Edge intelligence is an emerging paradigm for real-time training and inference at the wireless edge, thus enabling mission-critical applications. Accordingly, base stations (BSs) and edge servers (ESs) need to be densely deployed, leading to huge deployment and operation costs, in particular the energy costs. In this article, we propose a new framework called Mobility-Enhanced Edge inTelligence (MEET), which exploits the sensing, communication, computing, and self-powering capabilities of intelligent connected vehicles for the smart and green 6G networks. Specifically, the operators can incorporate infrastructural vehicles as movable BSs or ESs, and schedule them in a more flexible way to align with the communication and computation traffic fluctuations. Meanwhile, the remaining compute resources of opportunistic vehicles are exploited for edge training and inference, where mobility can further enhance edge intelligence by bringing more compute resources, communication opportunities, and diverse data. In this way, the deployment and operation costs are spread over the vastly available vehicles, so that the edge intelligence is realized cost-effectively and sustainably. Furthermore, these vehicles can be either powered by renewable energy to reduce carbon emissions, or charged more flexibly during off-peak hours to cut electricity bills. Yuxuan Sun is with School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China, and was previously with Tsinghua University. Bowen Xie, Sheng Zhou (Corresponding Author) and Zhisheng Niu are with Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.

Reasoning with occluded traffic agents is a significant open challenge for planning for autonomous vehicles. Recent deep learning models have shown impressive results for predicting occluded agents based on the behaviour of nearby visible agents; however, as we show in experiments, these models are difficult to integrate into downstream planning. To this end, we propose Bi-level Variational Occlusion Models (BiVO), a two-step generative model that first predicts likely locations of occluded agents, and then generates likely trajectories for the occluded agents. In contrast to existing methods, BiVO outputs a trajectory distribution which can then be sampled from and integrated into standard downstream planning. We evaluate the method in closed-loop replay simulation using the real-world nuScenes dataset. Our results suggest that BiVO can successfully learn to predict occluded agent trajectories, and these predictions lead to better subsequent motion plans in critical scenarios.

This article presents the design, implementation, and performance evaluation of SWheg, a novel modular wheel-leg transformable robot family with minimalist actuator realization. SWheg takes advantage of both wheeled and legged locomotion by seamlessly integrating them on a single platform. In contrast to other designs that use multiple actuators, SWheg uses only one actuator to drive the transformation of all the wheel-leg modules in sync. This means an N-legged SWheg robot requires only N+1 actuators, which can significantly reduce the cost and malfunction rate of the platform. The tendon-driven wheel-leg transformation mechanism based on a four-bar linkage can perform fast morphology transitions between wheels and legs. We validated the design principle with two SWheg robots with four and six wheel-leg modules separately, namely Quadrupedal SWheg and Hexapod SWheg. The design process, mechatronics infrastructure, and the gait behavioral development of both platforms were discussed. The performance of the robot was evaluated in various scenarios, including driving and turning in wheeled mode, step crossing, irregular terrain passing, and stair climbing in legged mode. The comparison between these two platforms was also discussed.

"Everything we love about civilization is a product of intelligence, so amplifying our human intelligence with artificial intelligence has the potential of helping civilization flourish like never before - as long as we manage to keep the technology beneficial." From SIRI to self-driving cars, artificial intelligence (AI) is progressing rapidly. While science fiction often portrays AI as robots with human-like characteristics, AI can encompass anything from Google's search algorithms to IBM's Watson to autonomous weapons. Artificial intelligence today is properly known as narrow AI (or weak AI), in that it is designed to perform a narrow task (e.g. However, the long-term goal of many researchers is to create general AI (AGI or strong AI).

There is vast potential for AI, 5G and the Metaverse to be applied towards advancing the Environment, Social and Governance (ESG) cause, including Sustainability. Our global economy is facing challenges and the tragic warfare in Ukraine has had consequential impacts on energy supply for much of Europe and beyond. Indeed, McKinsey forecast that $275 Trillion may have to be spent in the period to 2050 (ranging from circa 7% to 9% of global GDP) to achieve carbon next zero. There is a strategic imperative for the EU, UK and the US (following the adoption of the Inflation Reduction Act in 2022) to push for accelerating the scaling and adoption of renewable energy and advancing battery storage technology at a time when action on Climate Change is a high priority and also the need to diversify energy supplies is growing. AI technology may play a key role in helping scale these areas.

Artificial Intelligence is a technology that simulates human intelligence processes by machines and computer systems. There's a plethora of different Artificial Intelligence applications including natural language processing, deep learning and speech recognition just to name a few. In 2023 all companies will be under pressure to reduce their carbon footprint and minimize their impact on the environment. In this respect, the race to adopt and profit from AI can be both a blessing and a hindrance. AI algorithms – as well as all the infrastructure needed to support and deliver them, such as cloud networks and edge devices – require increasing amounts of power and resources.

In this blog, we will conduct picture segmentation on a very limited dataset using U-Net, a popular segmentation CNN model. There will also be some customized loss functions used for training reasons, such as dice loss and Jaccard index metrics. The data that we will be working with comes from kaggle. The dataset is called Semantic segmentation of aerial imagery. The dataset has two sorts of files .jpg

The race to remove CO2 from our atmosphere is on. In an effort to draw down carbon at a meaningful scale, people are looking to the ground. The top meter of the world's soil holds over three times the amount of carbon currently in our atmosphere--and if we treat our land better, it could suck up even more. This is good news for farmers. Companies and individuals desperate to offset their emissions by purchasing carbon credits are willing to pay farmers to use sustainable agricultural practices and sequester carbon in their fields.

Improving irradiance forecasting is critical to further increase the share of solar in the energy mix. On a short time scale, fish-eye cameras on the ground are used to capture cloud displacements causing the local variability of the electricity production. As most of the solar radiation comes directly from the Sun, current forecasting approaches use its position in the image as a reference to interpret the cloud cover dynamics. However, existing Sun tracking methods rely on external data and a calibration of the camera, which requires access to the device. To address these limitations, this study introduces an image-based Sun tracking algorithm to localise the Sun in the image when it is visible and interpolate its daily trajectory from past observations. We validate the method on a set of sky images collected over a year at SIRTA's lab. Experimental results show that the proposed method provides robust smooth Sun trajectories with a mean absolute error below 1% of the image size.

Proportional-integral-derivative (PID) control underlies more than $97\%$ of automated industrial processes. Controlling these processes effectively with respect to some specified set of performance goals requires finding an optimal set of PID parameters to moderate the PID loop. Tuning these parameters is a long and exhaustive process. A method (patent pending) based on deep reinforcement learning is presented that learns a relationship between generic system properties (e.g. resonance frequency), a multi-objective performance goal and optimal PID parameter values. Performance is demonstrated in the context of a real optical switching product of the foremost manufacturer of such devices globally. Switching is handled by piezoelectric actuators where switching time and optical loss are derived from the speed and stability of actuator-control processes respectively. The method achieves a $5\times$ improvement in the number of actuators that fall within the most challenging target switching speed, $\geq 20\%$ improvement in mean switching speed at the same optical loss and $\geq 75\%$ reduction in performance inconsistency when temperature varies between 5 and 73 degrees celcius. Furthermore, once trained (which takes $\mathcal{O}(hours)$), the model generates actuator-unique PID parameters in a one-shot inference process that takes $\mathcal{O}(ms)$ in comparison to up to $\mathcal{O}(week)$ required for conventional tuning methods, therefore accomplishing these performance improvements whilst achieving up to a $10^6\times$ speed-up. After training, the method can be applied entirely offline, incurring effectively zero optimisation-overhead in production.