Rowan McAllister

Learn More
Deep learning has attracted tremendous attention from researchers in various fields of information engineering such as AI, computer vision, and language processing [Kalchbrenner and Blunsom, 2013; Krizhevsky et al., 2012; Mnih et al., 2013], but also from more traditional sciences such as physics, biology, and manufacturing [Anjos et al., 2015; Baldi et(More)
Model-based reinforcement learning (RL) allows an agent to discover good policies with a small number of trials by generalising observed transitions. Data efficiency can be further improved with a probabilistic model of the agent’s ignorance about the world, allowing it to choose actions under uncertainty. Bayesian modelling offers tools for this task, with(More)
Motion planning for planetary rovers must consider control uncertainty in order to maintain the safety of the platform during navigation. Modelling such control uncertainty is difficult due to the complex interaction between the platform and its environment. In this paper, we propose a motion planning approach whereby the outcome of control actions is(More)
Motion planning for planetary rovers must consider control uncertainty in order to maintain the safety of the platform during navigation. Modelling such control uncertainty is difficult due to the complex interaction between the platform and its environment. In this paper, we propose a motion planning approach whereby the outcome of control actions is(More)
Reconfiguration allows a self-reconfiguring modular robot to adapt to its environment. The reconfiguration planning problem is one of the key algorithmic challenges in realizing self-reconfiguration. Many existing successful approaches rely on grouping modules together to act as meta-modules. However, we are interested in reconfiguration planning that does(More)
This paper presents an approach for a reconfigurable multi-modal mobile robot operating in an indoor environment, based on a probabilistic framework. The modalities are composed of a path planning method, a reactive motion strategy, and an emergency stop. While the mobile robot is achieving its mission to reach its goal, a Hidden Markov Model is used to(More)
Autonomous vehicle (AV) software is typically composed of a pipeline of individual components, linking sensor inputs to motor outputs. Erroneous component outputs propagate downstream, hence safe AV software must consider the ultimate effect of each component’s errors. Further, improving safety alone is not sufficient. Passengers must also feel safe to(More)
We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes (POMDPs) by considering the filtering process during policy evaluation. PILCO conducts policy search, evaluating each policy(More)
An improved electrolarynx is described. It provides handcontrolled fundamental frequency which enables the user to approximate natural intonation patterns, thus overcoming the monotony of speech with conventional aids. Training experiments with normal and with laryngectomized subjects have given promising results. A voice amplifier has been developed.(More)