Battery discharge capacity forecasting is critically essential for the applications of lithium-ion batteries. The capacity degeneration can be treated as the memory of the initial battery state of charge from the data point of view. The streaming sensor data collected by battery management systems (BMS) reflect the usable battery capacity degradation rates under various operational working conditions. The battery capacity in different cycles can be measured with the temporal patterns extracted from the streaming sensor data based on the attention mechanism. The attention-based similarity regarding the first cycle can describe the battery capacity degradation in the following cycles. The deep degradation network (DDN) is developed with the attention mechanism to measure similarity and predict battery capacity. The DDN model can extract the degeneration-related temporal patterns from the streaming sensor data and perform the battery capacity prediction efficiently online in real-time. Based on the MIT-Stanford open-access battery aging dataset, the root-mean-square error of the capacity estimation is 1.3 mAh. The mean absolute percentage error of the proposed DDN model is 0.06{\%}. The DDN model also performance well in the Oxford Battery Degradation Dataset with dynamic load profiles. Therefore, the high accuracy and strong robustness of the proposed algorithm are verified.

Li-Ion Solid-State Electrolytes (Li-SSEs) are a promising solution that resolves the critical issues of conventional Li-Ion Batteries (LIBs) such as poor ionic conductivity, interfacial instability, and dendrites growth. In this study, a platform consisting of a high-throughput screening and a machine-learning surrogate model for discovering superionic Li-SSEs among 20,237 Li-containing materials is developed. For the training database, the ionic conductivity of Na SuperIonic CONductor (NASICON) and Li SuperIonic CONductor (LISICON) type SSEs are obtained from the previous literature. Then, the chemical descriptor (CD) and additional structural properties are used as machine-readable features. Li-SSE candidates are selected through the screening criteria, and the prediction on the ionic conductivity of those is followed. Then, to reduce uncertainty in the surrogate model, the ensemble method by considering the best-performing two models is employed, whose mean prediction accuracy is 0.843 and 0.829, respectively. Furthermore, first-principles calculations are conducted for confirming the ionic conductivity of the strong candidates. Finally, six potential superionic Li-SSEs that have not previously been investigated are proposed. We believe that the constructed platform can accelerate the search for Li-SSEs with high ionic conductivity at minimum cost.

There are a half dozen refrigerator-sized cabinets inside a lab at Stanford University's Precourt Institute for energy that is designed for killing bacteria as quickly as possible. Each contains around 100 lithium-ion cells in trays in which the batteries could be charged and discharged dozens of times each day. The batteries used in these electrochemical torture chambers would normally be found in electronics or electric vehicles. Instead, energy is transported in and out of these cells as quickly as possible, generating reams of performance data that artificial intelligence can use to learn how to make a better battery. To estimate how a battery would perform in the future, AI would require data from a battery after it had begun to degrade. It could take months to cycle the battery enough times to get the required data.

We're still quite a ways away from wielding proper Power Loaders but advances in exosuit technology are rapidly changing how people perform physical tasks in their daily lives -- some designed to help rehabilitate spinal injury patients, others created to improve a Marine's warfighting capabilities, and many built simply to make physically repetitive vocations less stressful for the people performing them. But German Bionic claims only one of them is intelligent enough to learn from its users' mistaken movements: its 5th-generation Cray X. The Cray X fits on workers like a 7kg backpack with hip-mounted actuators that move carbon fiber linkages strapped to the upper legs, allowing a person to easily lift and walk with up to 30kg (66 lbs) with both their legs and backs fully supported. Though it doesn't actively assist the person's shoulders and arms with the task, the Cray X does offer a Smart Safety Companion system to help mitigate common lifting injuries. "It's a real time software application that runs in the background and can warn the worker when the ergonomic risk is getting too high," Norma Steller, German Bionic's Head of IoT, told Engadget.

Prescribing optimal operation based on the condition of the system and, thereby, potentially prolonging the remaining useful lifetime has a large potential for actively managing the availability, maintenance and costs of complex systems. Reinforcement learning (RL) algorithms are particularly suitable for this type of problems given their learning capabilities. A special case of a prescriptive operation is the power allocation task, which can be considered as a sequential allocation problem, where the action space is bounded by a simplex constraint. A general continuous action-space solution of such sequential allocation problems has still remained an open research question for RL algorithms. In continuous action-space, the standard Gaussian policy applied in reinforcement learning does not support simplex constraints, while the Gaussian-softmax policy introduces a bias during training. In this work, we propose the Dirichlet policy for continuous allocation tasks and analyze the bias and variance of its policy gradients. We demonstrate that the Dirichlet policy is bias-free and provides significantly faster convergence, better performance and better hyperparameters robustness over the Gaussian-softmax policy. Moreover, we demonstrate the applicability of the proposed algorithm on a prescriptive operation case, where we propose the Dirichlet power allocation policy and evaluate the performance on a case study of a set of multiple lithium-ion (Li-I) battery systems. The experimental results show the potential to prescribe optimal operation, improve the efficiency and sustainability of multi-power source systems.

Wearable devices that integrate multiple sensors, processors, and communication technologies have the potential to transform mobile health for remote monitoring of health parameters. However, the small form factor of the wearable devices limits the battery size and operating lifetime. As a result, the devices require frequent recharging, which has limited their widespread adoption. Energy harvesting has emerged as an effective method towards sustainable operation of wearable devices. Unfortunately, energy harvesting alone is not sufficient to fulfill the energy requirements of wearable devices. This paper studies the novel problem of adaptive energy management towards the goal of self-sustainable wearables by using harvested energy to supplement the battery energy and to reduce manual recharging by users. To solve this problem, we propose a principled algorithm referred as AdaEM. There are two key ideas behind AdaEM. First, it uses machine learning (ML) methods to learn predictive models of user activity and energy usage patterns. These models allow us to estimate the potential of energy harvesting in a day as a function of the user activities. Second, it reasons about the uncertainty in predictions and estimations from the ML models to optimize the energy management decisions using a dynamic robust optimization (DyRO) formulation. We propose a light-weight solution for DyRO to meet the practical needs of deployment. We validate the AdaEM approach on a wearable device prototype consisting of solar and motion energy harvesting using real-world data of user activities. Experiments show that AdaEM achieves solutions that are within 5% of the optimal with less than 0.005% execution time and energy overhead.

Energy harvesting (EH) IoT devices that operate intermittently without batteries, coupled with advances in deep neural networks (DNNs), have opened up new opportunities for enabling sustainable smart applications. Nevertheless, implementing those computation and memory-intensive intelligent algorithms on EH devices is extremely difficult due to the challenges of limited resources and intermittent power supply that causes frequent failures. To address those challenges, this paper proposes a methodology that enables fast deep learning with low-energy accelerators for tiny energy harvesting devices. We first propose $RAD$, a resource-aware structured DNN training framework, which employs block circulant matrix and structured pruning to achieve high compression for leveraging the advantage of various vector operation accelerators. A DNN implementation method, $ACE$, is then proposed that employs low-energy accelerators to profit maximum performance with small energy consumption. Finally, we further design $FLEX$, the system support for intermittent computation in energy harvesting situations. Experimental results from three different DNN models demonstrate that $RAD$, $ACE$, and $FLEX$ can enable fast and correct inference on energy harvesting devices with up to 4.26X runtime reduction, up to 7.7X energy reduction with higher accuracy over the state-of-the-art.

Car owners may soon be able to start up their cars using a face biometrics ignition solution rather than their car keys. This is possible thanks to the development of a system by LG Electronics which enables a car owner to start their car by having their facial expressions and finger movements recognized using in-built cameras, reports Digitimes. Explaining how the system works, the report states that the car owner's specific body parts are captured with one camera, and informs adjustments by the other camera, which captures their iris and other biometric characteristics. The car owner can then start up their cars and make certain controls to it using facial expressions and hand gestures. The report adds that the system is able to detect if a driver is tired or abruptly takes ill, from their facial and hand gestures as they drive.

Recent backscatter communication techniques enable ultra low power wireless devices that operate without batteries while interoperating directly with unmodified commodity wireless devices. Commodity devices cooperate in providing the unmodulated carrier that the battery-free nodes need to communicate while collecting energy from their environment to perform sensing, computation, and communication tasks. The optimal provision of the unmodulated carrier limits the size of the network because it is an NP-hard combinatorial optimization problem. Consequently, previous works either ignore carrier optimization altogether or resort to suboptimal heuristics, wasting valuable energy and spectral resources. We present DeepGANTT, a deep learning scheduler for battery-free devices interoperating with wireless commodity ones. DeepGANTT leverages graph neural networks to overcome variable input and output size challenges inherent to this problem. We train our deep learning scheduler with optimal schedules of relatively small size obtained from a constraint optimization solver. DeepGANTT not only outperforms a carefully crafted heuristic solution but also performs within ~3% of the optimal scheduler on trained problem sizes. Finally, DeepGANTT generalizes to problems more than four times larger than the maximum used for training, therefore breaking the scalability limitations of the optimal scheduler and paving the way for more efficient backscatter networks.

Coco, the robot based delivery service, announced the official launch of COCO 1, a larger, more advanced version of its signature pink bot. The COCO 1 is a first of its kind delivery robot designed and manufactured in partnership with the largest micro mobility hardware manufacturer, Segway. Coco is currently deploying 1,000s of COCO 1 robots to serve local merchants in multiple cities, over the next few months. With its increased carrying capacity, the COCO 1 will deliver larger orders for a wider range of merchants, further eliminating the need for car-based delivery. Compared to the current model, the COCO 1 offers a number of added features including a more efficient drivetrain and a larger battery capacity that allows for an increased delivery radius of up to three miles, nearly double the radius of the original model.