Rapid Concept Learning for Mobile Robots

Concept learning in robotics is an extremely challenging problem: sensory data is often high dimensional, and noisy due to specularities and other irregularities. In this paper, we investigate two general strategies to speed up learning, based on spatial decomposition of the sensory representation, and simultaneous learning of multiple classes using a shared structure. We study two concept learning scenarios: a hallway navigation problem, where the robot has to induce features such as opening or wall. The second task is recycling, where the robot has to learn to recognize objects, such as a trash can. We use a common underlying function approximator in both studies in the form of a feedforward neural network, with several hundred input units and multiple output units. Despite the high degree of freedom afforded by such an approximator, we show the two strategies provide sufficient bias to achieve rapid learning. We provide detailed experimental studies on an actual mobile robot called PAVLOV to illustrate the effectiveness of this approach.     

Rapid Concept Learning for Mobile Robots

Concept learning in robotics is an extremely challenging problem: sensory data is often high-dimensional, and noisy due to specularities and other irregularities. In this paper, we investigate two general strategies to speed up learning, based on spatial decomposition of the sensory representation, and simultaneous learning of multiple classes using a shared structure. We study two concept learning scenarios: a hallway navigation problem, where the robot has to induce features such as opening or wall. The second task is recycling, where the robot has to learn to recognize objects, such as a trash can. We use a common underlying function approximator in both studies in the form of a feedforward neural network, with several hundred input units and multiple output units. Despite the high degree of freedom afforded by such an approximator, we show the two strategies provide sufficient bias to achieve rapid learning. We provide detailed experimental studies on an actual mobile robot called PAVLOV to illustrate the effectiveness of this approach.     

Robot Homing by Exploiting Panoramic Vision

We propose a novel, vision-based method for robot homing, the problem of computing a route so that a robot can return to its initial home position after the execution of an arbitrary prior path. The method assumes that the robot tracks visual features in panoramic views of the environment that it acquires as it moves. By exploiting only angular information regarding the tracked features, a local control strategy moves the robot between two positions, provided that there are at least three features that can be matched in the panoramas acquired at these positions. The strategy is successful when certain geometric constraints on the configuration of the two positions relative to the features are fulfilled. In order to achieve long-range homing, the features trajectories are organized in a visual memory during the execution of the prior path. When homing is initiated, the robot selects Milestone Positions (MPs) on the prior path by exploiting information in its visual memory. The MP selection process aims at picking positions that guarantee the success of the local control strategy between two consecutive MPs. The sequential visit of successive MPs successfully guides the robot even if the visual context in the home position is radically different from the visual context at the position where homing was initiated. Experimental results from a prototype implementation of the method demonstrate that homing can be achieved with high accuracy, independent of the distance traveled by the robot. The contribution of this work is that it shows how a complex navigational task such as homing can be accomplished efficiently, robustly and in real-time by exploiting primitive visual cues. Such cues carry implicit information regarding the 3D structure of the environment. Thus, the computation of explicit range information and the existence of a geometric map are not required.     

Behaviour Synthesis of the Erect Stance for a Biped Control

In this paper we use free fall approach to develop a high level control/command strategy for a bipedal robot called BIPMAN, based on a multi-chain mechanical model with a general control architecture. The strategy is composed of three levels: the Legs and arms level, the Coordinator level and the Supervisor level. The Coordinator level is devoted to controlling leg movements and to ensure the stability of the whole biped. Actually perturbation effects threaten the equilibrium of the human robot and can only be compensated using a dynamic control strategy. This one is based on dynamic stability studies with a center of mass acceleration control and a force distribution on each leg and arm. Free fall in the gravity field is assumed to be deeply involved in the human locomotor control. According to studies of this specific motion through a direct dynamic model,the notion of equilibrium classes is introduced. They allow one to define time intervals in which the biped is able to maintain its posture. This notion is used for the definition of a reconfigurable high level control of the robot.     

Development of an autonomous underwater robot “Twin-Burger” for testing intelligent behaviors in realistic environments

An autonomous underwater robot named Twin-Burger was developed as a versatile test bed to establish the techniques which realize intelligent robot behaviors. The robot was designed to have necessary functions for complex tasks including cooperative task execution with other robots and divers. The first robot Twin-Burger I was completed and launched in November 1992. This paper describes hardware and software systems of the robot. Motion of the robot is controlled by sliding controllers based on simplified equations of motion which are derived from system identification experiments. Tank tests proved that the robot was able to cruise along a commanded path as a sequence of control actions generated by the sliding controllers. The Distributed Vehicle Management Architecture (DVMA) is applied to the robot as an architecture for the control software. Mission execution experiments shows that the Twin-Burger behaves appropriately according to the mission and environmental conditions.     

Sense-controlled flexible robot behavior

The creation of physical behavior by computational means has been approached differently by industrial and artificial intelligence robotics. Industrial robotics, considering fast response of a robot its most important characteristic, has equipped the robot with predefined, specific behavioral trajectories resulting in fast but inflexible behavior. Artificial intelligence robotics, claiming flexibility as the paramount robot feature, has employed inferred behavior whereby the robot itself determines behavioral patterns for tasks based on the robot's general knowledge about a task domain. Response is now flexible, but the response time is commonly badly degraded. This work defines an action propensity skill which generates flexibleand fast behavior. Flexibility is achieved by attaching perceptions in skills to guide behavior; fast response results from the direct activation of skills. The acquisition and generalization of skills happens under the supervision of a human teacher in an advice-taking mode into which the robot shifts from the execution mode after recognizing lacking competence for a given task. This paper defines such skills, describes an implemented skilled robot system, and discusses some simulation results.     

The Complexity of Symmetry-Breaking Formulas

Symmetry-breaking formulas for a constraint-satisfaction problem are satisfied by exactly one member (e.g., the lexicographic leader) from each set of symmetrical points in the search space. Thus, the incorporation of such formulas can accelerate the search for a solution without sacrificing satisfiability. We study the computational complexity of generating lex-leader formulas. We show, even for abelian symmetry groups, that the number of essential clauses in the natural lex-leader formula could be exponential. Furthermore, we show the intractability (NP-hardness) of finding any expression of lex-leadership without reordering the variables, even for elementary abelian groups with orbits of size 3. Nevertheless, using techniques of computational group theory, we describe a reordering relative to which we construct small lex-leader formulas for abelian groups.     

Real-time Collision-free Path Planning of Robot Manipulators using Neural Network Approaches

In this paper, a novel neural network approach to real-time collision-free path planning of robot manipulators in a nonstationary environment is proposed, which is based on a biologically inspired neural network model for dynamic trajectory generation of a point mobile robot. The state space of the proposed neural network is the joint space of the robot manipulators, where the dynamics of each neuron is characterized by a shunting equation or an additive equation. The real-time robot path is planned through the varying neural activity landscape that represents the dynamic environment. The proposed model for robot path planning with safety consideration is capable of planning a real-time comfortable path without suffering from the too close nor too far problems. The model algorithm is computationally efficient. The computational complexity is linearly dependent on the neural network size. The effectiveness and efficiency are demonstrated through simulation studies.     

Robotic Tasks Using Path Control: Two Case Studies

Some robotic tasks usually achieved through motion control – trajectory tracking control – can be also well performed by resorting to path control philosophy. This is the case for applications where motion coordination among the robot joints is more important than joint tracking of a timed desired reference. This paper illustrates this concept by means of two academic case studies – theory and experiments – using a two degrees-of-freedom direct-drive revolute arm.     

Fractal Fitness Landscape and Loss of Robustness in Evolutionary Robot Navigation

An autonomous robot Khepera was simulated with a sensory-motor model, which evolves in the genetic algorithm (GA) framework, with the fitness evaluation in terms of the navigation performance in a maze course. The sensory-motor model is a developed neural network decoded from a graph-represented chromosome, which is evolved in the GA process with several genetic operators.It was found that the fitness landscape is very rugged when it is observed at the starting point of the course. A hypothesis for this ruggedness is proposed, and is supported by the measurement of fractal dimension. It is also observed that the performance is sometimes plagued by Loss of Robustness, after the robot makes major evolutionary jumps. Here, the robustness is quantitatively defined as a ratio of the averaged fitness of the evolved robot navigating in perturbed environments over the fitness of the evolved robot in the referenced environment.Possible explanation of robustness loss is the over-adaptation occurred in the environment where the evolution was taken place. Testing some other possibilities for this loss of robustness, many simulation experiments were conducted which smooth out the discrete factors in the model and environment. It was found that smoothing the discrete factors does not solve the loss of robustness. An effective method for maintaining the robustness is the use of averaged fitness over different navigation conditions.The evolved models in the simulated environment were tested by down-loading the models into the real Khepera robot. It is demonstrated that the tendency of fitness values observed in the simulation were adequately regenerated.     

LAR: A logic of algorithmic reasoning

Summary Reasoning about programs involves some logical framework which seems to go beyond classical predicate logic. LAR is an extension of predicate logic by additional concepts which are to formalize our natural reasoning about algorithms. Semantically, this extension introduces an underlying time scale on which formulas are considered and time shifting connectives. Besides a full model-theoretic treatment, a consistent and complete formal system for LAR is given. The pure logical system can serve as a basis for various theories. As an example, a theory of while program schemes is developed which contains Hoare's correctness proof system.     

Symbolic computation of robot models for geometric parameters identification with singularity analysis

The computation of the geometrical parameters identification model of a robot arm leads to an intrinsic extended Jacobian matrix. This matrix is often singular and its manual computation is tedious and may lead to error. A computer assisted procedure is developed to compute this matrix symbolically and to check its singularity. The program GPIM is developed in Pascal and works on PC's for this purpose. Jacobian singularity is checked using its symbolic expressions with the aid of a proposed table for robot arm parameters to obtain a minimum set of identified parameters. This program can be used for simple chain robot arms having revolute (R) and/or prismatic (P) joints including the case of consecutive near parallel axes. TH8 robot arm of type RPPRRR having two pairs of consecutive near parallel axes is studied to show the program efficiency and how singularity is eliminated.Nomenclature a _i Denavit-Hartenberg parameter. - C _i ,C _i andC ₁₂ cos _i , cos _i and cos ( ₁ + ₂). - J ₀, J Basic Jacobian and Jacobian matrices. - J _a , J _r , J , J and J Sub-Jacobian matrices. - J _0a , J _0r , J ₀, J ₀ and J ₀ Intrinsic sub-Jacobian matrices. - m Work space dimensions. - n Number of moving links of the robot arm. - p Number of pairs of consecutive near parallel axes. - P _i,i+1 and P _li [3×1] position vectors. - Q _pi , Q _ai , Q _ri , Q _i , Q _i and Q _i [4×4] differential operator matrices. - r _i Denavit-Hartenberg parameter. - R _l , R _i , R _i+1 and R _n+1 Base, links i–1, i and n coordinate frames. - R _i,i+1 and R _1i [3×3] orientation matrices. - S _i , S _i and S ₁₂ sin _i , sin _i and sin ₁ + ₂. - T _i,i+1 and T _1i [4×4] homogeneous transformation matrices. - X [m×1] robot arm operational coordinates. - 1st columns of the orientation matrices, and associated tensors. - 2nd columns of the orientation matrices, and associated tensors. - 3rd columns of the orientation matrices, and associated tensors. - _i Denavit-Hartenberg parameter. - _i Twist angle parameter. - X Changes in robot arm operational coordinates. - , ls and rr Changes in robot arm geometrical parameters, and their least square and ridge regression estimated changes. - _i Denavit-Hartenberg parameter. - , ^c and ⁿ Robot geometrical parameters and their correct and nominal values. - pi, ai, ri, i, i and i [4×4] differential operator matrices. - and ^–1 [3×3] conversion matrix and its inverse.     

An efficient steering control formulation for the articulated body mobile robot “KR-II”

This paper introduces an efficient steering control method for the articulated body mobile robot Koryu-II (KR-II). KR-II is a real robot, composed of six cylindrical segments linked in series and has a long snake-like appearance. The main issue on KR-II's steering control is, given from a remote human operator the velocity and orientation commands for the foremost segment, to automatically generate joint commands for all the following segments, such that they follow the foremost segment's trajectory. The derived method is based on a trajectory planning scheme in the inertial reference frame, and is feasible for real time computation. It also presents good energy efficiency and trajectory tracking performance characteristics, and can be extended for KR-II's W-Shaped Configuration steering control, which augments the lateral stability of the robot, essential for locomotion over uneven terrain. The validity of these methods are verified by experiments on the mechanical model KR-II.     

Thiele Rational Interpolation for the Numerical Computation of the Reversible Randles–Sevcik Function in Electrochemistry

This paper uses Thiele rational interpolation to derive a simple method for computing the Randles–Sevcik function ^1/2(x), with relative error at most 1.9 × 10^–5 for – < x < . We develop a piecewise approximation method for the numerical computation of ^1/2(x) on the union (–, –10) [–10, 10] (10, ). This approximation is particularly convenient to employ in electrochemical applications where four significant digits of accuracy are usually sufficient. Although this paper is primarily concerned with the approximation of the Randles–Sevcik function, some examples are included that illustrate how Thiele rational interpolation can be employed to generate useful approximations to other functions of interest in scientific work.     

Revealing Translators' Knowledge: Statistical Methods in Constructing Practical Translation Lexicons for Language and Speech Processing

Parallel corpora encode extremely valuable linguistic knowledge about paired languages, both in terms of vocabulary and syntax. A professional translation of a text represents a series of linguistic decisions made by the translator in order to convey as faithfully as possible the meaning of the original text and to produce a natural text from the perspective of a native speaker of the target language. The naturalness of a translation implies not only the grammaticality of the translated text, but also style and cultural or social specificity.We describe a program that exploits the knowledge embedded in the parallel corpora and produces a set of translation equivalents (a translation lexicon). The program uses almost no linguistic knowledge, relying on statistical evidence and some simplifying assumptions. Our experiments were conducted on the MULTEXT-EAST multilingual parallel corpus (Orwell's 1984), and the evaluation of the system performance is presented in some detail in terms of precision, recall and processing time. We conclude by briefly mentioning some applications of the automatic extracted lexicons for text and speech processing.     

From Conditional Events to Conditional Measures: A New Axiomatic Approach

Our starting point is a definition of conditional event EH which differs from many seemingly similar ones adopted in the relevant literature since 1935, starting with de Finetti. In fact, if we do not assign the same third value u (undetermined) to all conditional events, but make it depend on EH, it turns out that this function t(EH) can be taken as a general conditional uncertainty measure, and we get (through a suitable – in a sense, compulsory – choice of the relevant operations among conditional events) the natural axioms for many different (besides probability) conditional measures.     

Using Real-Time Stereo Vision for Mobile Robot Navigation

This paper describes a working vision-based mobile robot that navigates and autonomously explores its environment while building occupancy grid maps of the environment. We present a method for reducing stereo vision disparity images to two-dimensional map information. Stereo vision has several attributes that set it apart from other sensors more commonly used for occupancy grid mapping. We discuss these attributes, the errors that some of them create, and how to overcome them. We reduce errors by segmenting disparity images based on continuous disparity surfaces to reject spikes caused by stereo mismatches. Stereo vision processing and map updates are done at 5 Hz and the robot moves at speeds of 300 cm/s.     

The role of “craft language” in learning “Waza”

The role of craft language in the process of teaching (learning) Waza (skill) will be discussed from the perspective of human intelligence.It may be said that the ultimate goal of learning Waza in any Japanese traditional performance is not the perfect reproduction of the teaching (learning) process of Waza. In fact, a special metaphorical language (craft language) is used, which has the effect of encouraging the learner to activate his creative imagination. It is through this activity that the he learns his own habitus (Kata).It is suggested that, in considering the difference of function between natural human intelligence and artificial intelligence, attention should be paid to the imaginative activity of the learner as being an essential factor for mastering Kata.This article is a modified English version of Chapter 5 of my bookWaza kara shiru (Learning from Skill), Tokyo University Press, 1987, pp. 93–105.     

States and the free orthogonality monoid

Let (X, #) be an orthogonality space such that the lattice C(X, #) of closed subsets of (X, #) is orthomodular and let (, ) denote the free orthogonality monoid over (X, #). Let C₀(, ) be the subset of C(, ), consisting of all closures of bounded orthogonal sets. We show that C₀(, ) is a suborthomodular lattice of C(, ) and we provide a necessary and sufficient condition for C₀(, ) to carry a full set of dispersion free states.The work of the second author on this paper was supported by National Science Foundation Grant GP-9005.     

A Typology of Translation Problems for Eurotra Translation Machines

This paper presents a detailed study of Eurotra Machine Translation engines, namely the mainstream Eurotra software known as the E-Framework, and two unofficial spin-offs – the C,A,T and Relaxed Compositionality translator notations – with regard to how these systems handle hard cases, and in particular their ability to handle combinations of such problems. In the C,A,T translator notation, some cases of complex transfer are wild, meaning roughly that they interact badly when presented with other complex cases in the same sentence. The effect of this is that each combination of a wild case and another complex case needs ad hoc treatment. The E-Framework is the same as the C,A,T notation in this respect. In general, the E-Framework is equivalent to the C,A,T notation for the task of transfer. The Relaxed Compositionality translator notation is able to handle each wild case (bar one exception) with a single rule even where it appears in the same sentence as other complex cases.