Author Archives: Juan-antonio Fernández-madrigal

Mental imaginery for a mobile robot that learns obstacle avoidance

February 10, 2015 16:58 ,

Wilmer Gaona, Esaú Escobar, Jorge Hermosillo, Bruno Lara (2015), Anticipation by multi-modal association through an artificial mental imagery process, Connection Science, 27:1, 68-88, DOI: 10.1080/09540091.2014.95628

Mental imagery has become a central issue in research laboratories seeking to emulate basic cognitive abilities in artificial agents. In this work, we propose a computational model to produce an anticipatory behaviour by means of a multi-modal off-line hebbian association. Unlike the current state of the art, we propose to apply hebbian learning during an internal sensorimotor simulation, emulating a process of mental imagery. We associate visual and tactile stimuli re-enacted by a long-term predictive simulation chain motivated by covert actions. As a result, we obtain a neural network which provides a robot with a mechanism to produce a visually conditioned obstacle avoidance behaviour. We developed our system in a physical Pioneer 3-DX robot and realised two experiments. In the first experiment we test our model on one individual navigating in two different mazes. In the second experiment we assess the robustness of the model by testing in a single environment five individuals trained under different conditions. We believe that our work offers an underpinning mechanism in cognitive robotics for the study of motor control strategies based on internal simulations. These strategies can be seen analogous to the mental imagery process known in humans, opening thus interesting pathways to the construction of upper-level grounded cognitive abilities.

Posted in: Developmental robotics , Tagged: ,

Active exploration strategy for RL in robots, and approximation of value function by Gaussian processes

February 10, 2015 16:49 ,

Jen Jen Chung, Nicholas R.J. Lawrance, Salah Sukkarieh (2015), Learning to soar: Resource-constrained exploration in reinforcement learning, The International Journal of Robotics Research vol. 34, pp. 158-172. DOI: 10.1177/0278364914553683

This paper examines temporal difference reinforcement learning with adaptive and directed exploration for resource-limited missions. The scenario considered is that of an unpowered aerial glider learning to perform energy-gaining flight trajectories in a thermal updraft. The presented algorithm, eGP-SARSA(\u03bb), uses a Gaussian process regression model to estimate the value function in a reinforcement learning framework. The Gaussian process also provides a variance on these estimates that is used to measure the contribution of future observations to the Gaussian process value function model in terms of information gain. To avoid myopic exploration we developed a resource-weighted objective function that combines an estimate of the future information gain using an action rollout with the estimated value function to generate directed explorative action sequences. A number of modifications and computational speed-ups to the algorithm are presented along with a standard GP-SARSA(\u03bb) implementation with Formula -greedy exploration to compare the respective learning performances. The results show that under this objective function, the learning agent is able to continue exploring for better state-action trajectories when platform energy is high and follow conservative energy-gaining trajectories when platform energy is low.

Posted in: Applications of reinforcement learning to robots , Tagged: , ,

Abstracting and representing tasks performed under Learning from Demonstration, using bayesian non-parametric time-series analysis (good review of both LfD and HMMs for time-series)

February 10, 2015 16:37 ,

Scott Niekum, Sarah Osentoski, George Konidaris, Sachin Chitta, Bhaskara Marthi, Andrew G. Barto (2015), Learning grounded finite-state representations from unstructured demonstrations, The International Journal of Robotics Research, vol. 34, pp. 131-157. DOI: 10.1177/0278364914554471

Robots exhibit flexible behavior largely in proportion to their degree of knowledge about the world. Such knowledge is often meticulously hand-coded for a narrow class of tasks, limiting the scope of possible robot competencies. Thus, the primary limiting factor of robot capabilities is often not the physical attributes of the robot, but the limited time and skill of expert programmers. One way to deal with the vast number of situations and environments that robots face outside the laboratory is to provide users with simple methods for programming robots that do not require the skill of an expert. For this reason, learning from demonstration (LfD) has become a popular alternative to traditional robot programming methods, aiming to provide a natural mechanism for quickly teaching robots. By simply showing a robot how to perform a task, users can easily demonstrate new tasks as needed, without any special knowledge about the robot. Unfortunately, LfD often yields little knowledge about the world, and thus lacks robust generalization capabilities, especially for complex, multi-step tasks. We present a series of algorithms that draw from recent advances in Bayesian non-parametric statistics and control theory to automatically detect and leverage repeated structure at multiple levels of abstraction in demonstration data. The discovery of repeated structure provides critical insights into task invariants, features of importance, high-level task structure, and appropriate skills for the task. This culminates in the discovery of a finite-state representation of the task, composed of grounded skills that are flexible and reusable, providing robust generalization and transfer in complex, multi-step robotic tasks. These algorithms are tested and evaluated using a PR2 mobile manipulator, showing success on several complex real-world tasks, such as furniture assembly.

Posted in: Learning from Demonstration , Tagged: , ,

Scientific limitations to the non-scientific idea that super-intelligence will come (for exterminating humans)

January 23, 2015 20:00 ,

Ernest Davis, Ethical guidelines for a superintelligence, Artificial Intelligence, Volume 220, March 2015, Pages 121-124, ISSN 0004-3702, DOI: 10.1016/j.artint.2014.12.003.

Nick Bostrom, in his new book SuperIntelligence, argues that the creation of an artificial intelligence with human-level intelligence will be followed fairly soon by the existence of an almost omnipotent superintelligence, with consequences that may well be disastrous for humanity. He considers that it is therefore a top priority for mankind to figure out how to imbue such a superintelligence with a sense of morality; however, he considers that this task is very difficult. I discuss a number of flaws in his analysis, particularly the viewpoint that implementing ethical behavior is an especially difficult problem in AI research.

Posted in: Artificial Intelligence , Tagged: ,

Solving the problem of the slow learning rate of reinfocerment learning through the acquisition of the transition model from the data

January 23, 2015 18:03 ,

Deisenroth, M.P.; Fox, D.; Rasmussen, C.E., Gaussian Processes for Data-Efficient Learning in Robotics and Control, Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol.37, no.2, pp.408,423, Feb. 2015, DOI: 10.1109/TPAMI.2013.218

Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system to learn controllers, which is a practical limitation in real systems, such as robots, where many interactions can be impractical and time consuming. To address this problem, current learning approaches typically require task-specific knowledge in form of expert demonstrations, realistic simulators, pre-shaped policies, or specific knowledge about the underlying dynamics. In this paper, we follow a different approach and speed up learning by extracting more information from data. In particular, we learn a probabilistic, non-parametric Gaussian process transition model of the system. By explicitly incorporating model uncertainty into long-term planning and controller learning our approach reduces the effects of model errors, a key problem in model-based learning. Compared to state-of-the art RL our model-based policy search method achieves an unprecedented speed of learning. We demonstrate its applicability to autonomous learning in real robot and control tasks.

Posted in: Applications of reinforcement learning to robots , Tagged: ,

Partially observable reinforcement learning and the problem of representing the history of the learning process efficiently

January 23, 2015 17:58 ,

Doshi-Velez, F.; Pfau, D.; Wood, F.; Roy, N., Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning, Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol.37, no.2, pp.394,407, Feb. 2015, DOI: 10.1109/TPAMI.2013.191

Making intelligent decisions from incomplete information is critical in many applications: for example, robots must choose actions based on imperfect sensors, and speech-based interfaces must infer a user\u2019s needs from noisy microphone inputs. What makes these tasks hard is that often we do not have a natural representation with which to model the domain and use for choosing actions; we must learn about the domain\u2019s properties while simultaneously performing the task. Learning a representation also involves trade-offs between modeling the data that we have seen previously and being able to make predictions about new data. This article explores learning representations of stochastic systems using Bayesian nonparametric statistics. Bayesian nonparametric methods allow the sophistication of a representation to scale gracefully with the complexity in the data. Our main contribution is a careful empirical evaluation of how representations learned using Bayesian nonparametric methods compare to other standard learning approaches, especially in support of planning and control. We show that the Bayesian aspects of the methods result in achieving state-of-the-art performance in decision making with relatively few samples, while the nonparametric aspects often result in fewer computations. These results hold across a variety of different techniques for choosing actions given a representation.

Posted in: Reinforcement learning theory , Tagged: ,

Mathematical model of quartz crystal clocks and Kalman Filter estimation for clock synchronization

January 23, 2015 17:46 ,

Giorgi, G., An Event-Based Kalman Filter for Clock Synchronization, Instrumentation and Measurement, IEEE Transactions on , vol.64, no.2, pp.449,457, Feb. 2015, DOI: 10.1109/TIM.2014.2340631

The distribution of a time reference has long been a significant research topic in measurement and different solutions have been proposed over the years. In this context, the design of servo clocks plays an important role to get better performances by smoothing the influence of noise sources affecting a synchronization system. A servo clock is asked to provide an adaptive and conservative measure of the time distance between the local clock and the time reference by minimizing, if possible, the energy consumption. In this paper, we propose a servo clock based on an efficient implementation of the Kalman filter (KF), called in the following event-based KF that allows to overcome drawbacks of existing KF-based servo clocks with furthermore a significant reduction of the computational cost. An in-depth analysis of the synchronization uncertainty has been reported to completely characterize the proposed solution; and finally, some guidelines on how to correctly initialize the KF are provided.

Posted in: Networked telerobots , Tagged: ,

Estimating an empirical distribution from a number of estimates distributed among several agents, minimizing the information exchange between the agents

January 23, 2015 17:25 ,

Sarwate, A.D.; Javidi, T., Distributed Learning of Distributions via Social Sampling, Automatic Control, IEEE Transactions on , vol.60, no.1, pp.34,45, Jan. 2015, DOI: 10.1109/TAC.2014.2329611

A protocol for distributed estimation of discrete distributions is proposed. Each agent begins with a single sample from the distribution, and the goal is to learn the empirical distribution of the samples. The protocol is based on a simple message-passing model motivated by communication in social networks. Agents sample a message randomly from their current estimates of the distribution, resulting in a protocol with quantized messages. Using tools from stochastic approximation, the algorithm is shown to converge almost surely. Examples illustrate three regimes with different consensus phenomena. Simulations demonstrate this convergence and give some insight into the effect of network topology.

Posted in: Probability and statistics , Tagged:

How to bypass the NP-hardness of estimating the best explanation of given data (instantiated as MAP, i.e., Maximum A Posteriori, not as maximum likelihood) in discrete Bayesian Networks, through distinction of relevant and irrelevant variables

January 23, 2015 17:15 ,

Johan Kwisthout, Most frugal explanations in Bayesian networks, Artificial Intelligence, Volume 218, January 2015, Pages 56-73, ISSN 0004-3702, DOI: 10.1016/j.artint.2014.10.001

Inferring the most probable explanation to a set of variables, given a partial observation of the remaining variables, is one of the canonical computational problems in Bayesian networks, with widespread applications in AI and beyond. This problem, known as MAP, is computationally intractable (NP-hard) and remains so even when only an approximate solution is sought. We propose a heuristic formulation of the MAP problem, denoted as Inference to the Most Frugal Explanation (MFE), based on the observation that many intermediate variables (that are neither observed nor to be explained) are irrelevant with respect to the outcome of the explanatory process. An explanation based on few samples (often even a singleton sample) from these irrelevant variables is typically almost as good as an explanation based on (the computationally costly) marginalization over these variables. We show that while MFE is computationally intractable in general (as is MAP), it can be tractably approximated under plausible situational constraints, and its inferences are fairly robust with respect to which intermediate variables are considered to be relevant.

Posted in: Artificial Intelligence , Tagged: , ,

On search as a consequence of the exploration-exploitation trade-off, and as a core element in human cognition

January 23, 2015 16:58 ,

Thomas T. Hills, Peter M. Todd, David Lazer, A. David Redish, Iain D. Couzin, the Cognitive Search Research Group, Exploration versus exploitation in space, mind, and society, Trends in Cognitive Sciences, Volume 19, Issue 1, January 2015, Pages 46-54, ISSN 1364-6613, DOI: 10.1016/j.tics.2014.10.004.

Search is a ubiquitous property of life. Although diverse domains have worked on search problems largely in isolation, recent trends across disciplines indicate that the formal properties of these problems share similar structures and, often, similar solutions. Moreover, internal search (e.g., memory search) shows similar characteristics to external search (e.g., spatial foraging), including shared neural mechanisms consistent with a common evolutionary origin across species. Search problems and their solutions also scale from individuals to societies, underlying and constraining problem solving, memory, information search, and scientific and cultural innovation. In summary, search represents a core feature of cognition, with a vast influence on its evolution and processes across contexts and requiring input from multiple domains to understand its implications and scope.

Posted in: Psycho-physiological bases of engineering , Tagged: , ,