A probabilistic plan recognition algorithm based on plan tree grammars

We present the PHATT algorithm for plan recognition. Unlike previous approaches to plan recognition, PHATT is based on a model of plan execution. We show that this clarifies several difficult issues in plan recognition including the execution of multiple interleaved root goals, partially ordered plans, and failing to observe actions. We present the PHATT algorithm's theoretical basis, and an implementation based on tree structures. We also investigate the algorithm's complexity, both analytically and empirically. Finally, we present PHATT's integrated constraint reasoning for parametrized actions and temporal constraints.     

A Bayesian approach to object detection using probabilistic appearance-based models

In this paper, we introduce a Bayesian approach, inspired by probabilistic principal component analysis (PPCA) (Tipping and Bishop in J Royal Stat Soc Ser B 61(3):611–622, 1999), to detect objects in complex scenes using appearance-based models. The originality of the proposed framework is to explicitly take into account general forms of the underlying distributions, both for the in-eigenspace distribution and for the observation model. The approach combines linear data reduction techniques (to preserve computational efficiency), non-linear constraints on the in-eigenspace distribution (to model complex variabilities) and non-linear (robust) observation models (to cope with clutter, outliers and occlusions). The resulting statistical representation generalises most existing PCA-based models (Tipping and Bishop in J Royal Stat Soc Ser B 61(3):611–622, 1999; Black and Jepson in Int J Comput Vis 26(1):63–84, 1998; Moghaddam and Pentland in IEEE Trans Pattern Anal Machine Intell 19(7):696–710, 1997) and leads to the definition of a new family of non-linear probabilistic detectors. The performance of the approach is assessed using receiver operating characteristic (ROC) analysis on several representative databases, showing a major improvement in detection performances with respect to the standard methods that have been the references up to now.This revised version was published online in November 2004 with corrections to the section numbers.     

A framework for robotic clothing assistance by imitation learning

ABSTRACT

The recent demographic trend across developed nations shows a dramatic increase in the aging population, fallen fertility rates and a shortage of caregivers. Hence, the demand for service robots to assist with dressing which is an essential Activity of Daily Living (ADL) is increasing rapidly. Robotic Clothing Assistance is a challenging task since the robot has to deal with two demanding tasks simultaneously, (a) non-rigid and highly flexible cloth manipulation and (b) safe human–robot interaction while assisting humans whose posture may vary during the task. On the other hand, humans can deal with these tasks rather easily. In this paper, we propose a framework for robotic clothing assistance by imitation learning from a human demonstration to a compliant dual-arm robot. In this framework, we divide the dressing task into three phases, i.e. reaching phase, arm dressing phase, and body dressing phase. We model the arm dressing phase as a global trajectory modification using Dynamic Movement Primitives (DMP), while we model the body dressing phase toward a local trajectory modification applying Bayesian Gaussian Process Latent Variable Model (BGPLVM). We show that the proposed framework developed towards assisting the elderly is generalizable to various people and successfully performs a sleeveless shirt dressing task. We also present participants feedback on public demonstration at the International Robot Exhibition (iREX) 2017. To our knowledge, this is the first work performing a full dressing of a sleeveless shirt on a human subject with a humanoid robot.     

Autonomous generation of reflexion-based robot controller using inductive learning

The paper proposes a novel architecture for autonomously generating and managing a robot control system, aiming for the application to planetary rovers which will move in a partially unknown, unstructured environment. The proposed architecture is similar to the well known subsumption architecture in that the movements are governed by a network of various reflexion patterns. The major departures are that firstly it utilizes inductive learning to automatically generate and modify a control architecture, which is, if human is to do, quite a difficult and time consuming task, secondly it employs the concept of “goal sensor” to deal with the system goal more explicitly, and thirdly it compiles the planning results into a reflexion network and decision trees to maintain the strong features of reflexion based planner such as real-timeness, robustness and extensibility. The architecture has been applied to movement control of a certain rover in computer simulations and simple experiments, in which its effectiveness and characteristics have been cleared.     

A multidimensional approach to syntactic pattern recognition

This paper describes a syntactic method for representing the primitive parts of a pattern as nodes of a type of directed graph. A linear representation of the digraph can then be presented to a regular unordered tree automaton for classification. Regular unordered tree automata can be simulated by deterministic pushdown automata, so this procedure can be implemented easily. Regular u-tree automata and the corresponding generative systems, regular u-tree grammars are formally defined. Several results are shown which are applicable to all syntactic pattern recognition schemes involving the use of primitives.     

An approach to learning mobile robot navigation

This paper describes an approach to learning an indoor robot navigation task through trial-and-error. A mobile robot, equipped with visual, ultrasonic and laser sensors, learns to servo to a designated target object. In less than ten minutes of operation time, the robot is able to navigate to a marked target object in an office environment. The central learning mechanism is the explanation-based neural network learning algorithm (EBNN). EBNN initially learns function purely inductively using neural network representations. With increasing experience, EBNN employs domain knowledge to explain and to analyze training data in order to generalize in a more knowledgeable way. Here EBNN is applied in the context of reinforcement learning, which allows the robot to learn control using dynamic programming.     

Continuous probabilistic model building genetic network programming using reinforcement learning

Recently, a novel probabilistic model-building evolutionary algorithm (so called estimation of distribution algorithm, or EDA), named probabilistic model building genetic network programming (PMBGNP), has been proposed. PMBGNP uses graph structures for its individual representation, which shows higher expression ability than the classical EDAs. Hence, it extends EDAs to solve a range of problems, such as data mining and agent control. This paper is dedicated to propose a continuous version of PMBGNP for continuous optimization in agent control problems. Different from the other continuous EDAs, the proposed algorithm evolves the continuous variables by reinforcement learning (RL). We compare the performance with several state-of-the-art algorithms on a real mobile robot control problem. The results show that the proposed algorithm outperforms the others with statistically significant differences.     

A reasoning-based approach to machine learning

This paper describes a novel approach to machine learning, based on the principle of learning by reasoning. Current learning systems have significant limitations such as brittleness, i.e., the deterioration of performance on a different domain or problem and lack of power required for handling real-world learning problems. The goal of our research was to develop an approach in which many of these limitations are overcome in a unified, coherent and general framework. Our learning approach is based on principles of reasoning, such as the discovery of the underlying principle and the recognition of the deeper basis of similarity, which is somewhat akin to human learning. In this paper, we argue the importance of these principles and tie the limitations of current systems to the lack of application of these principles. We then present the technique developed and illustrate it on a learning problem not directly solvable by previous approaches.     

Adaptive iterative learning control for robot manipulators

In this paper, we propose some adaptive iterative learning control (ILC) schemes for trajectory tracking of rigid robot manipulators, with unknown parameters, performing repetitive tasks. The proposed control schemes are based upon the use of a proportional-derivative (PD) feedback structure, for which an iterative term is added to cope with the unknown parameters and disturbances. The control design is very simple in the sense that the only requirement on the PD and learning gains is the positive definiteness condition and the bounds of the robot parameters are not needed. In contrast to classical ILC schemes where the number of iterative variables is generally equal to the number of control inputs, the second controller proposed in this paper uses just two iterative variables, which is an interesting fact from a practical point of view since it contributes considerably to memory space saving in real-time implementations. We also show that it is possible to use a single iterative variable in the control scheme if some bounds of the system parameters are known. Furthermore, the resetting condition is relaxed to a certain extent for a certain class of reference trajectories. Finally, simulation results are provided to illustrate the effectiveness of the proposed controllers.     

A new approach to hybrid probabilistic logic programs

This paper presents a novel revision of the framework of Hybrid Probabilistic Logic Programming, along with a complete semantics characterization, to enable the encoding of and reasoning about real-world applications. The language of Hybrid Probabilistic Logic Programs framework is extended to allow the use of non-monotonic negation, and two alternative semantical characterizations are defined: stable probabilistic model semantics and probabilistic well-founded semantics. These semantics generalize the stable model semantics and well-founded semantics of traditional normal logic programs, and they reduce to the semantics of Hybrid Probabilistic Logic programs for programs without negation. It is the first time that two different semantics for Hybrid Probabilistic Programs with non-monotonic negation as well as their relationships are described. This proposal provides the foundational grounds for developing computational methods for implementing the proposed semantics. Furthermore, it makes it clearer how to characterize non-monotonic negation in probabilistic logic programming frameworks for commonsense reasoning. An erratum to this article can be found at     

A fault-tolerant approach to robot teams

As the applications of mobile robotics evolve it has become increasingly less practical for researchers to design custom hardware and control systems for each problem. This paper presents a new approach to control system design in order to look beyond end-of-lifecycle performance, and consider control system structure, flexibility, and extensibility. Towards these ends the Control ad libitum philosophy was proposed, stating that to make significant progress in the real-world application of mobile robot teams the control system must be structured such that teams can be formed in real-time from diverse components. The Control ad libitum philosophy was applied to the design of the HAA (Host, Avatar, Agent) architecture: a modular hierarchical framework built with provably correct distributed algorithms. A control system for mapping, exploration, and foraging was developed using the HAA architecture and evaluated in three experiments. First, the basic functionality of the HAA architecture was studied, specifically the ability to: (a) dynamically form the control system, (b) dynamically form the robot team, (c) dynamically form the processing network, and (d) handle heterogeneous teams and allocate robots between tasks based on their capabilities. Secondly, the control system was tested with different rates of software failure and was able to successfully complete its tasks even when each module was set to fail every 0.5–1.5 min. Thirdly, the control system was subjected to concurrent software and hardware failures, and was still able to complete a foraging task in a 216 m² environment.     

A probabilistic fuzzy approach to modeling nonlinear systems

Recently, the study of incorporating probability theory and fuzzy logic has received much interest. To endow the traditional fuzzy rule-based systems (FRBs) with probabilistic features to handle randomness, this paper presents a probabilistic fuzzy neural network (ProFNN) by introducing the probability of input linguistic terms and providing linguistic meaning into the connectionist architecture. ProFNN integrates the probabilistic information of fuzzy rules into the antecedent parts and quantifies the impacts of the rules on the consequent parts using mutual subsethood, which work in conjunction with volume defuzzification in a gradient descent learning frame work. Despite the increase in the number of parameters, ProFNN provides a promising solution to deal with randomness and fuzziness in a single frame. To evaluate the performance and applicability of the proposed approach, ProFNN is carried out on various benchmarking problems and compared with other existing models with a performance better than most of them.     

Planning to see: A hierarchical approach to planning visual actions on a robot using POMDPs

Flexible, general-purpose robots need to autonomously tailor their sensing and information processing to the task at hand. We pose this challenge as the task of planning under uncertainty. In our domain, the goal is to plan a sequence of visual operators to apply on regions of interest (ROIs) in images of a scene, so that a human and a robot can jointly manipulate and converse about objects on a tabletop. We pose visual processing management as an instance of probabilistic sequential decision making, and specifically as a Partially Observable Markov Decision Process (POMDP). The POMDP formulation uses models that quantitatively capture the unreliability of the operators and enable a robot to reason precisely about the trade-offs between plan reliability and plan execution time. Since planning in practical-sized POMDPs is intractable, we partially ameliorate this intractability for visual processing by defining a novel hierarchical POMDP based on the cognitive requirements of the corresponding planning task. We compare our hierarchical POMDP planning system (HiPPo) with a non-hierarchical POMDP formulation and the Continual Planning (CP) framework that handles uncertainty in a qualitative manner. We show empirically that HiPPo and CP outperform the naive application of all visual operators on all ROIs. The key result is that the POMDP methods produce more robust plans than CP or the naive visual processing. In summary, visual processing problems represent a challenging domain for planning techniques and our hierarchical POMDP-based approach for visual processing management opens up a promising new line of research.     

Further results on adaptive iterative learning control of robot manipulators

Based on a combination of a PD controller and a switching type two-parameter compensation force, an iterative learning controller with a projection-free adaptive algorithm is presented in this paper for repetitive control of uncertain robot manipulators. The adaptive iterative learning controller is designed without any a priori knowledge of robot parameters under certain properties on the dynamics of robot manipulators with revolute joints only. This new adaptive algorithm uses a combined time-domain and iteration-domain adaptation law allowing to guarantee the boundedness of the tracking error and the control input, in the sense of the infinity norm, as well as the convergence of the tracking error to zero, without any a priori knowledge of robot parameters. Simulation results are provided to illustrate the effectiveness of the learning controller.     

Categorical approach to the construction of fuzzy graph grammars

The categorical approach is proposed to the formalization of fuzzy graph grammars obtained as a result of generalization of sequential graph grammars. This approach takes into consideration the basic types of fuzziness that arise in constructing categories of fuzzy objects and describing transformations of fuzzy graphs generated by fuzzy sets. All the problems of undecidability that are well known for Chomsky grammars are proved to hold true for fuzzy graph grammars. __________ Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 130–144, July–August 2006.     

A robust approach to robot team learning

The paper achieves two outcomes. First, it summarizes previous work on concurrent Markov decision processes (CMDPs) currently demonstrated for use with multi-agent foraging problems. When using CMDPs, each agent models the environment using two Markov decision process (MDP). The two MDPs characterize a multi-agent foraging problem by modeling both a single-agent foraging problem, and multi-agent task allocation problem, for each agent. Second, the paper studies the effects of state uncertainty on a heterogeneous robot team that utilizes the aforementioned CMDP modelling approach. Furthermore, the paper presents a method to maintain performance despite state uncertainty. The resulting robust concurrent individual and social learning (RCISL) mechanism leads to an enhanced team learning behaviour despite state uncertainty. The paper analyzes the performance of the concurrent individual and social learning mechanism with and without a particle filter for a heterogeneous foraging scenario. The RCISL mechanism confers statistically significant performance improvements over the CISL mechanism.     

A visual tool for computer supported learning: The robot motion planning example

We introduce an effective computer aided learning visual tool (CALVT) to teach graph-based applications. We present the robot motion planning problem as an example of such applications. The proposed tool can be used to simulate and/or further to implement practical systems in different areas of computer science such as graphics, computational geometry, robotics and networking. In the robot motion planning example, CALVT enables users to setup the working environment by creating obstacles and a robot of different shapes, specifying starting and goal positions, and setting other path or environment parameters from a user-friendly interface. The path planning system involves several phases. Each of these modules is complex and therefore we provide the possibility of visualizing graphically the output of each phase. Based on our experience, this tool has been an effective one in classroom teaching. It not only cuts down, significantly, on the instructor’s time and effort but also motivates senior/graduate students to pursue work in this specific area of research.     

Incremental online sparsification for model learning in real-time robot control

For many applications such as compliant, accurate robot tracking control, dynamics models learned from data can help to achieve both compliant control performance as well as high tracking quality. Online learning of these dynamics models allows the robot controller to adapt itself to changes in the dynamics (e.g., due to time-variant nonlinearities or unforeseen loads). However, online learning in real-time applications - as required in control - cannot be realized by straightforward usage of off-the-shelf machine learning methods such as Gaussian process regression or support vector regression. In this paper, we propose a framework for online, incremental sparsification with a fixed budget designed for fast real-time model learning. The proposed approach employs a sparsification method based on an independence measure. In combination with an incremental learning approach such as incremental Gaussian process regression, we obtain a model approximation method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques. Implementation on a real Barrett WAM robot demonstrates the applicability of the approach in real-time online model learning for real world systems.     

Computational intelligence for structured learning of a partner robot based on imitation

Imitation is a powerful tool for gestural interaction between children and for teaching behaviors to children by parent. Furthermore, others’ action can be a hint for acquiring a new behavior that might not be the same as the original action. The importance is how to map or represent others’ action into new one in the internal state space. A good instructor can teach an action to a learner by understanding the mapping or imitating method of the learner. This indicates a robot also can acquire various behaviors using interactive learning based on imitation. This paper proposes structured learning for a partner robot based on the interactive teaching mechanism. The proposed method is composed of a spiking neural network, self-organizing map, steady-state genetic algorithm, and softmax action selection. Furthermore, we discuss the interactive learning of a human and a partner robot based on the proposed method through experiment results.