I get it: On one hand, you want to be a resilient off-grid solarpunk freed from the yoke of your increasingly-unreliable power company. On the other, you'd still like to enjoy creature comforts both at home and when you're on the road. It's a problem EcoFlow understands, and has turned up to CES promising to help. The company is showing off a new Whole Home Backup Solution, which ties in to its existing Delta Pro batteries. But that's less interesting to me than the gizmos which are joining the ecosystem at today's show.

The latest leaps in artificial intelligence in everything from cars, robots to appliances will be on full display at the annual Consumer Electronics Show (CES) opening Thursday in Las Vegas. Forced by the pandemic to go virtual in 2021 and hybrid last year, tens of thousands of show-goers are hoping for a return to packed halls and rapid-fire deal-making that were long the hallmark of the annual gadget extravaganza. "In 2022, it was a shadow of itself-- empty halls, no meetings in hotel rooms," Avi Greengart, an analyst at Techspotential told AFP. "Now, (we expect) crowds, trouble getting around and meetings behind closed doors--which is what a trade show is all about." The CES show officially opens on January 5, but companies will begin to vie for the spotlight with the latest tech wizardry as early as Tuesday. CES will be spread over more than 18 acres (seven hectares), from the sprawling Las Vegas Convention Center to pavilions set up in parking lots.

Heliogen, a leading provider of AI-enabled concentrated solar energy, announced that on December 23, 2022, it received written notice from the New York Stock Exchange ("NYSE") that the average closing price of its common stock over the prior consecutive 30 trading-day period was below $1.00 per share, which is the minimum average share price for continued listing on the NYSE. Heliogen intends to respond to the NYSE within ten business days of receipt of the notice of its intent to cure the deficiency. Pursuant to the NYSE's rules, Heliogen has a six-month period following receipt of the deficiency letter to bring its share price and average share price back above $1.00. During the cure period, Heliogen's shares of common stock will continue to trade on the NYSE, subject to compliance with other continued listing requirements. The NYSE notification does not affect Heliogen's ongoing business operations or its Securities and Exchange Commission reporting requirements.

Global warming is partly due to the vast amount of carbon dioxide that we release, mostly from power generation and industrial processes, such as making steel and cement. For a while now, chemical engineers have been exploring carbon capture, a process that can separate carbon dioxide and store it in ways that keep it out of the atmosphere. This is done in dedicated carbon-capture plants, whose chemical process involves amines, compounds that are already used to capture carbon dioxide from natural gas processing and refining plants. Amines are also used in certain pharmaceuticals, epoxy resins, and dyes. The problem is that amines could be potentially harmful to the environment as well as a health hazard, making it essential to mitigate their impact.

In this paper, we focus on the simulation of active stereovision depth sensors, which are popular in both academic and industry communities. Inspired by the underlying mechanism of the sensors, we designed a fully physics-grounded simulation pipeline that includes material acquisition, ray-tracing-based infrared (IR) image rendering, IR noise simulation, and depth estimation. The pipeline is able to generate depth maps with material-dependent error patterns similar to a real depth sensor in real time. We conduct real experiments to show that perception algorithms and reinforcement learning policies trained in our simulation platform could transfer well to the real-world test cases without any fine-tuning. Furthermore, due to the high degree of realism of this simulation, our depth sensor simulator can be used as a convenient testbed to evaluate the algorithm performance in the real world, which will largely reduce the human effort in developing robotic algorithms. The entire pipeline has been integrated into the SAPIEN simulator and is open-sourced to promote the research of vision and robotics communities.

Fair resource allocation is one of the most important topics in communication networks. Existing solutions almost exclusively assume each user utility function is known and concave. This paper seeks to answer the following question: how to allocate resources when utility functions are unknown, even to the users? This answer has become increasingly important in the next-generation AI-aware communication networks where the user utilities are complex and their closed-forms are hard to obtain. In this paper, we provide a new solution using a distributed and data-driven bilevel optimization approach, where the lower level is a distributed network utility maximization (NUM) algorithm with concave surrogate utility functions, and the upper level is a data-driven learning algorithm to find the best surrogate utility functions that maximize the sum of true network utility. The proposed algorithm learns from data samples (utility values or gradient values) to autotune the surrogate utility functions to maximize the true network utility, so works for unknown utility functions. For the general network, we establish the nonasymptotic convergence rate of the proposed algorithm with nonconcave utility functions. The simulations validate our theoretical results and demonstrate the great effectiveness of the proposed method in a real-world network.

Urban metabolism is an active field of research that deals with the estimation of emissions and resource consumption from urban regions. The analysis could be carried out through a manual surveyor by the implementation of elegant machine learning algorithms. In this exploratory work, we estimate the water consumption by the buildings in the region captured by satellite imagery. To this end, we break our analysis into three parts: i) Identification of building pixels, given a satellite image, followed by ii) identification of the building type (residential/non-residential) from the building pixels, and finally iii) using the building pixels along with their type to estimate the water consumption using the average per unit area consumption for different building types as obtained from municipal surveys.

This talk will cover our particular use case and the workflow we used. This talk will cover our particular use case and the workflow we used. At addresscloud we have used OpenStreetMap building data in our main application for the UK but we've recently found the need to get this data on a global basis. Our main goal was to extract the building outlines that have been captured in OSM and push these into our datastore to use in our applications. We didn't want to do this for a whole country as the amount of data and time to upload could be costly. We looked at a few different solutions but wanted something that was easy to set up and use so went with the python library OSMnx. OSMnx is a Python package to retrieve, model, analyse, and visualise street networks and other geometries from OpenStreetMap. In a single line of code, OSMnx lets you download spatial geometries, place boundaries, buildings footprints, or points of interest as a GeoDataFrame. This talk will look at the different options available in terms of downloading the data .i.e by city name, polygon, bounding box, or point/address plus distance. It will then show how we added geopandas into the workflow to export the data for use in our wider ecosystem. Finally we will look at the whole workflow and show how easily you can use OSMnx and geopandas in real world applications. Example code snippets will be shown for people to get an idea of how they can make use of OSMnx. Geospatial technologist who loves working with data and creating workflows with open source tools and scripting in python, nodejs and bash. The talk presents AROSICS and SpecHomo, two open-source and easy-to-use Python packages for automated and robust geometric and spectral fusion of multi-sensor, multi-spectral satellite images.

This paper presents an approach for learning Model Predictive Control (MPC) schemes directly from data using Reinforcement Learning (RL) methods. The state-of-the-art learning methods use RL to improve the performance of parameterized MPC schemes. However, these learning algorithms are often gradient-based methods that require frequent evaluations of computationally expensive MPC schemes, thereby restricting their use on big datasets. We propose to tackle this issue by using tools from RL to learn a parameterized MPC scheme directly from data in an offline fashion. Our approach derives an MPC scheme without having to solve it over the collected dataset, thereby eliminating the computational complexity of existing techniques for big data. We evaluate the proposed method on three simulated experiments of varying complexity.

Dynamically typed languages such as Python have become very popular. Among other strengths, Python's dynamic nature and its straightforward linking to native code have made it the de-facto language for many research areas such as Artificial Intelligence. This flexibility, however, makes static analysis very hard. While creating a sound, or a soundy, analysis for Python remains an open problem, we present in this work Serenity, a framework for static analysis of Python that turns out to be sufficient for some tasks. The Serenity framework exploits two basic mechanisms: (a) reliance on dynamic dispatch at the core of language translation, and (b) extreme abstraction of libraries, to generate an abstraction of the code. We demonstrate the efficiency and usefulness of Serenity's analysis in two applications: code completion and automated machine learning. In these two applications, we demonstrate that such analysis has a strong signal, and can be leveraged to establish state-of-the-art performance, comparable to neural models and dynamic analysis respectively.