Unsupervised Domain Adaptation (UDA) is essential for autonomous driving due to a lack of labeled real-world road images. Most of the existing UDA methods, however, have focused on a single-step domain adaptation (Synthetic-to-Real). These methods overlook a change in environments in the real world as time goes by. Thus, developing a domain adaptation method for sequentially changing target domains without catastrophic forgetting is required for real-world applications. To deal with the problem above, we propose Continual Unsupervised Domain Adaptation with Adversarial learning (CUDA^2) framework, which can generally be applicable to other UDA methods conducting adversarial learning. CUDA^2 framework generates a sub-memory, called Target-specific Memory (TM) for each new target domain guided by Double Hinge Adversarial (DHA) loss. TM prevents catastrophic forgetting by storing target-specific information, and DHA loss induces a synergy between the existing network and the expanded TM. To the best of our knowledge, we consider realistic autonomous driving scenarios (Synthetic-to-Real-to-Real) in UDA research for the first time. The model with our framework outperforms other state-of-the-art models under the same settings. Besides, extensive experiments are conducted as ablation studies for in-depth analysis.
Using Social Agents as health-care assistants or trainers is one focus area of IVA research. While their use as physical health-care agents is well established, their employment in the field of psychotherapeutic care comes with daunting challenges. This paper presents our mobile Social Agent EmmA in the role of a vocational reintegration assistant for burn-out outpatient treatment. We follow a typical participatory design approach including experts and patients in order to address requirements from both sides. Since the success of such treatments is related to a patients emotion regulation capabilities, we employ a real-time social signal interpretation together with a computational simulation of emotion regulation that influences the agent's social behavior as well as the situational selection of verbal treatment strategies. Overall, our interdisciplinary approach enables a novel integrative concept for Social Agents as assistants for burn-out patients.
Advances in artificial intelligence are driven by technologies inspired by the brain, but these technologies are orders of magnitude less powerful and energy efficient than biological systems. Inspired by the nonlinear dynamics of neural networks, new unconventional computing hardware has emerged with the potential for extreme parallelism and ultra-low power consumption. Physical reservoir computing demonstrates this with a variety of unconventional systems from optical-based to spintronic. Reservoir computers provide a nonlinear projection of the task input into a high-dimensional feature space by exploiting the system's internal dynamics. A trained readout layer then combines features to perform tasks, such as pattern recognition and time-series analysis. Despite progress, achieving state-of-the-art performance without external signal processing to the reservoir remains challenging. Here we show, through simulation, that magnetic materials in thin-film geometries can realise reservoir computers with greater than or similar accuracy to digital recurrent neural networks. Our results reveal that basic spin properties of magnetic films generate the required nonlinear dynamics and memory to solve machine learning tasks. Furthermore, we show that neuromorphic hardware can be reduced in size by removing the need for discrete neural components and external processing. The natural dynamics and nanoscale size of magnetic thin-films present a new path towards fast energy-efficient computing with the potential to innovate portable smart devices, self driving vehicles, and robotics.
To address the mounting destruction caused by floods in climate-vulnerable regions, we propose Street to Cloud, a machine learning pipeline for incorporating crowdsourced ground truth data into the segmentation of satellite imagery of floods. We propose this approach as a solution to the labor-intensive task of generating high-quality, hand-labeled training data, and demonstrate successes and failures of different plausible crowdsourcing approaches in our model. Street to Cloud leverages community reporting and machine learning to generate novel, near-real time insights into the extent of floods to be used for emergency response.
Combinatorial decision problems arise in many different domains such as scheduling, routing, packing, bioinformatics, and many more. Despite recent advances in developing scalable solvers, there are still many problems which are often very hard to solve. Typically the most advanced solvers include elements which are stochastic in nature. If a same instance is solved many times using different seeds then depending on the inherent characteristics of a problem instance and the solver, one can observe a highly-variant distribution of times spanning multiple orders of magnitude. Therefore, to solve a problem instance efficiently it is often useful to solve the same instance in parallel with different seeds. With the proliferation of cloud computing, it is natural to think about an elastic solver which can scale up by launching searches in parallel on thousands of machines (or cores). However, this could result in consuming a lot of energy. Moreover, not every instance would require thousands of machines. The challenge is to resolve the tradeoff between solution time and energy consumption optimally for a given problem instance. We analyse the impact of the number of machines (or cores) on not only solution time but also on energy consumption. We highlight that although solution time always drops as the number of machines increases, the relation between the number of machines and energy consumption is more complicated. In many cases, the optimal energy consumption may be achieved by a middle ground, we analyse this relationship in detail. The tradeoff between solution time and energy consumption is studied further, showing that the energy consumption of a solver can be reduced drastically if we increase the solution time marginally. We also develop a prediction model, demonstrating that such insights can be exploited to achieve faster solutions times in a more energy efficient manor.
Mobile manipulation tasks remain one of the critical challenges for the widespread adoption of autonomous robots in both service and industrial scenarios. While planning approaches are good at generating feasible whole-body robot trajectories, they struggle with dynamic environments as well as the incorporation of constraints given by the task and the environment. On the other hand, dynamic motion models in the action space struggle with generating kinematically feasible trajectories for mobile manipulation actions. We propose a deep reinforcement learning approach to learn feasible dynamic motions for a mobile base while the end-effector follows a trajectory in task space generated by an arbitrary system to fulfill the task at hand. This modular formulation has several benefits: it enables us to readily transform a broad range of end-effector motions into mobile applications, it allows us to use the kinematic feasibility of the end-effector trajectory as a dense reward signal and its modular formulation allows it to generalise to unseen end-effector motions at test time. We demonstrate the capabilities of our approach on multiple mobile robot platforms with different kinematic abilities and different types of wheeled platforms in extensive simulated as well as real-world experiments.
This paper proposes a new algorithm, named Householder Dice (HD), for simulating dynamics on dense random matrix ensembles with translation-invariant properties. Examples include the Gaussian ensemble, the Haar-distributed random orthogonal ensemble, and their complex-valued counterparts. A "direct" approach to the simulation, where one first generates a dense $n \times n$ matrix from the ensemble, requires at least $\mathcal{O}(n^2)$ resource in space and time. The HD algorithm overcomes this $\mathcal{O}(n^2)$ bottleneck by using the principle of deferred decisions: rather than fixing the entire random matrix in advance, it lets the randomness unfold with the dynamics. At the heart of this matrix-free algorithm is an adaptive and recursive construction of (random) Householder reflectors. These orthogonal transformations exploit the group symmetry of the matrix ensembles, while simultaneously maintaining the statistical correlations induced by the dynamics. The memory and computation costs of the HD algorithm are $\mathcal{O}(nT)$ and $\mathcal{O}(nT^2)$, respectively, with $T$ being the number of iterations. When $T \ll n$, which is nearly always the case in practice, the new algorithm leads to significant reductions in runtime and memory footprint. Numerical results demonstrate the promise of the HD algorithm as a new computational tool in the study of high-dimensional random systems.
In light-sheet microscopy, overall image content and resolution are improved by acquiring and fusing multiple views of the sample from different directions. State-of-the-art multi-view (MV) deconvolution employs the point spread functions (PSF) of the different views to simultaneously fuse and deconvolve the images in 3D, but processing takes a multiple of the acquisition time and constitutes the bottleneck in the imaging pipeline. Here we show that MV deconvolution in 3D can finally be achieved in real-time by reslicing the acquired data and processing cross-sectional planes individually on the massively parallel architecture of a graphics processing unit (GPU).
Scene text is an important feature to be extracted, especially in vision-based mobile robot navigation as many potential landmarks such as nameplates and information signs contain text. In this paper, a novel two-step text localization method for Indoor Mobile Robot Navigation is introduced. This method is based on morphological operators and machine learning techniques and can be used in real time environments. The proposed method has two steps. At First, a new set of morphological operators is applied with a particular sequence to extract high contrast areas that have high probability of text existence. Using of morphological operators has many advantages such as: high computation speed, being invariant to several geometrical transformations like translation, rotations, and scaling, and being able to extract all areas containing text. After extracting text candidate regions, a set of nine features are extracted for accurate detection and deletion of the regions that don't have text. These features are descriptors for texture properties and are computed in real time. Then, we use a SVM classifier to detect the existence of text in the region. Performance of the proposed algorithm is compared against a number of widely used text localization algorithms and the results show that this method can quickly and effectively localize and extract text regions from real scenes and can be used in mobile robot navigation under an indoor environment to detect text based landmarks.
Segmentation of COVID-19 lesions from chest CT scans is of great importance for better diagnosing the disease and investigating its extent. However, manual segmentation can be very time consuming and subjective, given the lesions' large variation in shape, size and position. On the other hand, we still lack large manually segmented datasets that could be used for training machine learning-based models for fully automatic segmentation. In this work, we propose a new interactive and user-friendly tool for COVID-19 lesion segmentation, which works by alternating automatic steps (based on level-set segmentation and statistical shape modeling) with manual correction steps. The present software was tested by two different expertise groups: one group of three radiologists and one of three users with an engineering background. Promising segmentation results were obtained by both groups, which achieved satisfactory agreement both between- and within-group. Moreover, our interactive tool was shown to significantly speed up the lesion segmentation process, when compared to fully manual segmentation. Finally, we investigated inter-observer variability and how it is strongly influenced by several subjective factors, showing the importance for AI researchers and clinical doctors to be aware of the uncertainty in lesion segmentation results.