Everyday robotics are challenged to deal with autonomous product handling in applications like logistics or retail, possibly causing damage on the items during manipulation. Traditionally, most approaches try to minimize physical interaction with goods. However, this paper proposes to take into account any unintended object motion and to learn damage-minimizing manipulation strategies in a self-supervised way. The presented approach consists of a simulation-based planning method for an optimal manipulation sequence with respect to possible damage. The planned manipulation sequences are generalized to new, unseen scenes in the same application scenario using machine learning. This learned manipulation strategy is continuously refined in a self-supervised, simulation-in-the-loop optimization cycle during load-free times of the system, commonly known as mental simulation. In parallel, the generated manipulation strategies can be deployed in near-real time in an anytime fashion. The approach is validated on an industrial container-unloading scenario and on a retail shelf-replenishment scenario.

In recent years, data-driven methods have been utilized to learn dynamical systems and partial differential equations (PDE). However, major challenges remain to be resolved, including learning PDE under noisy data and limited discrete data. To overcome these challenges, in this work, a deep-learning based data-driven method, called DL-PDE, is developed to discover the governing PDEs of underlying physical processes. The DL-PDE method combines deep learning via neural networks and data-driven discovery of PDEs via sparse regressions, such as the least absolute shrinkage and selection operator (Lasso) and sequential threshold ridge regression (STRidge). In this method, derivatives are calculated by automatic differentiation from the deep neural network, and equation form and coefficients are obtained with sparse regressions. The DL-PDE is tested with physical processes, governed by groundwater flow equation, contaminant transport equation, Burgers equation and Korteweg-de Vries (KdV) equation, for proof-of-concept and applications in real-world engineering settings. The proposed DL-PDE achieves satisfactory results when data are discrete and noisy.

The concepts of risk-aversion, chance-constrained optimization, and robust optimization have developed significantly over the last decade. Statistical learning community has also witnessed a rapid theoretical and applied growth by relying on these concepts. A modeling framework, called distributionally robust optimization (DRO), has recently received significant attention in both the operations research and statistical learning communities. This paper surveys main concepts and contributions to DRO, and its relationships with robust optimization, risk-aversion, chance-constrained optimization, and function regularization.

ABSTRACT In this paper, we propose "personal V AD", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming speech recognition system, such that it only triggers for the target user, which helps reduce the computational cost and battery consumption. We achieve this by training a V ADalike neural network that is conditioned on the target speaker embedding or the speaker verification score. With our optimal setup, we are able to train a 130KB model that outperforms a baseline system where individually trained standard V AD and speaker recognition network are combined to perform the same task. Index T erms-- Personal V AD, voice activity detection, speaker recognition, speech recognition 1. INTRODUCTION In modern speech processing systems, voice activity detection (V AD) usually lives in the upstream of other speech components such as speech recognition and speaker recognition. As a gating module, V AD not only improves the performance of downstream components by discarding non-speech signal, but also significantly reduces the overall computational cost due to its relatively small size.

Guided by artificial intelligence and powered by a robotic platform, a system developed by MIT researchers moves a step closer to automating the production of small molecules that could be used in medicine, solar energy, and polymer chemistry. The system, described in the August 8 issue of Science, could free up bench chemists from a variety of routine and time-consuming tasks, and may suggest possibilities for how to make new molecular compounds, according to the study co-leaders Klavs F. Jensen, the Warren K. Lewis Professor of Chemical Engineering, and Timothy F. Jamison, the Robert R. Taylor Professor of Chemistry and associate provost at MIT. The technology "has the promise to help people cut out all the tedious parts of molecule building," including looking up potential reaction pathways and building the components of a molecular assembly line each time a new molecule is produced, says Jensen. "And as a chemist, it may give you inspirations for new reactions that you hadn't thought about before," he adds. The new system combines three main steps.

We propose a predictive neural network architecture that can be utilized to update reference velocity models as inputs to full waveform inversion. Deep learning models are explored to augment velocity model building workflows during 3D seismic volume reprocessing in salt-prone environments. Specifically, a neural network architecture, with 3D convolutional, de-convolutional layers, and 3D max-pooling, is designed to take standard amplitude 3D seismic volumes as an input. Enhanced data augmentations through generative adversarial networks and a weighted loss function enable the network to train with few sparsely annotated slices. Batch normalization is also applied for faster convergence. Moreover, a 3D probability cube for salt bodies is generated through ensembles of predictions from multiple models in order to reduce variance. Velocity models inferred from the proposed networks provide opportunities for FWI forward models to converge faster with an initial condition closer to the true model. In each iteration step, the probability cubes of salt bodies inferred from the proposed networks can be used as a regularization term in FWI forward modelling, which may result in an improved velocity model estimation while the output of seismic migration can be utilized as an input of the 3D neural network for subsequent iterations.

Deep Reinforcement Learning has made significant progress in multi-agent systems in recent years. In this review article, we have mostly focused on recent papers on Multi-Agent Reinforcement Learning (MARL) than the older papers, unless it was necessary. Several ideas and papers are proposed with different notations, and we tried our best to unify them with a single notation and categorize them by their relevance. In particular, we have focused on five common approaches on modeling and solving multi-agent reinforcement learning problems: (I) independent-learners, (II) fully observable critic, (III) value function decomposition, (IV) consensus, (IV) learn to communicate. Moreover, we discuss some new emerging research areas in MARL along with the relevant recent papers. In addition, some of the recent applications of MARL in real world are discussed. Finally, a list of available environments for MARL research are provided and the paper is concluded with proposals on the possible research directions.

Unlike task-specific algorithms, Deep Learning is a part of Machine Learning family based on learning data representations. With massive amounts of computational power, machines can now recognize objects and translate speech in real time, enabling a smart Artificial intelligence in systems. The concept of a software simulating the neocortex's large array of neurons in an artificial neural network is decades old, and it has led to as many disappointments as breakthroughs. But because of improvements in mathematical formulas and increasingly powerful computers, today researchers & data scientists can model many more layers of virtual neurons than ever before. "Recent improvements in Deep Learning has reignited some of the grand challenges in Artificial Intelligence."

Guided by artificial intelligence and powered by a robotic platform, a system developed by MIT researchers moves a step closer to automating the production of small molecules that could be used in medicine, solar energy, and polymer chemistry. The system, described in the August 8 issue of Science, could free up bench chemists from a variety of routine and time-consuming tasks, and may suggest possibilities for how to make new molecular compounds, according to the study co-leaders Klavs F. Jensen, the Warren K. Lewis Professor of Chemical Engineering, and Timothy F. Jamison, the Robert R. Taylor Professor of Chemistry and associate provost at MIT. The technology "has the promise to help people cut out all the tedious parts of molecule building," including looking up potential reaction pathways and building the components of a molecular assembly line each time a new molecule is produced, says Jensen. "And as a chemist, it may give you inspirations for new reactions that you hadn't thought about before," he adds. The new system combines three main steps.

-- Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In this paper we present a novel approach for efficient exploration that leverages previously learned tasks. We exploit the fact that the same system is used across many tasks and build a generative model for exploration based on data from previously solved tasks to improve learning new tasks. The approach also enables continuous learning of improved exploration strategies as novel tasks are learned. Extensive simulations on a robot manipulator performing a variety of motion and contact interaction tasks demonstrate the capabilities of the approach. In particular, our experiments suggest that the exploration strategy can more than double learning speed, especially when rewards are sparse. Moreover, the algorithm is robust to task variations and parameter tuning, making it beneficial for complex robotic problems. I. INTRODUCTION Deep reinforcement learning has attracted a lot of attention for robotic applications where full robot models can be difficult to identify, especially for contact dynamics, and lead to computationally challenging planning and control problems.