Informatics Report Series: Recent submissions
Now showing items 120 of 53

Computational mechanisms for action selection
(The University of Edinburgh, 1993)Imagine a zebra in the African savannah. At each moment in time this zebra has to weigh up alternative courses of action before deciding which will be most beneficial to it. For instance, it may want to graze because it ... 
Robot dynamics algorithms
(The University of Edinburgh, 1984)In this dissertation I introduce a new notation for representing rigidbody dynamics, and use it to describe a number of methods for calculating robot dynamics efficiently. The notation (called spatial notation) is based ... 
The Polyadic piCalculus: A Tutorial
(The University of Edinburgh, 1991)The picalculus is a model of concurrent computation based upon the notion of naming. It is first presented in its simplest and original form, with the help of several illustrative applications. Then it is generalized from ... 
Value Function Approximation on NonLinear Manifolds for Robot Motor Control
(IEEE, 200704)The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, ... 
Reinforcement Learning for Humanoid Robots  Policy Gradients and Beyond
(200407)Reinforcement learning offers one of the most general frameworks to take traditional robotics towards true autonomy and versatility. However, applying reinforcement learning to high dimensional movement systems like ... 
Reconstructing Nullspace Policies Subject to Dynamic Task Constraints in Redundant Manipulators
(2007)We consider the problem of direct policy learning in situations where the policies are only observable through their projections into the nullspace of a set of dynamic, nonlinear task constraints. We tackle the issue ... 
LWPR: A Scalable Method for Incremental Online Learning in High Dimensions
(200506)Locally weighted projection regression (LWPR) is a new algorithm for incremental nonlinear func tion approximation in high dimensional spaces with redundant and irrelevant input dimensions. At its core, it employs ... 
Context Estimation and Learning Control through Latent Variable Extraction: From discrete to continuous contexts
(IEEE, 200704)Recent advances in machine learning and adaptive motor control have enabled efficient techniques for online learning of stationary plant dynamics and it's use for robust predictive control. However, in realistic domains, ... 
Implications of different classes of sensorimotor disturbance for cerebellarbased motor learning models
(Springer, 2009)The exact role of the cerebellum in motor control and learning is not yet fully understood. The structure, connectivity and plasticity within cerebellar cortex has been extensively studied, but the patterns of connectivity ... 
Synthesising Novel Movements through Latent Space Modulation of Scalable Control Policies
(SpringerVerlag, 2008)We propose a novel methodology for learning and synthesising whole classes of high dimensional movements from a limited set of demonstrated examples that satisfy some underlying ’latent’ low dimensional task constraints. ... 
Animal learning models as robot controllers
(The University of Edinburgh, 2000)Robots can do a range of wonderful things, but they can also appear really stupid. I would like my autonomous, sensorrich, robot to be able to: complete its task whenever possible, despite distractions and disabilities; ... 
Design and Implementation of an Online Auction
(The University of Edinburgh, 2000)This dissertation reports on the design and implementation of a distributed application that hosts online auctions. The system is implemented using Java and CORBA. Special care has been taken to make it secure, flexible, ... 
Resolving References to Graphical Objects in Multimodal Queries by Constraint Satisfaction
(The University of Edinburgh, 2000)In natural language queries to an intelligent multimodal system, ambiguities related to referring expressions  source ambiguities  can occur between items in the visual display and objects in the domain being represented. ... 
Frame: An Imperative Coordination Language for Parallel Programming
(The University of Edinburgh, 2000)We present Frame, a simple language which facilitates structured expression of imperative parallelism. Programs are described at two levels. The top level captures the main parallel algorithmic structure (which may be ... 
A Web Based Replayer For Proof General
(The University of Edinburgh, 2000)Proof General is a generic interface for proof assistants, based on Emacs. It has been developed at the LFCS in the University of Edinburgh. One of the nice features of Proof General is that it is very easy to replay ... 
Stratified coherent spaces: a denotational semantics for Light Linear Logic
(The University of Edinburgh, 200008)Light linear logic (LLL) was introduced by Girard as a logical system capturing the class of polytime function within the proofsasprograms approach. This paper deals with the denotational semantics of LLL: we introduce ... 
Representing Trees with Constraints
(The University of Edinburgh, 200007)This paper presents a method for representing trees using constraint logic programming over finite domains. We describe a class of trees that is of particular interest to us and how we can represent the set of trees belonging ... 
A CaseBased Reasoning Framework for Enterprise Model Building, Sharing and Reusing
(The University of Edinburgh, 2000)Enterprise model development is essentially a labourintensive exercise. Human experts depend heavily on prior experience when they are building new models making it a natural domain to apply Case Based Reasoning techniques. ... 
Formal Support for an Informal Business Modelling Method
(The University of Edinburgh, 2000)Business modelling methods are popular but, since they operate primarily in the early stages of software lifecycles, most are informal. This paper describes how we have used a conventional formal notation (first order ... 
Completeness Conditions for Mixed Strategy Bidirectional Parsing
(The University of Edinburgh, 2000)It has been suggested that, in certain circumstances, it might be useful for a grammarwriter to annotate which rules are to be used bottomup and which are to be used topdown within a parser, using a bidirectional variant ...