Co-evolving embodied intelligence with design for artificial intelligence architecture
Related Articles
Rising greenhouse gas emissions embodied in the global bioeconomy supply chain
The bioeconomy is key to meeting climate targets. Here, we examine greenhouse gas emissions in the global bioeconomy supply chain (1995–2022) using advanced multi-regional input-output analysis and a global land-use change model. Considering agriculture, forestry, land use, and energy, we assess the carbon footprint of biomass production and examine its end-use by provisioning systems. The footprint increased by 3.3 Gt CO2-eq, with 80% driven by international trade, mainly beef and biochemicals (biofuels, bioplastics, rubber). Biochemicals showed the largest relative increase, doubling due to tropical land-use change (feedstock cultivation) and China’s energy-intensive processing. Food from retail contributes most to the total biomass carbon footprint, while food from restaurants and canteens account for >50% of carbon-footprint growth, with three times higher carbon intensity than retail. Our findings emphasize the need for sustainable sourcing strategies and that adopting renewables and halting land-use change could reduce the bioeconomy carbon footprint by almost 60%.
An Integrative lifecycle design approach based on carbon intensity for renewable-battery-consumer energy systems
Driven by sustainable development goals and carbon neutrality worldwide, demands for both renewable energy and storage systems are constantly increasing. However, the lack of an appropriate approach without considering renewable intermittence and demand stochasticity will lead to capacity oversizing or undersizing. In this study, an optimal design approach is proposed for integrated photovoltaic-battery-consumer energy systems in the form of a m2-kWp-kWh relationship in both centralized and distributed formats. Superiorities of the proposed matching degree approach are compared with the traditional uniformity approach, in photovoltaic capacity, battery capacity, net present value and lifecycle carbon intensity. Results showed that the proposed method is superior to the traditional approach with higher net present value and lower carbon intensity. Furthermore, the proposed method can be scaled and applied to guide the design of photovoltaic-battery-consumer energy systems in different climate zones, promoting sustainable development and carbon neutrality globally.
Preserving and combining knowledge in robotic lifelong reinforcement learning
Humans can continually accumulate knowledge and develop increasingly complex behaviours and skills throughout their lives, which is a capability known as ‘lifelong learning’. Although this lifelong learning capability is considered an essential mechanism that makes up general intelligence, recent advancements in artificial intelligence predominantly excel in narrow, specialized domains and generally lack this lifelong learning capability. Here we introduce a robotic lifelong reinforcement learning framework that addresses this gap by developing a knowledge space inspired by the Bayesian non-parametric domain. In addition, we enhance the agent’s semantic understanding of tasks by integrating language embeddings into the framework. Our proposed embodied agent can consistently accumulate knowledge from a continuous stream of one-time feeding tasks. Furthermore, our agent can tackle challenging real-world long-horizon tasks by combining and reapplying its acquired knowledge from the original tasks stream. The proposed framework advances our understanding of the robotic lifelong learning process and may inspire the development of more broadly applicable intelligence.
An artificial market model for the forex market
As financial markets have transitioned toward electronic trading, there has been a corresponding increase in the number of algorithmic strategies and degree of transaction frequency. This move to high-frequency trading at the millisecond level, propelled by algorithmic strategies, has brought to the forefront short-term market reactions, like market impact, which were previously negligible in low-frequency trading scenarios. Such evolution necessitates a new framework for analyzing and developing algorithmic strategies in these rapidly evolving markets. Employing artificial markets stands out as a solution to this problem. This study aims to construct an artificial foreign exchange market referencing market microstructure theory, without relying on the assumption of information or technical traders. Furthermore, it endeavors to validate the model by replicating stylized facts, such as fat tails, which exhibit a higher degree of kurtosis in the return distribution than that predicted by normal distribution models. The validated artificial market model will be used to simulate market dynamics and algorithm strategies; its generated rates could also be applied to pricing and risk management for currency options and other foreign exchange derivatives. Moreover, this work explores the importance of order flow and the underlying factors of stylized facts within the artificial market model.
Responsive DNA artificial cells for contact and behavior regulation of mammalian cells
Artificial cells have emerged as synthetic entities designed to mimic the functionalities of natural cells, but their interactive ability with mammalian cells remains challenging. Herein, we develop a generalizable and modular strategy to engineer DNA-empowered stimulable artificial cells designated to regulate mammalian cells (STARM) via synthetic contact-dependent communication. Constructed through temperature-controlled DNA self-assembly involving liquid-liquid phase separation (LLPS), STARMs feature organized all-DNA cytoplasm-mimic and membrane-mimic compartments. These compartments can integrate functional nucleic acid (FNA) modules and light-responsive gold nanorods (AuNRs) to establish a programmable sense-and-respond mechanism to specific stimuli, such as light or ions, orchestrating diverse biological functions, including tissue formation and cellular signaling. By combining two designer STARMs into a dual-channel system, we achieve orthogonally regulated cellular signaling in multicellular communities. Ultimately, the in vivo therapeutic efficacy of STARM in light-guided muscle regeneration in living animals demonstrates the promising potential of smart artificial cells in regenerative medicine.
Responses