Learning,goals, and learning goals: A perspective on goal-driven learning

In cognitive science, artificial intelligence, psychology, and education, a growing body of research supports the view that the learning process is strongly influenced by the learner's goals. The fundamental tenet ofgoal-driven learning is that learning is largely an active and strategic process in which the learner, human or machine, attempts to identify and satisfy its information needs in the context of its tasks and goals, its prior knowledge, its capabilities, and environmental opportunities for learning. This article examines the motivations for adopting a goal-driven model of learning, the relationship between task goals and learning goals, the influences goals can have on learning, and the pragmatic implications of the goal-driven learning model. It presents a new integrative framework for understanding the goal-driven learning process and applies this framework to characterizing research on goal-driven learning.     

A survey of robot learning from demonstration

We present a comprehensive survey of robot Learning from Demonstration (LfD), a technique that develops policies from example state to action mappings. We introduce the LfD design choices in terms of demonstrator, problem space, policy derivation and performance, and contribute the foundations for a structure in which to categorize LfD research. Specifically, we analyze and categorize the multiple ways in which examples are gathered, ranging from teleoperation to imitation, as well as the various techniques for policy derivation, including matching functions, dynamics models and plans. To conclude we discuss LfD limitations and related promising areas for future research.     

Simultaneously learning to recognize and control a low-cost robotic arm

In this paper, we present a visual servoing method based on a learned mapping between feature space and control space. Using a suitable recognition algorithm, we present and evaluate a complete method that simultaneously learns the appearance and control of a low-cost robotic arm. The recognition part is trained using an action precedes perception approach. The novelty of this paper, apart from the visual servoing method per se, is the combination of visual servoing with gripper recognition. We show that we can achieve high precision positioning without knowing in advance what the robotic arm looks like or how it is controlled.     

A modular approach to learning manipulation strategies from human demonstration

Object manipulation is a challenging task for robotics, as the physics involved in object interaction is complex and hard to express analytically. Here we introduce a modular approach for learning a manipulation strategy from human demonstration. Firstly we record a human performing a task that requires an adaptive control strategy in different conditions, i.e. different task contexts. We then perform modular decomposition of the control strategy, using phases of the recorded actions to guide segmentation. Each module represents a part of the strategy, encoded as a pair of forward and inverse models. All modules contribute to the final control policy; their recommendations are integrated via a system of weighting based on their own estimated error in the current task context. We validate our approach by demonstrating it, both in a simulation for clarity, and on a real robot platform to demonstrate robustness and capacity to generalise. The robot task is opening bottle caps. We show that our approach can modularize an adaptive control strategy and generate appropriate motor commands for the robot to accomplish the complete task, even for novel bottles.     

Bagging for Gaussian mixture regression in robot learning from demonstration

Journal of Intelligent Manufacturing - Robot learning from demonstration (LfD) emerges as a promising solution to transfer human motion to the robot. However, because of the open-loop between the...     

A robot learning from demonstration framework to perform force-based manipulation tasks

This paper proposes an end-to-end learning from demonstration framework for teaching force-based manipulation tasks to robots. The strengths of this work are manyfold. 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 the 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.     

Continuous control actions learning and adaptation for robotic manipulation through reinforcement learning

Autonomous Robots - This paper presents a learning-based method that uses simulation data to learn an object manipulation task using two model-free reinforcement learning (RL) algorithms. The...     

Principles and experimentations of self-organizing embedded agents allowing learning from demonstration in ambient robotics

Ambient systems are populated by many heterogeneous devices to provide adequate services to their users. The adaptation of an ambient system to the specific needs of its users is a challenging task. Because human–system interaction has to be as natural as possible, we propose an approach based on Learning from Demonstration (LfD). LfD is an interesting approach to generalize what has been observed during the demonstration to similar situations. However, using LfD in ambient systems needs adaptivity of the learning technique. We present ALEX, a multi-agent system able to dynamically learn and reuse contexts from demonstrations performed by a tutor. The results of the experiments performed on both a real and a virtual robot show interesting properties of our technology for ambient applications.     

Linking learning goals and educational resources through interactive concept map visualizations

Concept browsing interfaces can help educators and learners to locate and use learning resources that are aligned with recognized learning goals. The Strand Map Service enables users to navigate interactive visualizations of related learning goals and to request digital library resources aligned with learning goals. These interfaces are created using a programmatic Web service interface that dynamically generates interactive visual components. Preliminary findings suggest that these library interfaces appear to help users stay focused on the scientific content of their information discovery task, as opposed to focusing on the mechanics of searching.     

The use of explicit goals for knowledge to guide inference and learning

Combinatorial explosion of inferences has always been a central problem in artificial intelligence. Although the inferences that can be drawn from a reasoner's knowledge and from available inputs is very large (potentially infinite), the inferential resources available to any reasoning system are limited. With limited inferential capacity and very many potential inferences, reasoners must somehow control the process of inference. Not all inferences are equally useful to a given reasoning system. Any reasoning system that has goals (or any form of a utility function) and acts based on its beliefs indirectly assigns utility to its beliefs. Given limits on the process of inference, and variation in the utility of inferences, it is clear that a reasoner ought to draw the inferences that will be most valuable to it. This paper presents an approach to this problem that makes the utility of a (potential) belief an explicit part of the inference process. The method is to generate explicit desires for knowledge. The question of focus of attention is thereby transformed into two related problems: How can explicit desires for knowledge be used to control inference and facilitate resource-constrained goal pursuit in general? and, Where do these desires for knowledge come from? We present a theory of knowledge goals, or desires for knowledge, and their use in the processes of understanding and learning. The theory is illustrated using two case studies, a natural language understanding program that learns by reading novel or unusual newspaper stories, and a differential diagnosis program that improves its accuracy with experience.     

一种结合演示数据和演化优化的强化学习方法

强化学习研究智能体如何从与环境的交互中学习最优的策略,以最大化长期奖赏。由于环境反馈的滞后性,强化学习问题面临巨大的决策空间,进行有效的搜索是获得成功学习的关键。以往的研究从多个角度对策略的搜索进行了探索,在搜索算法方面,研究结果表明基于演化优化的直接策略搜索方法能够获得优于传统方法的性能;在引入外部信息方面,通过加入用户提供的演示,可以有效帮助强化学习提高性能。然而,这两种有效方法的结合却鲜有研究。对用户演示与演化优化的结合进行研究,提出iNEAT+Q算法,尝试将演示数据通过预训练神经网络和引导演化优化的适应值函数的方式与演化强化学习方法结合。初步实验表明,iNEAT+Q较不使用演示数据的演化强化学习方法NEAT+Q有明显的性能改善。     

Recognizing human actions by learning and matching shape-motion prototype trees

A shape-motion prototype-based approach is introduced for action recognition. The approach represents an action as a sequence of prototypes for efficient and flexible action matching in long video sequences. During training, an action prototype tree is learned in a joint shape and motion space via hierarchical K-means clustering and each training sequence is represented as a labeled prototype sequence; then a look-up table of prototype-to-prototype distances is generated. During testing, based on a joint probability model of the actor location and action prototype, the actor is tracked while a frame-to-prototype correspondence is established by maximizing the joint probability, which is efficiently performed by searching the learned prototype tree; then actions are recognized using dynamic prototype sequence matching. Distance measures used for sequence matching are rapidly obtained by look-up table indexing, which is an order of magnitude faster than brute-force computation of frame-to-frame distances. Our approach enables robust action matching in challenging situations (such as moving cameras, dynamic backgrounds) and allows automatic alignment of action sequences. Experimental results demonstrate that our approach achieves recognition rates of 92.86 percent on a large gesture data set (with dynamic backgrounds), 100 percent on the Weizmann action data set, 95.77 percent on the KTH action data set, 88 percent on the UCF sports data set, and 87.27 percent on the CMU action data set.     

Neural network learning from demonstration and epipolar geometry for visual control of a nonholonomic mobile robot

The control of a robot system using camera information is a challenging task regarding unpredictable conditions, such as feature point mismatch and changing scene illumination. This paper presents a solution for the visual control of a nonholonomic mobile robot in demanding real world circumstances based on machine learning techniques. A novel intelligent approach for mobile robots using neural networks (NNs), learning from demonstration (LfD) framework, and epipolar geometry between two views is proposed and evaluated in a series of experiments. A direct mapping from the image space to the actuator command is conducted using two phases. In an offline phase, NN–LfD approach is employed in order to relate the feature position in the image plane with the angular velocity for lateral motion correction. An online phase refers to a switching vision based scheme between the epipole based linear velocity controller and NN–LfD based angular velocity controller, which selection depends on the feature distance from the pre-defined interest area in the image. In total, 18 architectures and 6 learning algorithms are tested in order to find optimal solution for robot control. The best training outcomes for each learning algorithms are then employed in real time so as to discover optimal NN configuration for robot orientation correction. Experiments conducted on a nonholonomic mobile robot in a structured indoor environment confirm an excellent performance with respect to the system robustness and positioning accuracy in the desired location.     

A nonparametric Bayesian approach toward robot learning by demonstration

In the past years, many authors have considered application of machine learning methodologies to effect robot learning by demonstration. Gaussian mixture regression (GMR) is one of the most successful methodologies used for this purpose. A major limitation of GMR models concerns automatic selection of the proper number of model states, i.e., the number of model component densities. Existing methods, including likelihood- or entropy-based criteria, usually tend to yield noisy model size estimates while imposing heavy computational requirements. Recently, Dirichlet process (infinite) mixture models have emerged in the cornerstone of nonparametric Bayesian statistics as promising candidates for clustering applications where the number of clusters is unknown a priori. Under this motivation, to resolve the aforementioned issues of GMR-based methods for robot learning by demonstration, in this paper we introduce a nonparametric Bayesian formulation for the GMR model, the Dirichlet process GMR model. We derive an efficient variational Bayesian inference algorithm for the proposed model, and we experimentally investigate its efficacy as a robot learning by demonstration methodology, considering a number of demanding robot learning by demonstration scenarios.     

A morphable template framework for robot learning by demonstration: Integrating one-shot and incremental learning approaches

Robot learning by demonstration is key to bringing robots into daily social environments to interact with and learn from human and other agents. However, teaching a robot to acquire new knowledge is a tedious and repetitive process and often restrictive to a specific setup of the environment. We propose a template-based learning framework for robot learning by demonstration to address both generalisation and adaptability. This novel framework is based upon a one-shot learning model integrated with spectral clustering and an online learning model to learn and adapt actions in similar scenarios. A set of statistical experiments is used to benchmark the framework components and shows that this approach requires no extensive training for generalisation and can adapt to environmental changes flexibly. Two real-world applications of an iCub humanoid robot playing the tic-tac-toe game and soldering a circuit board are used to demonstrate the relative merits of the framework.     

Fuzzy fusion for attending and responding assessment system of affective teaching goals in distance learning

Teachers can handle learning situations during activities in peer-to-peer classes, and assess student achievements associated with teaching goals in the affective domain. In distance learning, teachers cannot directly observe student states and assess achievement concurrently. Many distance education studies adopted frequency of interaction as the basis of student participation when assessing the student achievements in class. However, the number of times a student interacts is not equal to discussion quality. Although synchronous discussions during class can help teachers assess learning states, these discussions are not suited to all courses. If a teacher can supervise student images from computer’s webcam and observe student status, the teacher can assess achievement accurately. Image processing technology can be applied in an assessment system in distance learning, student states can be observed and these observational results can be combined with behavior detection to help teachers assess student achievement in terms of teaching goals in the affective domain.This study had analyzed the theory and method of assessing affective domain teaching goals. The assessment system had been implemented and simulated using image processing technology and records to analyze student achievement of attending and responding stages with a class period, via fuzzy logic and a fuzzy integral. Simulation results indicate that this assessment system can accurately assess student achievement in terms of attending and responding stages of affective domain teaching goals.     

Building actions from classification rules

Rule induction has attracted a great deal of attention in Machine Learning and Data Mining. However, generating rules is not an end in itself because their applicability is not straightforward especially when their number is large. Ideally, the ultimate user would like to use these rules to decide which actions to undertake. In the literature, this notion is usually referred to as actionability. We propose a new framework to address actionability. Our goal is to lighten the burden of analyzing a large set of classification rules when the user is confronted to an “unsatisfactory situation” and needs help to decide about the appropriate actions to remedy to this situation. The method consists in comparing the situation to a set of classification rules. For this purpose, we propose   a new framework for learning action recommendations dealing with complex notions of feasibility and quality of actions. Our approach has been motivated by an environmental application aiming at building a tool to help specialists in charge of the management of a catchment to preserve stream-water quality. The results show the utility of this methodology with regard to enhancing the actionability of a set of classification rules in a real-world application.