We present IS-MPC, an intrinsically stable MPC framework for humanoid gait generation which incorporates an explicit stability constraint in the formulation. The proposed method uses as prediction model a dynamically extended LIP where ZMP velocities are the control inputs, producing in real time a gait (including footsteps with the associated timing) that realizes omnidirectional motion commands coming from an external source. The stability constraint links the future ZMP velocities to the current system state so as to guarantee the essential requirement that the generated CoM trajectory is bounded with respect to the ZMP trajectory. Since the control horizon of the MPC algorithm is finite, only part of the future ZMP velocities are decision variables of the QP problem; the remaining part, called tail, must be either conjectured or anticipated using preview information on the reference motion. Several possible options for the tail are discussed, and each of them is shown to correspond to a specific terminal constraint. A theoretical analysis of the feasibility of the generic MPC iteration is developed and used to obtain sufficient conditions for recursive feasibility. Finally, it is proved that IS-MPC guarantees stability of the CoM/ZMP dynamics if it is recursively feasible. Simulation and experimental results on the NAO and the HRP-4 humanoids are presented to illustrate the performance of the proposed method.

Despite the promising results of convolutional neural networks (CNNs), applying them on resource limited devices is still a challenge, mainly due to the huge memory and computation requirements. To tackle these problems, pruning can be applied to reduce the network size and number of floating point operations (FLOPs). Contrary to the \emph{filter norm} method -- that is used in network pruning and uses the assumption that the smaller this norm, the less important is the associated component --, we develop a novel filter importance norm that incorporates the loss caused by the elimination of a component from the CNN. To estimate the importance of a set of architectural components, we measure the CNN performance as different components are removed. The result is a collection of filter ensembles -- filter masks -- and associated performance values. We rank the filters based on a linear and additive model and remove the least important ones such that the drop in network accuracy is minimal. We evaluate our method on a fully connected network, as well as on the ResNet architecture trained on the CIFAR-10 data-set. Using our pruning method, we managed to remove $60\%$ of the parameters and $64\%$ of the FLOPs from the ResNet with an accuracy drop of less than $0.6\%$.

We present a general numerical approach for learning unknown dynamical systems using deep neural networks (DNNs). Our method is built upon recent studies that identified the residue network (ResNet) as an effective neural network structure. In this paper, we present a generalized ResNet framework and broadly define residue as the discrepancy between observation data and prediction made by another model, which can be an existing coarse model or reduced-order model. In this case, the generalized ResNet serves as a model correction to the existing model and recovers the unresolved dynamics. When an existing coarse model is not available, we present numerical strategies for fast creation of coarse models, to be used in conjunction with the generalized ResNet. These coarse models are constructed using the same data set and thus do not require additional resources. The generalized ResNet is capable of learning the underlying unknown equations and producing predictions with accuracy higher than the standard ResNet structure. This is demonstrated via several numerical examples, including long-term prediction of a chaotic system.

A FUTURISTIC city designed by Danish architecture practice Bjarke Ingels Group (BIG) and featuring autonomous cars, smart homes, artificial intelligence and other technologies is set to be constructed at the base of Japan's Mount Fuji. Above: The city will have substantial public spaces (image courtesy of Toyota). The so-called "City of the Future" prototype will be constructed on a 175-acre site by Toyota. Toyota will use its technologies to create a fully connected ecosystem powered by hydrogen fuel cells. The city will house over 2,000 full-time residents and researchers.

The concept of the circular economy is designed to replace the end-of-life economic system with restoration, use of renewable energy, and the elimination of waste through the better design of materials, products, systems and business models. Most leading organizations worldwide have begun identifying feasible opportunities in adopting sustainable business practices, embracing circular business models and leveraging disruptive technologies. For city planners, businesses and policymakers, a smart city transformation from the current economic model, knows as linear economy, to a circular economy encompasses high complexity. They need to consider material and energy, product design, business models, manufacturing, service and distribution processes and data management and more. However, embracing artificial intelligence in a circular economy can expedite the efforts of a smart city project needs, creating ways to accomplish sustainable development goals.

Sellafield are seeking to innovate in the way they analyse Health, Safety and Environmental data to improve insight, trend analysis and early prediction of safety issues. The data which needs to be analysed includes safety observations, assurance activities, assurance action tracking information, accident reports and unsafe condition reports. Applications are invited for technological solutions to meet this challenge. The deadline for applications is Friday 24th January at 12 noon. Sellafield are exploring the use of Machine Learning (ML) to help analyse health, safety and environmental data to improve prediction of risk.

There is a definition of a Fourth Industrial Revolution (4IR) as the age of digitalization. This is making smart cities, vastly improved factories and a lot of automation of tasks and services in our homes and at work. Industry 4.0 enables real-time data gathering, analysis, and decision- and prediction-making capabilities. Nextbigfuture would indicate that this 4IR is just an extension of the third industrial revolution of computers and robotic automation. The adoption levels of computers and robots are too low and the impact on factory and production levels has not reached the level of improvements reached by the Ford factories and oil machinery over the steam age.

There's a dire need to speed the planet's shift to clean energy - and the power of Artificial Intelligence can help. The world has gone through a number of energy transformations – from wood to coal, then to oil, gas and (partly) nuclear. These shifts were gradual and contingent on economic conditions. Now major efforts are under way to reform the global energy sector to make it low-carbon, non-nuclear and climate-compatible. But, unlike the previous transformations, the ongoing restructuring process is driven by elevated awareness of the disastrous consequences of climate change. Notwithstanding the global efforts made to revolutionise the energy business (to make it capable of coping with the variability inherent in most renewable energy generation technologies), there is still a dire need to speed up the shift to clean energy solutions.

We introduce Lyceum, a high-performance computational ecosystem for robot learning. Lyceum is built on top of the Julia programming language and the MuJoCo physics simulator, combining the ease-of-use of a high-level programming language with the performance of native C. In addition, Lyceum has a straightforward API to support parallel computation across multiple cores and machines. Overall, depending on the complexity of the environment, Lyceum is 5-30x faster compared to other popular abstractions like OpenAI's Gym and DeepMind's dm-control. This substantially reduces training time for various reinforcement learning algorithms; and is also fast enough to support real-time model predictive control through MuJoCo. The code, tutorials, and demonstration videos can be found at: www.lyceum.ml.

Predicting outcomes and planning interactions with the physical world are long-standing goals for machine learning. A variety of such tasks involves continuous physical systems, which can be described by partial differential equations (PDEs) with many degrees of freedom. Existing methods that aim to control the dynamics of such systems are typically limited to relatively short time frames or a small number of interaction parameters. We present a novel hierarchical predictor-corrector scheme which enables neural networks to learn to understand and control complex nonlinear physical systems over long time frames. We propose to split the problem into two distinct tasks: planning and control. To this end, we introduce a predictor network that plans optimal trajectories and a control network that infers the corresponding control parameters. Both stages are trained end-to-end using a differentiable PDE solver. We demonstrate that our method successfully develops an understanding of complex physical systems and learns to control them for tasks involving PDEs such as the incompressible Navier-Stokes equations.