Finite-state controllers represent an effective action selection mechanisms widely used in domains such as video-games and mobile robotics. In contrast to the policies obtained from MDPs and POMDPs, finite-state controllers have two advantages: they are often extremely compact, and they are general, applying to many problems and not just one. A limitation of finite-state controllers, on the other hand, is that they are written by hand. In this paper, we address this limitation, presenting a method for deriving controllers automatically from models. The models represent a class of contingent problems where actions are deterministic and some fluents are observable. The problem of deriving a controller is converted into a conformant problem that is solved using classical planners, taking advantage of a complete translation into classical planning introduced recently. The controllers derived are ‘general’ in the sense that they do not solve the original problem only, but many variations as well, including changes in the size of the problem or in the uncertainty of the initial situation and action effects. Several experiments illustrating the automatic derivation of controllers are presented.

Labeling nodes in a network is an important problem that has seen a growing interest. A number of methods that exploit both local and relational information have been developed for this task. Acquiring the labels for a few nodes at inference time can greatly improve the accuracy, however the question of figuring out which node labels to acquire is challenging. Previous approaches have been based on simple structural properties. Here, we present a novel technique, which we refer to as reflect and correct,that can learn and predict when the underlying classification system is likely to make mistakes and it suggests acquisitions to correct those mistakes.

We report a new error-aware monocular visual odometry method that only uses vertical lines, such as vertical edges of buildings and poles in urban areas as landmarks. Since vertical lines are easy to extract, insensitive to lighting conditions/ shadows, and sensitive to robot movements on the ground plane, they are robust features if compared with regular point features or line features. We derive a recursive visual odometry method based on the vertical line pairs. We analyze how errors are propagated and introduced in the continuous odometry process by deriving the closed form representation of covariance matrix. We formulate the minimum variance ego-motion estimation problem and present a method that outputs weights for different vertical line pairs. The resulting visual odometry method is tested in physical experiments and compared with two existing methods that are based on point features and line features, respectively. The experiment results show that our method outperforms its two counterparts in robustness, accuracy, and speed. The relative errors of our method are less than 2% in experiments.

In this work, we show how to use existing hardware on The main advantage of legged locomotion over wheeled locomotion bipedal robots to address the sensing part of the problem is that legs have the capability of climbing rougher using online machine learning techniques. By incorporating terrain than wheeled or tracked vehicles. Unfortunately, this electronic compliance and foot pressure sensors, the swing ideal is often not achieved in reality, especially for the current foot is used to provide noisy estimates of the local gradient generation of bipedal humanoid robots. Many walking of the contact point, and the computed pose of the foot from controller implementations for humanoid robots assume perfectly joint encoders and the inertial measurement unit is used to flat surfaces, and even a slight deviation in the floor rapidly learn an explicit model of the surface the robot is can lead to serious instabilities in these controllers.

People tracking is a key technology for autonomous systems, intelligent cars and social robots operating in populated environments. What makes the task difficult is that the appearance of humans in range data can change drastically as a function of body pose, distance to the sensor, self-occlusion and occlusion by other objects. In this paper we propose a novel approach to pedestrian detection in 3D range data based on supervised learning techniques to create a bank of classifiers for different height levels of the human body. In particular, our approach applies AdaBoost to train a strong classifier from geometrical and statistical features of groups of neighboring points at the same height. In a second step, the AdaBoost classifiers mutually enforce their evidence across different heights by voting into a continuous space. Pedestrians are finally found efficiently by mean-shift search for local maxima in the voting space. Experimental results carried out with 3D laser range data illustrate the robustness and efficiency of our approach even in cluttered urban environments. The learned people detector reaches a classification rate up to 96% from a single 3D scan.

We report a new filter for assisting the search for rare bird species. Since a rare bird only appears in front of the camera with very low occurrence (e.g. less than ten times per year) for very short duration (e.g. less than a fraction of a second), our algorithm must have very low false negative rate. We verify the bird body axis information with the known bird flying dynamics from the short video segment. Since a regular extended Kalman filter (EKF) cannot converge due to high measurement error and limited data, we develop a novel Probable Observation Data Set (PODS)-based EKF method. The new PODS-EKF searches the measurement error range for all probable observation data that ensures the convergence of the corresponding EKF in short time frame. The algorithm has been extensively tested in experiments. The results show that the algorithm achieves 95.0% area under ROC curve in physical experiment with close to zero false negative rate.

Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature convergence and implausible solutions. As first suggested in the context of covariant policy gradients, many of these problems may be addressed by constraining the information loss. In this paper, we continue this path of reasoning and suggest the Relative Entropy Policy Search (REPS) method. The resulting method differs significantly from previous policy gradient approaches and yields an exact update step. It can be shown to work well on typical reinforcement learning benchmark problems.

Modeling human behavior requires vast quantities of accurately labeled training data, but for ubiquitous people-aware applications such data is rarely attainable. Even researchers make mistakes when labeling data, and consistent, reliable labels from low-commitment users are rare. In particular, users may give identical labels to activities with characteristically different signatures (e.g., labeling eating at home or at a restaurant as "dinner") or may give different labels to the same context (e.g., "work" vs. "office"). In this scenario, labels are unreliable but nonetheless contain valuable information for classification. To facilitate learning in such unconstrained labeling scenarios, we propose Community-Guided Learning (CGL), a framework that allows existing classifiers to learn robustly from unreliably-labeled user-submitted data. CGL exploits the underlying structure in the data and the unconstrained labels to intelligently group crowd-sourced data. We demonstrate how to use similarity measures to determine when and how to split and merge contributions from different labeled categories and present experimental results that demonstrate the effectiveness of our framework.

Developing a robust, flexible, closed-loop walking algorithm for a humanoid robot is a challenging task due to the complex dynamics of the general biped walk. Common analytical approaches to biped walk use simplified models of the physical reality. Such approaches are partially successful as they lead to failures of the robot walk in terms of unavoidable falls. Instead of further refining the analytical models, in this work we investigate the use of human corrective demonstrations, as we realize that a human can visually detect when the robot may be falling. We contribute a two-phase biped walk learning approach, which we experiment on the Aldebaran NAO humanoid robot. In the first phase, the robot walks following an analytical simplified walk algorithm, which is used as a black box, and we identify and save a walk cycle as joint motion commands. We then show how the robot can repeatedly and successfully play back the recorded motion cycle, even if in open-loop. In the second phase, we create a closed-loop walk by modifying the recorded walk cycle to respond to sensory data. The algorithm learns joint movement corrections to the open-loop walk based on the corrective feedback provided by a human, and on the sensory data, while walking autonomously. In our experimental results, we show that the learned closed-loop walking policy outperforms a hand-tuned closed-loop policy and the open-loop playback walk, in terms of the distance traveled by the robot without falling.

Constructing models of mobile agents can be difficult without domain-specific knowledge. Parametric models flexible enough to capture all mobility patterns that an expert believes are possible are often large, requiring a great deal of training data. In contrast, nonparametric models are extremely flexible and can generalize well with relatively little training data. We propose modeling the mobility patterns of moving agents as a mixture of Gaussian processes (GP) with a Dirichlet process (DP) prior over mixture weights. The GP provides a flexible representation for each individual mobility pattern, while the DP assigns observed trajectories to particular mobility patterns. Both the GPs and the DP adjust the model's complexity based on available data, implicitly avoiding issues of over-fitting or under-fitting. We apply our model to a helicopter-based tracking task, where the mobility patterns of the tracked agents — cars — are learned from real data collected from taxis in the greater Boston area.