Now we were able start a training job from the command line with the option to modify almost everything on the fly. We could adjust things like number of epochs, batch size, shuffling, checkpoint saving and even switch between model architectures easily, by adding a flag after the command. This allowed us to iterate fast, test different theories, and burn through a lot of (free) credits. We' built our model with tf.Keras using the functional API. We feed the array and scalar features into the model at separate entry points, so we can do different things to them before bringing them back together.

Tesla's battery research partner has released a new paper on a battery cell that could last over 1 million miles, which they say is going to be particularly useful in'robot taxis' -- something that Tesla wants to bring to market. When talking about the economics of Tesla's future fleet of robotaxis at the Tesla Autonomy Event, Tesla CEO Elon Musk emphasized that the vehicles need to be durable in order for the economics to work: The cars currently built are all designed for a million miles of operation. The drive unit is design, tested, and validated for 1 million miles of operation. But the CEO admitted that the battery packs are not built to last 1 million miles. Earlier this year, Musk said that they built Model 3 to last as long as a commercial truck, a million miles, and the battery modules should last between 300,000 miles and 500,000 miles.

Predict, manage and improve the life of lithium-ion batteries with Edison Analytics. Leverage data science, machine learning & digital twin to access real-time battery Intelligence insights. Edison Analytics is enabling battery pack makers, electric fleet managers, OEMs, and ESS providers across the world to acquire better ROI through all stages of the battery lifecycle. The full-stack advanced battery management and intelligence SaaS platform solution blend advanced electronics and machine learning with deep domain expertise in energy storage. At ION, we believe that technology needs to be developed keeping in mind the domain and the business.

In its next major breakthrough, Artificial Intelligence (AI) is defined to interrupt the battery technology distance, by combining the power of predictive intelligence and information analytics to accomplish high-performance and operational reliability. OEMs, battery pack makers, electrical fleet supervisors, and Electric Vehicle (EV) manufacturers will leverage AI, information engineering and machine learning how to remarkably enhance the battery's functionality & acquire much better ROI through all phases of the battery life cycle. With significant development and conscious efforts being led towards sustainable living and authorities pushing for fresh freedom, the worldwide EV market has been valued is estimated to reach 567,299.8 million by 2025, increasing at a CAGR of 22.3percent from 2018 to 2025. The EV uptake indicates a substantial transition in battery production volumes and improved investment in battery technologies, which is critical as EVs are costly and the price of the battery figures to 40 percent of the entire vehicle price. Lithium-ion batteries, that power high-resolution solutions such as EVs, houses & big solar/wind micro-grids, have among the maximum energy densities of almost any battery technology, a comparatively low self-discharge, & needs minimal maintenance.

Syntiant, an Irvine, California-based startup with big name backers like Intel and Microsoft, said its custom chips could be used to push Amazon's Alexa into smaller, battery-powered devices like wearables and wireless headphones that wake themselves up when they hear the voice assistant's wake word or other commands. Amazon just approved its deep learning accelerators for use with Alexa Voice Services (AVS). The company's NDP100 can be programmed to continuously listen for 64 wake words or specific sounds--like glass breaking or a baby crying--with power consumption in the range of 150 uW and more than 100 KB of SRAM. "These chips are purpose-built for keyword spotting such as wake words like Alexa, and now our processors can be used for quickly developing voice applications in battery-powered devices," chief executive Kurt Busch said in a statement. Syntiant, which was founded by former engineering executives from Broadcom, has raised over $30 million in funding from investors including Microsoft's M12, Amazon's Alexa Fund, Applied Ventures, Intel Capital, Motorola Ventures, and Robert Bosch Venture Capital.

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.