Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation in the form of reasoning and planning. Despite the progress, most still rely on pre-defined motion primitives to carry out the physical interactions with the environment, which remains a major bottleneck. In this work, we aim to synthesize robot trajectories, i.e., a dense sequence of 6-DoF end-effector waypoints, for a large variety of manipulation tasks given an open-set of instructions and an open-set of objects. We achieve this by first observing that LLMs excel at inferring affordances and constraints given a free-form language instruction. More importantly, by leveraging their code-writing capabilities, they can interact with a visual-language model (VLM) to compose 3D value maps to ground the knowledge into the observation space of the agent. The composed value maps are then used in a model-based planning framework to zero-shot synthesize closed-loop robot trajectories with robustness to dynamic perturbations. We further demonstrate how the proposed framework can benefit from online experiences by efficiently learning a dynamics model for scenes that involve contact-rich interactions. We present a large-scale study of the proposed method in both simulated and real-robot environments, showcasing the ability to perform a large variety of everyday manipulation tasks specified in free-form natural language. Project website: this https URL <<<

The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications. The advancement of Artificial General Intelligence (AGI) that transcends task and application boundaries is critical for enhancing IDM. Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks, including computer vision, natural language processing, and reinforcement learning. We propose that a Foundation Decision Model (FDM) can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture, offering a promising solution for expanding IDM applications in complex real-world situations. In this paper, we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI, production scheduling, and robotics tasks. Lastly, we present a case study demonstrating our FDM implementation, DigitalBrain (DB1) with 1.3 billion parameters, achieving human-level performance in 870 tasks, such as text generation, image captioning, video game playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 represents an initial step toward more autonomous and efficient real-world IDM applications. <<<

A high-throughput lithographic method with 25-nanometer resolution and smooth vertical sidewalls is proposed and demonstrated. The technique uses compression molding to create a thickness contrast pattern in a thin resist film carried on a substrate, followed by anisotropic etching to transfer the pattern through the entire resist thickness. Metal patterns with a feature size of 25 nanometers and a period of 70 nanometers were fabricated with the use of resist templates created by imprint lithography in combination with a lift-off process. With further development, imprint lithography should allow fabrication of sub-10-nanometer structures and may become a commercially viable technique for manufacturing integrated circuits and other nanodevices. <<<

An ultrasonic imaging technique has been developed to investigate the internal changes of pouch cells nondestructively. The local ultrasonic transmittance of pouch cells has been measured and used for imaging with a new ultrasonic scanning machine designed and built in-house. The wetting process of the cells is clearly observed via such ultrasonic imaging techniques. Furthermore, ultrasonic transmission images of fresh cells and aged cells with different electrolytes and cycling conditions exhibit very different ultrasonic transmittance, which can be caused by electrolyte dry-out or “unwetting” due to cell swelling. The ultrasonic imaging technique is a very sensitive method to probe failure mechanisms in Li-ion pouch cells. <<<

The magnetoelectric effects in multiferroics have a great potential in creating next-generation memory devices. We use an alternative concept of nonvolatile memory based, on a type of nonlinear magnetoelectric effects showing a butterfly-shaped hysteresis loop. The principle is to utilize the states of the magnetoelectric coefficient, instead of magnetization, electric polarization, or resistance, to store binary information. Our experiments in a device made of the PMN-PT/Terfenol- D multiferroic heterostructure clearly demonstrate that the sign of the magnetoelectric coefficient can be repeatedly switched between positive and negative by applying electric fields, confirming the feasibility of this principle. This kind of nonvolatile memory has outstanding practical virtues such as simple structure, easy operation in writing and reading, low power, fast speed, and diverse materials available. <<<

Recent findings indicate that the Japanese IT sector increasingly lags the U.S. IT sector in software innovation and that this underlies Japan's weakening competitive performance vis-à-vis U.S. IT. This article explores alternative explanations for this outcome and analyzes what explains the Japanese software industry's trajectory. The sources are found in the late understanding of the transformational role of software and its value-creating potential as well as in the evolution of the industry's structure. Finally, this article considers what policy makers in other nations might learn from the Japanese experience in building a more vibrant software industry. <<<

Computation-intensive design problems are becoming increasingly common in manufacturing industries. The computation burden is often caused by expensive analysis and simulation processes in order to reach a comparable level of accuracy as physical testing data. To address such a challenge, approximation or metamodeling techniques are often used. Metamodeling techniques have been developed from many different disciplines including statistics, mathematics, computer science, and various engineering disciplines. These metamodels are initially developed as “surrogates” of the expensive simulation process in order to improve the overall computation efficiency. They are then found to be a valuable tool to support a wide scope of activities in modern engineering design, especially design optimization. This work reviews the state-of-the-art metamodel-based techniques from a practitioner’s perspective according to the role of metamodeling in supporting design optimization, including model approximation, design space exploration, problem formulation, and solving various types of optimization problems. Challenges and future development of metamodeling in support of engineering design is also analyzed and discussed. <<<