For a long, long time, renewable energy proponents have considered advancements in battery technology to be the Holy Grail of the industry. Advancements in energy storage has been among the hardest to achieve economically, thanks to the incredibly tricky chemistry that's involved in storing power. Now, one company that's launching from Y Combinator believes it has found the key to making batteries better. The company is called Holy Grail and it's launching in the accelerator's latest cohort. With an executive team that initially included Nuno Pereira, David Pervan and Martin Hansen, Holy Grail is trying to bring the techniques of the fabless semiconductor industry to the world of batteries.

By Laure-Anne Pessina and Nicola Nosengo Scientists at EPFL have developed a tiny pump that could play a big role in the development of autonomous soft robots, lightweight exoskeletons and smart clothing. Flexible, silent and weighing only one gram, it is poised to replace the rigid, noisy and bulky pumps currently used. The scientists' work has just been published in Nature. Soft robots have a distinct advantage over their rigid forebears: they can adapt to complex environments, handle fragile objects and interact safely with humans. Made from silicone, rubber or other stretchable polymers, they are ideal for use in rehabilitation exoskeletons – such as the ones being developed in the NCCR Robotics "Wearable Robotics" research line – and robotic clothing.

As oceans are altered by rising temperatures, acidification and other consequences of anthropogenic activity, understanding the behavioral patterns and responses of marine animals is required for effective stewardship. Researchers have made great strides in investigating marine megafauna behavior related to long-distance migrations (Block et al., 2011; Rasmussen et al., 2007; Sequeira et al., 2018) and foraging strategies (Sims et al., 2008; Weise et al., 2010). However, the behavior of more numerous, higher total-biomass, lower trophic-level animals such as zooplankton is much less well understood. Early attempts to investigate in situ behavior of zooplankton such as jellyfish relied on scuba divers following animals with hand-held video cameras (Colin and Costello, 2002; Costello et al., 1998) and later with remotely operated vehicles (ROVs; Kaartvedt et al., 2015; Purcell, 2009; Rife and Rock, 2003). Acoustic methods have also been used to describe large-scale movement patterns of jellyfish (Båmstedt et al., 2003; Kaartvedt et al., 2007; Klevjer et al., 2009), although these methods can be resolution-limited.

The battery is a key component of autonomous robots. Its performance limits the robot's safety and reliability. Unlike liquid-fuel, a battery, as a chemical device, exhibits complicated features, including (i) capacity fade over successive recharges and (ii) increasing discharge rate as the state of charge (SOC) goes down for a given power demand. Existing formal verification studies of autonomous robots, when considering energy constraints, formalise the energy component in a generic manner such that the battery features are overlooked. In this paper, we model an unmanned aerial vehicle (UA V) inspection mission on a wind farm and via probabilistic model checking in PRISM show (i) how the battery features may affect the verification results significantly in practical cases; and (ii) how the battery features, together with dynamic environments and battery safety strategies, jointly affect the verification results. Potential solutions to explicitly integrate battery prognostics and health management (PHM) with formal verification of autonomous robots are also discussed to motivate future work. Keywords: Formal verification · Probabilistic model checking · PRISM · Autonomous systems · Unmanned aerial vehicle · Battery PHM. 1 Introduction Autonomous robots, such as unmanned aerial vehicles (UA V) (commonly termed drones 3), unmanned underwater vehicles (UUV), self-driving cars and legged-robots, obtain increasingly widespread applications in many domains [14].

A latent function decomposition method is proposed for forecasting the capacity of lithium-ion battery cells. The method uses the Multi-Output Gaussian Process, a generative machine learning framework for multi-task and transfer learning. The MCGP decomposes the available capacity trends from multiple battery cells into latent functions. The latent functions are then convolved over kernel smoothers to reconstruct and/or forecast capacity trends of the battery cells. Besides the high prediction accuracy the proposed method possesses, it provides uncertainty information for the predictions and captures nontrivial cross-correlations between capacity trends of different battery cells. These two merits make the proposed MCGP a very reliable and practical solution for applications that use battery cell packs. The MCGP is derived and compared to benchmark methods on an experimental lithium-ion battery cells data. The results show the effectiveness of the proposed method.

Alexa-enabled devices like the Echo or Echo Dot can be used to control smart home products such as the Ring Alarm Kit. If you make a purchase by clicking one of our links, we may earn a small share of the revenue. Our picks and opinions are independent from USA TODAY's newsroom and any business incentives. Prime Day is a great opportunity to find money-saving deals on smart home products that can be controlled using Amazon Alexa on your Echo device. From smart doorbells to pressure cookers, here are the best Alexa-compatible Prime Day deals of 2019.

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

The aluminum-bodied robot weighs in at 16.5 kg (36 lb), and can run for a claimed five hours on one eight-hour charge of its user-swappable 28.8-V/7.2-Ah And while the prototype that we saw in Montreal at the 2019 International Conference on Robotics and Automation had six dual-purpose composite "legs," more swimming-efficient vinyl/steel-spring flippers can be substituted if it's going to only be used underwater – a place where it should be more eco-friendly than traditional remote-operated vehicles (ROVs).

Last year RISC-V cores made it into low-cost hardware with neural network and audio accelerator to speed up artificial intelligence workloads at the edge such as object recognition, and speech processing. More precisely, Kendryte K210 dual-core RISC-V processor was found in Sipeed MAIX modules and boards going for $5 and up. Since then a few other variants and kits have been made available including Seeed Studio Grove AI HAT that works connected to a Raspberry Pi or in standalone mode. Seeed Studio has now released another board with Kendryte K210 RISC-V AI processor, but based on Arduino UNO form factor and equipped with an ESP32 module for WiFi and Bluetooth connectivity. Typical applications would include smart home (robot cleaners or smart speakers), medical devices, factory 4.0 (intelligent sorting or monitoring of electrical equipment), as well as agriculture, and education.

Visual inspection of underwater structures by vehicles, e.g. remotely operated vehicles (ROVs), plays an important role in scientific, military, and commercial sectors. However, the automatic extraction of information using software tools is hindered by the characteristics of water which degrade the quality of captured videos. As a contribution for restoring the color of underwater images, Underwater Denoising Autoencoder (UDAE) model is developed using a denoising autoencoder with U-Net architecture. The proposed network takes into consideration the accuracy and the computation cost to enable real-time implementation on underwater visual tasks using end-to-end autoencoder network. Underwater vehicles perception is improved by reconstructing captured frames; hence obtaining better performance in underwater tasks. Related learning methods use generative adversarial networks (GANs) to generate color corrected underwater images, and to our knowledge this paper is the first to deal with a single autoencoder capable of producing same or better results. Moreover, image pairs are constructed for training the proposed network, where it is hard to obtain such dataset from underwater scenery. At the end, the proposed model is compared to a state-of-the-art method.