose a framework for a user to teach a robot collaborative skills from demonstrations. We mainly focus on tasks involving physical contact with the user, where not only position, but also force sensing and compliance become highly relevant. Specifically, we present an approach that combines probabilistic learning, dynamical systems and stiffness estimation, to encode the robot behavior along the task. Our method allows a robot to learn not only trajectory following skills, but also impedance behaviors. To show the functionality and flexibility of our approach, two different testbeds are used: a transportation task and a collaborative table assembly.
Robot 2019: Fourth Iberian Robotics Conference, Nov 20, 2019
This paper proposes a Social Reward Sources (SRS) design for a Human-Robot Collaborative Navigati... more This paper proposes a Social Reward Sources (SRS) design for a Human-Robot Collaborative Navigation (HRCN) task: humanrobot collaborative search. It is a flexible approach capable of handling the collaborative task, human-robot interaction and environment restrictions, all integrated on a common environment. We modelled task rewards based on unexplored area observability and isolation and evaluated the model through different levels of human-robot communication. The models are validated through quantitative evaluation against both agents' individual performance and qualitative surveying of participants' perception. After that, the three proposed communication levels are compared against each other using the previous metrics.
The textbook on Motion Planning "Principles of Robot Motion: Theory, Algorithms, and Implementati... more The textbook on Motion Planning "Principles of Robot Motion: Theory, Algorithms, and Implementations", by H. Choset et al., MIT Press, appeared on June 2005, is reviewed and compared to other two textbooks on the same subject, from 1991 and 2006 respectively. The groundbreaking developments over the last decade justify the necessity of the newer textbooks, that appear to be complementary, despite some overlap in the contents.
Cloth manipulation by robots is gaining popularity among researchers because of its relevance, ma... more Cloth manipulation by robots is gaining popularity among researchers because of its relevance, mainly (but not only) in domestic and assistive robotics. The required science and technologies begin to be ripe for the challenges posed by the manipulation of soft materials, and many contributions have appeared in the last years. This survey provides a systematic review of existing techniques for the basic perceptual tasks of grasp point localization, state estimation and classification of cloth items, from the perspective of their manipulation by robots. This choice is grounded on the fact that any manipulative action requires to instruct the robot where to grasp, and most garment handling activities depend on the correct recognition of the type to which the particular cloth item belongs and its state. The high inter-and intraclass variability of garments, the continuous nature of the possible deformations of cloth and the evident difficulties in predicting their localization and extension on the garment piece are challenges that have encouraged the researchers to provide a plethora of methods to confront such problems, with some promising results. The present review constitutes for the first time an effort in furnishing a structured framework of these works, with the aim of helping future contributors to gain both insight and perspective on the subject.
Uploads
Papers by Pablo Jiménez