From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

https://web.cs.wpi.edu/~rail/files/ArgallEtAlRAS09.pdf

A survey of robot learning from demonstration

Reinforcement learning offers to robotics a framework and set of tools for the design of sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic problems provide both inspiration, impact, and validation for developments in reinforcement learning. The relationship between disciplines has sufficient promise to be likened to that between physics and mathematics. In this article, we attempt to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots. We highlight both key challenges in robot reinforcement learning as well as notable successes. We discuss how contributions tamed the complexity of the domain and study the role of algorithms, representations, and prior knowledge in achieving these successes. As a result, a particular focus of our paper lies on the choice between model-based and model-free as well as between value-function-based and policy-search methods. By analyzing a simple problem in some detail we demonstrate how reinforcement learning approaches may be profitably applied, and we note throughout open questions and the tremendous potential for future research.

/pdf/reinforcement-learning-in-robotics-a-survey-4w4397qx9i.pdf

Reinforcement learning in robotics: A survey

IEEE Transactions on Pattern Analysis and Machine Intelligence

/pdf/an-introduction-to-reinforcement-learning-e60mjj3y0p.pdf

An Introduction to Reinforcement Learning

High-fidelity simulation is a key enabling technology for the widespread deployment of large unmanned ground vehicles (UGVs). However, current approaches for lidar simulation leave much to be desired, particularly for scenes with vegetation. We introduce a novel 3D mapping technique that learns high-fidelity models for geo-specific lidar simulation directly from pose tagged lidar data. We introduce a novel stochastic, volumetric model that captures and can reproduce the statistical interactions of lidar with terrain. We show how to automatically learn the model directly from 3D mapping data collected by a UGV in the target environment. We extend our approach using terrain-classification techniques to develop a hybrid surface–volumetric model that combines the efficiency of surface modeling for areas that are well approximated by large surfaces (e.g. roads, bare earth) with our volumetric approach for more complex areas (e.g. bushes, trees) without sacrificing overall fidelity. We quantitatively compare the performance of our approach against more conventional methods on large outdoor datasets from urban and off-road environments. Our results show significant performance gains using our volumetric and hybrid approaches over the state-of-the-art, laying the ground work for truly high-fidelity simulation engines for UGVs.

3D Mapping for high-fidelity unmanned ground vehicle lidar simulation

Feature descriptors, such as SIFT and ORB, are well-known for their robustness to illumination changes, which has made them popular for feature-based VSLAM\@. However, in degraded imaging conditions such as low light, low texture, blur and specular reflections, feature extraction is often unreliable. In contrast, direct VSLAM methods which estimate the camera pose by minimizing the photometric error using raw pixel intensities are often more robust to low textured environments and blur. Nonetheless, at the core of direct VSLAM is the reliance on a consistent photometric appearance across images, otherwise known as the brightness constancy assumption. Unfortunately, brightness constancy seldom holds in real world applications. 
In this work, we overcome brightness constancy by incorporating feature descriptors into a direct visual odometry framework. This combination results in an efficient algorithm that combines the strength of both feature-based algorithms and direct methods. Namely, we achieve robustness to arbitrary photometric variations while operating in low-textured and poorly lit environments. Our approach utilizes an efficient binary descriptor, which we call Bit-Planes, and show how it can be used in the gradient-based optimization required by direct methods. Moreover, we show that the squared Euclidean distance between Bit-Planes is equivalent to the Hamming distance. Hence, the descriptor may be used in least squares optimization without sacrificing its photometric invariance. Finally, we present empirical results that demonstrate the robustness of the approach in poorly lit underground environments.

Direct Visual Odometry using Bit-Planes

Fundamental to the successful, autonomous operation of mobile robots are robust motion control algorithms. Motion control algorithms determine an appropriate action to take based on the current state of the world. A robot observes the world through sensors, and executes physical actions through actuation mechanisms. Sensors are noisy and can mislead, however, and actions are non-deterministic and thus execute with uncertainty. Furthermore, the trajectories produced by the physical motion devices of mobile robots are complex, which make them difficult to model and treat with traditional control approaches. Thus, to develop motion control algorithms for mobile robots poses a significant challenge, even for simple motion behaviors. As behaviors become more complex, the generation of appropriate control algorithms only becomes more challenging. To develop sophisticated motion behaviors for a dynamically balancing differential drive mobile robot is one target application for this thesis work. Not only are the desired behaviors complex, but prior experiences developing motion behaviors through traditional means for this robot proved to be tedious and demand a high level of expertise. 
One approach that mitigates many of these challenges is to develop motion control algorithms within a Learning from Demonstration (LfD) paradigm. Here, a behavior is represented as pairs of states and actions; more specifically, the states encountered and actions executed by a teacher during demonstration of the motion behavior. The control algorithm is generated from the robot learning a policy, or mapping from world observations to robot actions, that is able to reproduce the demonstrated motion behavior. Robot executions with any policy, including those learned from demonstration, may at times exhibit poor performance; for example, when encountering areas of the state-space unseen during demonstration. Execution experience of this sort can be used by a teacher to correct and update a policy, and thus improve performance and robustness. 
The approaches for motion control algorithm development introduced in this thesis pair demonstration learning with human feedback on execution experience. The contributed feedback framework does not require revisiting areas of the execution space in order to provide feedback, a key advantage for mobile robot behaviors, for which revisiting an exact state can be expensive and often impossible. The types of feedback this thesis introduces range from binary indications of performance quality to execution corrections. In particular, advice-operators are a mechanism through which continuous-valued corrections are provided for multiple execution points. The advice-operator formulation is thus appropriate for low-level motion control, which operates in continuous-valued action spaces sampled at high frequency. 
This thesis contributes multiple algorithms that develop motion control policies for mobile robot behaviors, and incorporate feedback in various ways. Our algorithms use feedback to refine demonstrated policies, as well as to build new policies through the scaffolding of simple motion behaviors learned from demonstration. We evaluate our algorithms empirically, both within simulated motion control domains and on a real robot. We show that feedback improves policy performance on simple behaviors, and enables policy execution of more complex behaviors. Results with the Segway RMP robot confirm the effectiveness of the algorithms in developing and correcting motion control policies on a mobile robot.

/pdf/learning-mobile-robot-motion-control-from-demonstration-and-n1yjs22mz4.pdf

Learning mobile robot motion control from demonstration and corrective feedback

In an adversarial multi-robot task, such as playing robot soccer, decisions for team and single-robot behaviour must be made quickly to take advantage of short-term fortuitous events. When no such opportunities exist, the team must execute sequences of coordinated team action that increases the likelihood of future opportunities. A hierarchical architecture, called STP, has been developed to control an autonomous team of robots operating in an adversarial environment. STP consists of skills for executing the low-level actions that make up robot behaviour, tactics for determining what skills to execute, and plays for coordinating synchronized activity among team members. The STP architecture combines each of these components to achieve autonomous team control. Moreover, the STP hierarchy allows for fast team response in adversarial environments while carrying out actions with longer goals. This article presents the STP architecture for controlling an autonomous robot team in a dynamic adversarial t...

STP: Skills, Tactics and Plays for Multi-Robot Control in Adversarial Environments

A novel closed-form solution for pose-graph SLAM is presented. It optimizes pose-graphs of particular structure called pose-chains by employing an extended version of trajectory bending. Our solution is designed as a back-end optimizer to be used within systems whose front-end performs state-of-the-art visual odometry and appearance based loop detection. The optimality conditions of our closed-form method and that of state-of-the-art iterative methods are discussed. The practical relevance of their theoretical differences is investigated by extensive experiments using simulated and real data. It is shown using 49 kilometers of challenging binocular data that the accuracy obtained by our closed-form solution is comparable to that of state-of-the-art iterative solutions while the time it needs to compute its solution is a factor 50 to 200 times lower. This makes our approach relevant to a broad range of applications and computational platforms.

/pdf/closed-form-online-pose-chain-slam-p7rrq0f93h.pdf

Brett Browning

Papers

3D Mapping for high-fidelity unmanned ground vehicle lidar simulation

Direct Visual Odometry using Bit-Planes

Learning mobile robot motion control from demonstration and corrective feedback

STP: Skills, Tactics and Plays for Multi-Robot Control in Adversarial Environments

Closed-form Online Pose-chain SLAM