Certified orientation and mobility specialists (COMS) work with clients who are blind or visually impaired (BVI) to help them travel independently with confidence. Part of this process involves creating a narrative description of a route and using specific techniques to help the client internalize it. We focus on the problem of automatically generating a narrative description of an indoor route based on a recording from a smartphone. These automatically generated narrations could be used in cases where a COMS is not available or to enable clients to independently practice routes that were originally learned with the help of a COMS. Specifically, we introduce Clew3D, a mobile app that leverages LIDAR-equipped iOS devices to identify orientation and mobility (O&M) landmarks and their relative location along a recorded route. The identified landmarks are then used to provide a spoken narration modeled after traditional O&M techniques. Our solution is co-designed with COMS and uses methods and language that they employ when creating route narrations for their clients. In addition to presenting Clew3D, we report the results of an analysis conducted with COMS regarding techniques and terminology used in traditional, in-person O&M instruction. We also discuss challenges posed by vision-based systems to achieve automatic narrations that are reliable. Finally, we provide an example of an automatically generated route description and compare it with the same route provided by a COMS.

The introduction of augmented reality technology to iOS and Android enables, for the first time, mainstream smartphones to estimate their own motion in 3D space with high accuracy. For assistive technology researchers, this development presents a potential opportunity. In this spirit, we present our work leveraging these technologies to create a smartphone app to empower people who are visually impaired to more easily navigate indoor environments. Our app, Clew, allows users to record routes and then load them, at any time, providing automatic guidance (using haptic, speech, and sound feedback) along the route. We present our user-centered design process, Clew's system architecture and technical details, and both small and large-scale evaluations of the app. We discuss opportunities, pitfalls, and design guidelines for utilizing augmented reality for orientation and mobility apps. Our work expands the capabilities of technology for orientation and mobility that can be distributed on a mass scale.

CS majors are certainly not disappearing, but the interest and demand for computing from non-CS majors is a far larger part of our future, as members of CS departments, than those on the disciplinary-major path. As computing evolves from valuable specialty to a professional literacy, CS departments face several challenges. How do we support both the traditional CS-major path and provide computing curriculum to a far broader audience? How do we partner with sibling departments in order to foster their sense of ownership and identity with computing's mindsets and toolsets? And, perhaps especially poignant in 2018, how do we invest energy into the CS-for-All future during a time that demand in our major pathway is at historic highs? This workshop distills the experiences of three faculty members who have tried to answer these questions within the context of their departments. The presenters will share the results of those experiments, will offer hands-on exploration of a representative subset of the curricular materials, and will scaffold a strategic discussion of CS's future and identity in the era of "CS for All."

This work-in-progress, innovative-practice paper describes the creation and first two iterations of an experimental course which aims to develop a process-focused approach to integrated quantitative engineering analysis in early stage engineering students. The goal of this two-semester course is to improve the confidence and competence of our students in choosing and applying the tools of quantitative analysis to solve practical problems throughout their time in college and beyond, including in other course projects, senior capstone experiences, internships and in their careers. The course is led by an interdisciplinary team of faculty, in a project-based format, including in the presentation of fundamental concepts in mathematics. The course is run studio style, with emphasis placed on the process of engineering, improving students' self-directed learning skills, and encouraging peer and near-peer learning. Overall, we observed a high level of engagement in the course, with student-chosen final projects that involved significant analysis and self-directed learning of new tools and approaches.

What is needed to help CS professors teach their students about the fundamental concepts of accessible design? How can every CS student become competent in the development of mainstream technologies that meet the needs of people with disabilities? Society is demanding such capabilities and companies such as Microsoft, Facebook, Oath (Yahoo), Adobe, and Google are today working with major universities to assure that new hires graduate college with this essential skillset. The Teach Access project is actively addressing the barriers, incentives and mechanisms through curriculum change, influencing accreditation, faculty bootcamps, industry guest lectures, online tutorials, and student engagement programs. What works for you and how can more university and faculty champions be engaged?

I present a robotics localization challenge based on the inexpensive Neato XV robotic vacuum cleaner platform. The challenge teaches skills such as computational modeling, probabilistic inference, efficiency vs. accuracy tradeoffs, debugging, parameter tuning, and benchmarking of algorithmic performance. Rather than allowing students to pursue any localization algorithm of their choosing, here, I propose a challenge structured around the particle filter family of algorithms. This additional scaffolding allows students at all levels to successfully implement one approach to the challenge, while providing enough flexibility and richness to enable students to pursue their own creative ideas. Additionally, I provide infrastructure for automatic evaluation of systems through the collection of ground truth robot location data via ceiling-mounted location tags that are automatically scanned using an upward facing camera attached to the robot. The robot and supporting hardware can be purchased for under $400 dollars, and the challenge can even be run without any robots at all using a set of recorded sensor traces.

The success of applying policy gradient reinforcement learning (RL) to difficult control tasks hinges crucially on the ability to determine a sensible initialization for the policy. Transfer learning methods tackle this problem by reusing knowledge gleaned from solving other related tasks. In the case of multiple task domains, these algorithms require an inter-task mapping to facilitate knowledge transfer across domains. However, there are currently no general methods to learn an inter-task mapping without requiring either background knowledge that is not typically present in RL settings, or an expensive analysis of an exponential number of inter-task mappings in the size of the state and action spaces. This paper introduces an autonomous framework that uses unsupervised manifold alignment to learn inter-task mappings and effectively transfer samples between different task domains. Empirical results on diverse dynamical systems, including an application to quadrotor control, demonstrate its effectiveness for cross-domain transfer in the context of policy gradient RL.

This paper develops an efficient online algorithm for learning multiple consecutive tasks based on the K-SVD algorithm for sparse dictionary optimization. We first derive a batch multi-task learning method that builds upon K-SVD, and then extend the batch algorithm to train models online in a lifelong learning setting. The resulting method has lower computational complexity than other current lifelong learning algorithms while maintaining nearly identical model performance. Additionally, the proposed method offers an alternate formulation for lifelong learning that supports both task and feature similarity matrices.

Policy gradient algorithms have shown considerable recent success in solving high-dimensional sequential decision making tasks, particularly in robotics. However, these methods often require extensive experience in a domain to achieve high performance. To make agents more sample-efficient, we developed a multi-task policy gradient method to learn decision making tasks consecutively, transferring knowledge between tasks to accelerate learning. Our approach provides robust theoretical guarantees, and we show empirically that it dramatically accelerates learning on a variety of dynamical systems, including an application to quadrotor control.

In a lifelong learning framework, an agent acquires knowledge incrementally over consecutive learning tasks, continually building upon its experience. Recent lifelong learning algorithms have achieved nearly identical performance to batch multi-task learning methods while reducing learning time by three orders of magnitude. In this paper, we further improve the scalability of lifelong learning by developing curriculum selection methods that enable an agent to actively select the next task to learn in order to maximize performance on future learning tasks. We demonstrate that active task selection is highly reliable and effective, allowing an agent to learn high performance models using up to 50% fewer tasks than when the agent has no control over the task order. We also explore a variant of transfer learning in the lifelong learning setting in which the agent can focus knowledge acquisition toward a particular target task.

The problem of learning multiple consecutive tasks, known as lifelong learning, is of great importance to the creation of intelligent, general-purpose, and flexible machines. In this paper, we develop a method for online multi-task learning in the lifelong learning setting. The proposed Efficient Lifelong Learning Algorithm (ELLA) maintains a sparsely shared basis for all task models, transfers knowledge from the basis to learn each new task, and refines the basis over time to maximize performance across all tasks. We show that ELLA has strong connections to both online dictionary learning for sparse coding and state-of-the-art batch multi-task learning methods, and provide robust theoretical performance guarantees. We show empirically that ELLA yields nearly identical performance to batch multi-task learning while learning tasks sequentially in three orders of magnitude (over 1,000x) less time.

We present a new machine learning algorithm for learning optimal feedback control policies to guide a robot to a goal in the presence of obstacles. Our method works by first reducing the problem of obstacle avoidance to a continuous state, action, and time control problem, and then uses efficient collocation methods to solve for an optimal feedback control policy. This formulation of the obstacle avoidance problem improves over standard approaches, such as potential field methods, by being resistant to local minima, allowing for moving obstacles, handling stochastic systems, and computing feedback control strategies that take into account the robot's (possibly non-linear) dynamics. In addition to contributing a new method for obstacle avoidance, our work contributes to the state-of-the-art in collocation methods for non-linear stochastic optimal control problems in two important ways: (1) we show that taking into account local gradient and second-order derivative information of the optimal value function at the collocation points allows us to exploit knowledge of the derivative information about the system dynamics, and (2) we show that computational savings can be achieved by directly fitting the gradient of the optimal value function rather than the optimal value function itself. We validate our approach on three problems: non-convex obstacle avoidance of a point-mass robot, obstacle avoidance for a 2 degree of freedom robotic manipulator, and optimal control of a non-linear dynamical system.

In expression recognition and many other computer vision applications, the recognition performance is greatly improved by adding a layer of nonlinear texture filters between the raw input pixels and the classifier. The function of this layer is typically known as feature extraction. Popular filter types for this layer are Gabor energy filters (GEFs) and local binary patterns (LBPs). Recent work [1] suggests that adding a second layer of nonlinear filters on top of the first layer may be beneficial. However, it is unclear what is the best architecture of layers and selection of filters. In this paper, we present a thorough empirical analysis of the performance of single-layer and dual-layer texture-based approaches for action unit recognition. For the single hidden layer case, GEFs perform consistently better than LBPs, which may be due to their robustness to jitter and illumination noise as well as to their ability to encode texture at multiple resolutions. For dual-layer case, we confirm that, while small, the benefit of adding this second layer is reliable and consistent across data sets. Interestingly for this second layer, LBPs appear to perform better than GEFs.

This paper assesses the performance of measures of facial expression dynamics derived from the Computer Expression Recognition Toolbox (CERT) for classifying emotions in the Facial Expression Recognition and Analysis (FERA) Challenge. The CERT system automatically estimates facial action intensity and head position using learned appearance-based models on single frames of video. CERT outputs were used to derive a representation of the intensity and motion in each video, consisting of the extremes of displacement, velocity and acceleration. Using this representation, emotion detectors were trained on the FERA training examples. Experiments on the released portion of the FERA dataset are presented, as well as results on the blind test. No consideration of subject identity was taken into account in the blind test. The F1 scores were well above the baseline criterion for success.

We explore how CERT, a computer expression recognition toolbox trained on a large dataset of spontaneous facial expressions (FFD07), generalizes to a new, previously unseen dataset (FERA). The experiment was unique in that the authors had no access to the test labels, which were guarded as part of the FERA challenge. We show that without any training or special adaptation to the new database, CERT performs better than a baseline method trained exclusively on that database. Best results are achieved by retraining CERT with a combination of old and new data. We also found that the FERA dataset may be too small and idiosyncratic to generalize to other datasets. Training on FERA alone produced good results on FERA but very poor results on FFD07. We reflect on the importance of challenges like this for the future of the field, and discuss suggestions for standardization of future challenges.

In this paper, we evaluate adaptive sound localization algorithms for robotic heads. To this end we built a 3 degree-of-freedom head with two microphones encased in artificial pinnae (outer ears). The geometry of the head and pinnae induce temporal differences in the sound recorded at each microphone. These differences change with the frequency of the sound, location of the sound, and orientation of the robot in a complex manner. To learn the relationship between these auditory differences and the location of a sound source, we applied machine learning methods to a database of different audio source locations and robot head orientations. Our approach achieves a mean error of 2.5 degrees for azimuth and 11 degrees for elevation for estimating the position of an audio source. The impressive results highlight the benefits of a two-stage regression model to make use of the properties of the artificial pinnae for elevation estimation. In this work, the algorithms were trained using ground truth data provided by a motion capture system. We are currently generalizing the approach so that the training signal is provided online based on a real-time face detection and speech detection system.

Determining whether someone is talking has applications in many areas such as speech recognition, speaker diarization, social robotics, facial expression recognition, and human computer interaction. One popular approach to this problem is audio-visual synchrony detection. A candidate speaker is deemed to be talking if the visual signal around that speaker correlates with the auditory signal. Here we show that with the proper visual features (in this case movements of various facial muscle groups), a very accurate detector of speech can be created that does not use the audio signal at all. Further we show that this person independent visual-only detector can be used to train very accurate audio-based person dependent voice models. The voice model has the advantage of being able to identify when a particular person is speaking even when they are not visible to the camera (e.g. in the case of a mobile robot). Moreover, we show that a simple sensory fusion scheme between the auditory and visual models improves performance on the task of talking detection. The work here provides dramatic evidence about the efficacy of two very different approaches to multimodal speech detection on a challenging database.

Modern machine learning-based approaches to computer vision require very large databases of labeled images. Some contemporary vision systems already require on the order of millions of images for training (e.g., Omron face detector). While the collection of these large databases is becoming a bottleneck, new Internet-based services that allow labelers from around the world to be easily hired and managed provide a promising solution. However, using these services to label large databases brings with it new theoretical and practical challenges: (1) The labelers may have wide ranging levels of expertise which are unknown a priori, and in some cases may be adversarial; (2) images may vary in their level of difficulty; and (3) multiple labels for the same image must be combined to provide an estimate of the actual label of the image. Probabilistic approaches provide a principled way to approach these problems. In this paper we present a probabilistic model and use it to simultaneously infer the label of each image, the expertise of each labeler, and the difficulty of each image. On both simulated and real data, we demonstrate that the model outperforms the commonly used ``Majority Vote heuristic for inferring image labels, and is robust to both adversarial and noisy labelers.

Social robots face the fundamental challenge of detecting and adapting their behavior to the current social mood. For example, robots that assist teachers in early education must choose different behaviors depending on whether the children are crying, laughing, sleeping, or singing songs. Interactive robotic applications require perceptual algorithms that both run in real time and are adaptable to the challenging conditions of daily life. This paper explores a novel approach to auditory mood detection which was born out of our experience immersing social robots in classroom environments. We propose a new set of low-level spectral contrast features that extends a class of features which have proven very successful for object recognition in the modern computer vision literature. Features are selected and combined using machine learning approaches so as to make decisions about the ongoing auditory mood. We demonstrate excellent performance on two standard emotional speech databases (the Berlin Emotional Speech [W. Burkhardt et al., 2005], and the ORATOR dataset [H. Quast, 2001]). In addition we establish strong baseline performance for mood detection on a database collected from a social robot immersed in a classroom of 18-24 months old children [J. Movellan er al., 2007]. This approach operates in real time at little computational cost. It has the potential to greatly enhance the effectiveness of social robots in daily life environments.

Many popular optimization algorithms, like the Levenberg-Marquardt algorithm (LMA), use heuristic-based controllers'' that modulate the behavior of the optimizer during the optimization process. For example, in the LMA a damping parameter is dynamically modified based on a set rules that were developed using various heuristic arguments. Reinforcement learning (RL) is a machine learning approach to learn optimal controllers by examples and thus is an obvious candidate to improve the heuristic-based controllers implicit in the most popular and heavily used optimization algorithms. Improving the performance of off-the-shelf optimizers is particularly important for time-constrained optimization problems. For example the LMA algorithm has become popular for many real-time computer vision problems, including object tracking from video, where only a small amount of time can be allocated to the optimizer on each incoming video frame. Here we show that a popular modern reinforcement learning technique using a very simply state space can dramatically improve the performance of general purpose optimizers, like the LMA. Most surprisingly the controllers learned for a particular domain appear to work very well also on very different optimization domains. For example we used RL methods to train a new controller for the damping parameter of the LMA. This controller was trained on a collection of classic, relatively small, non-linear regression problems. The modified LMA performed better than the standard LMA on these problems. Most surprisingly, it also dramatically outperformed the standard LMA on a difficult large scale computer vision problem for which it had not been trained before. Thus the controller appeared to have extracted control rules that were not just domain specific but generalized across a wide range of optimization domains."

The goal of the RUBI project is to accelerate progress in the development of social robots by addressing the problem at multiple levels, including the development of a scientific agenda, research methods, formal approaches, software, and hardware. The project is based on the idea that progress will go hand-in-hand with the emergence of a new scientific discipline that focuses on understanding the organization of adaptive behavior in real-time within the environments in which organisms operate. As such, the RUBI project emphasizes the process of design by immersion, i.e., embedding scientists, engineers and robots in everyday life environments so as to have these environments shape the hardware, software, and scientific questions as early as possible in the development process. The focus of the project so far has been on social robots that interact with 18 to 24 month old toddlers as part of their daily activities at the Early Childhood Education Center at the University of California, San Diego. In this document we present an overall assessment of the lessons and progress through year two of the project.