REGAL : a regularization based algorithm for reinforcement learning in weakly communicating MDPs

We provide an algorithm that achieves the optimal regret rate in an unknown weakly communicating Markov Decision Process (MDP). The algorithm proceeds in episodes where, in each episode, it picks a policy using regularization based on the span of the optimal bias vector. For an MDP with S states and A actions whose optimal bias vector has span bounded by H, we show a regret bound of ~ O(HS p AT ). We also relate the span to various diameter-like quantities associated with the MDP, demonstrating how our results improve on previous regret bounds.

Optimal allocation strategies for the dark pool problem

We study the problem of allocating stocks to dark pools. We propose and analyze an optimal approach for allocations, if continuous-valued allocations are allowed. We also propose a modification for the case when only integer-valued allocations are possible. We extend the previous work on this problem to adversarial scenarios, while also improving on their results in the iid setup. The resulting algorithms are efficient, and perform well in simulations under stochastic and adversarial inputs.

Current AI in games : a review

As the graphics race subsides and gamers grow weary of predictable and deterministic game characters, game developers must put aside their “old faithful” finite state machines and look to more advanced techniques that give the users the gaming experience they crave. The next industry breakthrough will be with characters that behave realistically and that can learn and adapt, rather than more polygons, higher resolution textures and more frames-per-second. This paper explores the various artificial intelligence techniques that are currently being used by game developers, as well as techniques that are new to the industry. The techniques covered in this paper are finite state machines, scripting, agents, flocking, fuzzy logic and fuzzy state machines decision trees, neural networks, genetic algorithms and extensible AI. This paper introduces each of these technique, explains how they can be applied to games and how commercial games are currently making use of them. Finally, the effectiveness of these techniques and their future role in the industry are evaluated.

Emergent task-specific object semantics through distributed experience networks

Autonomous development of sensorimotor coordination enables a robot to adapt and change its action choices to interact with the world throughout its lifetime. The Experience Network is a structure that rapidly learns coordination between visual and haptic inputs and motor action. This paper presents methods which handle the high dimensionality of the network state-space which occurs due to the simultaneous detection of multiple sensory features. The methods provide no significant increase in the complexity of the underlying representations and also allow emergent, task-specific, semantic information to inform action selection. Experimental results show rapid learning in a real robot, beginning with no sensorimotor mappings, to a mobile robot capable of wall avoidance and target acquisition.

Dynamic texture reconstruction from sparse codes for unusual event detection in crowded scenes

Unusual event detection in crowded scenes remains challenging because of the diversity of events and noise. In this paper, we present a novel approach for unusual event detection via sparse reconstruction of dynamic textures over an overcomplete basis set, with the dynamic texture described by local binary patterns from three orthogonal planes (LBPTOP). The overcomplete basis set is learnt from the training data where only the normal items observed. In the detection process, given a new observation, we compute the sparse coefficients using the Dantzig Selector algorithm which was proposed in the literature of compressed sensing. Then the reconstruction errors are computed, based on which we detect the abnormal items. Our application can be used to detect both local and global abnormal events. We evaluate our algorithm on UCSD Abnormality Datasets for local anomaly detection, which is shown to outperform current state-of-the-art approaches, and we also get promising results for rapid escape detection using the PETS2009 dataset.

Aerial SLAM with a single camera using visual expectation

Micro aerial vehicles (MAVs) are a rapidly growing area of research and development in robotics. For autonomous robot operations, localization has typically been calculated using GPS, external camera arrays, or onboard range or vision sensing. In cluttered indoor or outdoor environments, onboard sensing is the only viable option. In this paper we present an appearance-based approach to visual SLAM on a flying MAV using only low quality vision. Our approach consists of a visual place recognition algorithm that operates on 1000 pixel images, a lightweight visual odometry algorithm, and a visual expectation algorithm that improves the recall of place sequences and the precision with which they are recalled as the robot flies along a similar path. Using data gathered from outdoor datasets, we show that the system is able to perform visual recognition with low quality, intermittent visual sensory data. By combining the visual algorithms with the RatSLAM system, we also demonstrate how the algorithms enable successful SLAM.

Activity modelling in crowded environments : a soft decision approach

Probabilistic topic models have recently been used for activity analysis in video processing, due to their strong capacity to model both local activities and interactions in crowded scenes. In those applications, a video sequence is divided into a collection of uniform non-overlaping video clips, and the high dimensional continuous inputs are quantized into a bag of discrete visual words. The hard division of video clips, and hard assignment of visual words leads to problems when an activity is split over multiple clips, or the most appropriate visual word for quantization is unclear. In this paper, we propose a novel algorithm, which makes use of a soft histogram technique to compensate for the loss of information in the quantization process; and a soft cut technique in the temporal domain to overcome problems caused by separating an activity into two video clips. In the detection process, we also apply a soft decision strategy to detect unusual events.We show that the proposed soft decision approach outperforms its hard decision counterpart in both local and global activity modelling.

Unusual Event Detection in Crowded Scenes Using Bag of LBPs in spatio-temporal patches

Modelling events in densely crowded environments remains challenging, due to the diversity of events and the noise in the scene. We propose a novel approach for anomalous event detection in crowded scenes using dynamic textures described by the Local Binary Patterns from Three Orthogonal Planes (LBP-TOP) descriptor. The scene is divided into spatio-temporal patches where LBP-TOP based dynamic textures are extracted. We apply hierarchical Bayesian models to detect the patches containing unusual events. Our method is an unsupervised approach, and it does not rely on object tracking or background subtraction. We show that our approach outperforms existing state of the art algorithms for anomalous event detection in UCSD dataset.

Combining influence maps and cellular automata for reactive game agents

Agents make up an important part of game worlds, ranging from the characters and monsters that live in the world to the armies that the player controls. Despite their importance, agents in current games rarely display an awareness of their environment or react appropriately, which severely detracts from the believability of the game. Some games have included agents with a basic awareness of other agents, but they are still unaware of important game events or environmental conditions. This paper presents an agent design we have developed, which combines cellular automata for environmental modeling with influence maps for agent decision-making. The agents were implemented into a 3D game environment we have developed, the EmerGEnT system, and tuned through three experiments. The result is simple, flexible game agents that are able to respond to natural phenomena (e.g. rain or fire), while pursuing a goal.

Scripting versus emergence : issues for game developers and players in game environment design

This paper defines and discusses two contrasting approaches to designing game environments. The first, referred to as scripting, requires developers to anticipate, hand-craft and script specific game objects, events and player interactions. The second, known as emergence, involves defining general, global rules that interact to give rise to emergent gameplay. Each of these approaches is defined, discussed and analyzed with respect to the considerations and affects for game developers and game players. Subsequently, various techniques for implementing these design approaches are identified and discussed. It is concluded that scripting and emergence are two extremes of the same continuum, neither of which are ideal for game development. Rather, there needs to be a compromise in which the boundaries of action (such as story and game objectives) can be hardcoded and non-scripted behavior (such as interactions and strategies) are able to emerge within these boundaries.

Emergence in games

The future direction of game development is towards more flexible, realistic, and interactive game worlds. However, current methods of game design do not allow for anything other than pre-scripted player exchanges and static objects and environments. An emergent approach to game development involves the creation of a globally designed game system that provides rules and boundaries for player interactions, rather than prescribed paths. Emergence in Games provides a detailed foundation for applying the theory and practice of emergence in games to game design. Emergent narrative, characters and agents, and game worlds are covered and a hands-on tutorial and case study allow the reader to the put the skills and ideas presented into practice.

Implementation of a survey form marking system using image processing techniques on an Imputer

This paper describes the feasibility of the application of an Imputer in a multiple choice answer sheet marking system based on image processing techniques.

Visual voice activity detection using frontal versus profile views

Visual activity detection of lip movements can be used to overcome the poor performance of voice activity detection based solely in the audio domain, particularly in noisy acoustic conditions. However, most of the research conducted in visual voice activity detection (VVAD) has neglected addressing variabilities in the visual domain such as viewpoint variation. In this paper we investigate the effectiveness of the visual information from the speaker’s frontal and profile views (i.e left and right side views) for the task of VVAD. As far as we are aware, our work constitutes the first real attempt to study this problem. We describe our visual front end approach and the Gaussian mixture model (GMM) based VVAD framework, and report the experimental results using the freely available CUAVE database. The experimental results show that VVAD is indeed possible from profile views and we give a quantitative comparison of VVAD based on frontal and profile views The results presented are useful in the development of multi-modal Human Machine Interaction (HMI) using a single camera, where the speaker’s face may not always be frontal.

A multi-resolution image alignment technique based on direct methods for pose estimation of aerial vehicles

In this paper, we seek to expand the use of direct methods in real-time applications by proposing a vision-based strategy for pose estimation of aerial vehicles. The vast majority of approaches make use of features to estimate motion. Conversely, the strategy we propose is based on a MR (Multi- Resolution) implementation of an image registration technique (Inverse Compositional Image Alignment ICIA) using direct methods. An on-board camera in a downwards-looking configuration, and the assumption of planar scenes, are the bases of the algorithm. The motion between frames (rotation and translation) is recovered by decomposing the frame-to-frame homography obtained by the ICIA algorithm applied to a patch that covers around the 80% of the image. When the visual estimation is required (e.g. GPS drop-out), this motion is integrated with the previous known estimation of the vehicles’ state, obtained from the on-board sensors (GPS/IMU), and the subsequent estimations are based only on the vision-based motion estimations. The proposed strategy is tested with real flight data in representative stages of a flight: cruise, landing, and take-off, being two of those stages considered critical: take-off and landing. The performance of the pose estimation strategy is analyzed by comparing it with the GPS/IMU estimations. Results show correlation between the visual estimation obtained with the MR-ICIA and the GPS/IMU data, that demonstrate that the visual estimation can be used to provide a good approximation of the vehicle’s state when it is required (e.g. GPS drop-outs). In terms of performance, the proposed strategy is able to maintain an estimation of the vehicle’s state for more than one minute, at real-time frame rates based, only on visual information.