Learning to avoid indoor obstacles from optical flow

Optical flow (OF) is a powerful motion cue that captures the fusion of two important properties for the task of obstacle avoidance − 3D self-motion and 3D environmental surroundings. The problem of extracting such information for obstacle avoidance is commonly addressed through quantitative techniques such as time-to-contact and divergence, which are highly sensitive to noise in the OF image. This paper presents a new strategy towards obstacle avoidance in an indoor setting, using the combination of quantitative and structural properties of the OF field, coupled with the flexibility and efficiency of a machine learning system.The resulting system is able to effectively control the robot in real-time, avoiding obstacles in familiar and unfamiliar indoor environments, under given motion constraints. Furthermore, through the examination of the networks internal weights, we show how OF properties are being used toward the detection of these indoor obstacles.

Experiments in learning helicopter control from a pilot

This paper details the development of a machine learning system which uses the helicopter state and the actions of an instructing pilot to synthesise helicopter control modules online. Aggressive destabilisation/restabilisation sequences are used for training, such that a wide state space envelope is covered during training. The performance of heading, roll, pitch, height and lateral velocity control learning is presented using our Xcell 60 experimental platform. The helicopter is demonstrated to be stabilised on all axes using the “learning from a pilot” technique. To our knowledge, this is the first time a “learning from a pilot” technique has been successfully applied to all axes.

Learning to win process-control games watching game-masters

The present paper focuses on some interesting classes of process-control games, where winning essentially means successfully controlling the process. A master for one of these games is an agent who plays a winning strategy. In this paper we investigate situations in which even a complete model (given by a program) of a particular game does not provide enough information to synthesize—even incrementally—a winning strategy. However, if in addition to getting a program, a machine may also watch masters play winning strategies, then the machine is able to incrementally learn a winning strategy for the given game. Studied are successful learning from arbitrary masters and from pedagogically useful selected masters. It is shown that selected masters are strictly more helpful for learning than are arbitrary masters. Both for learning from arbitrary masters and for learning from selected masters, though, there are cases where one can learn programs for winning strategies from masters but not if one is required to learn a program for the master's strategy itself. Both for learning from arbitrary masters and for learning from selected masters, one can learn strictly more by watching m+1 masters than one can learn by watching only m. Last, a simulation result is presented where the presence of a selected master reduces the complexity from infinitely many semantic mind changes to finitely many syntactic ones.

The application of neural networks to induction machine control

Neural networks (NNs) are discussed in connection with their possible use in induction machine drives. The mathematical model of the NN as well as a commonly used learning algorithm is presented. Possible applications of NNs to induction machine control are discussed. A simulation of an NN successfully identifying the nonlinear multivariable model of an induction-machine stator transfer function is presented. Previously published applications are discussed, and some possible future applications are proposed.

Three primary school students’ cognition about 3D rotation in a virtual reality learning environment

This paper reports on three primary school students’ explorations of 3D rotation in a virtual reality learning environment (VRLE) named VRMath. When asked to investigate if you would face the same direction when you turn right 45 degrees first then roll up 45 degrees, or when you roll up 45 degrees first then turn right 45 degrees, the students found that the different order of the two turns ended up with different directions in the VRLE. This was contrary to the students’ prior predictions based on using pen, paper and body movements. The findings of this study showed the difficulty young children have in perceiving and understanding the non-commutative nature of 3D rotation and the power of the computational VRLE in giving students experiences that they rarely have in real life with 3D manipulations and 3D mental movements.

Sequential nonlinear manifold learning

The computation of compact and meaningful representations of high dimensional sensor data has recently been addressed through the development of Nonlinear Dimensional Reduction (NLDR) algorithms. The numerical implementation of spectral NLDR techniques typically leads to a symmetric eigenvalue problem that is solved by traditional batch eigensolution algorithms. The application of such algorithms in real-time systems necessitates the development of sequential algorithms that perform feature extraction online. This paper presents an efficient online NLDR scheme, Sequential-Isomap, based on incremental singular value decomposition (SVD) and the Isomap method. Example simulations demonstrate the validity and significant potential of this technique in real-time applications such as autonomous systems.

Learning the kernel matrix with semidefinite programming

Kernel-based learning algorithms work by embedding the data into a Euclidean space, and then searching for linear relations among the embedded data points. The embedding is performed implicitly, by specifying the inner products between each pair of points in the embedding space. This information is contained in the so-called kernel matrix, a symmetric and positive semidefinite matrix that encodes the relative positions of all points. Specifying this matrix amounts to specifying the geometry of the embedding space and inducing a notion of similarity in the input space - classical model selection problems in machine learning. In this paper we show how the kernel matrix can be learned from data via semidefinite programming (SDP) techniques. When applied to a kernel matrix associated with both training and test data this gives a powerful transductive algorithm -using the labeled part of the data one can learn an embedding also for the unlabeled part. The similarity between test points is inferred from training points and their labels. Importantly, these learning problems are convex, so we obtain a method for learning both the model class and the function without local minima. Furthermore, this approach leads directly to a convex method for learning the 2-norm soft margin parameter in support vector machines, solving an important open problem.

Implicit online learning

Online learning algorithms have recently risen to prominence due to their strong theoretical guarantees and an increasing number of practical applications for large-scale data analysis problems. In this paper, we analyze a class of online learning algorithms based on fixed potentials and nonlinearized losses, which yields algorithms with implicit update rules. We show how to efficiently compute these updates, and we prove regret bounds for the algorithms. We apply our formulation to several special cases where our approach has benefits over existing online learning methods. In particular, we provide improved algorithms and bounds for the online metric learning problem, and show improved robustness for online linear prediction problems. Results over a variety of data sets demonstrate the advantages of our framework.

Learning the Kernel Matrix with Semi-Definite Programming

Kernel-based learning algorithms work by embedding the data into a Euclidean space, and then searching for linear relations among the embedded data points. The embedding is performed implicitly, by specifying the inner products between each pair of points in the embedding space. This information is contained in the so-called kernel matrix, a symmetric and positive definite matrix that encodes the relative positions of all points. Specifying this matrix amounts to specifying the geometry of the embedding space and inducing a notion of similarity in the input space -- classical model selection problems in machine learning. In this paper we show how the kernel matrix can be learned from data via semi-definite programming (SDP) techniques. When applied to a kernel matrix associated with both training and test data this gives a powerful transductive algorithm -- using the labelled part of the data one can learn an embedding also for the unlabelled part. The similarity between test points is inferred from training points and their labels. Importantly, these learning problems are convex, so we obtain a method for learning both the model class and the function without local minima. Furthermore, this approach leads directly to a convex method to learn the 2-norm soft margin parameter in support vector machines, solving another important open problem. Finally, the novel approach presented in the paper is supported by positive empirical results.

Meaningful musical engagement : the potential impact of generative music systems on learning experiences

In order to create music, the student must establish a relationship with the musical materials. In this thesis, I examine the capacity of a generative music system called jam2jam to offer individuals a virtual musical play-space to explore. I outline the development of an iteration of software development named jam2jam blue and the evolution of a games-like user interface in the research design that jointly revealed the nature of this musical exploration. The findings suggest that the jam2jam blue interface provided an expressive gestural instrument to jam and experience musicmaking. By using the computer as an instrument, participants in this study were given access to meaningful musical experiences in both solo and ensemble situations and the researcher is allowed a view of their development of a relationship with the musical materials from the perspective of the individual participants. Through an iterative software development methodology, pedagogy and experience design were created simultaneously. The research reveals the potential for the jam2jam software to be used as a reflective tool for feedback and assessment purposes. The power of access to ensemble music making is realised though the participants’ virtual experiences which are brought into their physical space by sharing their experience with others. It is suggested that this interaction creates an environment conducive to self-initiated learning in which music is the language of interaction. The research concludes that the development of a relationship between the explorer and the musical materials is subject to the collaborative nature of the interaction through which the music is experienced.

A simulated annealing algorithm for energy efficient virtual machine placement

Improving energy efficiency has become increasingly important in data centers in recent years to reduce the rapidly growing tremendous amounts of electricity consumption. The power dissipation of the physical servers is the root cause of power usage of other systems, such as cooling systems. Many efforts have been made to make data centers more energy efficient. One of them is to minimize the total power consumption of these servers in a data center through virtual machine consolidation, which is implemented by virtual machine placement. The placement problem is often modeled as a bin packing problem. Due to the NP-hard nature of the problem, heuristic solutions such as First Fit and Best Fit algorithms have been often used and have generally good results. However, their performance leaves room for further improvement. In this paper we propose a Simulated Annealing based algorithm, which aims at further improvement from any feasible placement. This is the first published attempt of using SA to solve the VM placement problem to optimize the power consumption. Experimental results show that this SA algorithm can generate better results, saving up to 25 percentage more energy than First Fit Decreasing in an acceptable time frame.

Learning hierarchical prototypes of motion time series for interactive systems

Abstract. For interactive systems, recognition, reproduction, and generalization of observed motion data are crucial for successful interaction. In this paper, we present a novel method for analysis of motion data that we refer to as K-OMM-trees. K-OMM-trees combine Ordered Means Models (OMMs) a model-based machine learning approach for time series with an hierarchical analysis technique for very large data sets, the K-tree algorithm. The proposed K-OMM-trees enable unsupervised prototype extraction of motion time series data with hierarchical data representation. After introducing the algorithmic details, we apply the proposed method to a gesture data set that includes substantial inter-class variations. Results from our studies show that K-OMM-trees are able to substantially increase the recognition performance and to learn an inherent data hierarchy with meaningful gesture abstractions.