Search for: All records

UniT is an approach to tactile representation learn¬ing, using VQGAN to learn a compact latent space and serve as the tactile representation. It uses tactile images obtained from a single simple object to train the representation with generalizability. This tactile representation can be zero-shot transferred to various downstream tasks, including perception tasks and manipulation policy learning. Our benchmarkings on in-hand 3D pose and 6D pose estimation tasks and a tactile classifcation task show that UniT outperforms existing visual and tactile representation learning methods. Additionally, UniT’s effectiveness in policy learning is demonstrated across three real-world tasks involving diverse manipulated objects and complex robot-object-environment interactions. Through extensive experi¬mentation, UniT is shown to be a simple-to-train, plug-and-play, yet widely effective method for tactile representation learning. For more details, please refer to our open-source repository https://github.com/ZhengtongXu/UniT and the project website https://zhengtongxu.github.io/unit-website/. 

Additive manufacturing has become one of the forefront technologies in fabrication, enabling products impossible to manufacture before. Although many materials exist for additive manufacturing, most suffer from performance trade-offs. Current materials are designed with inefficient human-driven intuition-based methods, leaving them short of optimal solutions. We propose a machine learning approach to accelerating the discovery of additive manufacturing materials with optimal trade-offs in mechanical performance. A multiobjective optimization algorithm automatically guides the experimental design by proposing how to mix primary formulations to create better performing materials. The algorithm is coupled with a semiautonomous fabrication platform to substantially reduce the number of performed experiments and overall time to solution. Without prior knowledge of the primary formulations, the proposed methodology autonomously uncovers 12 optimal formulations and enlarges the discovered performance space 288 times after only 30 experimental iterations. This methodology could be easily generalized to other material design systems and enable automated discovery. 

Abstract Lithium‐ion battery electrodes are manufactured using a new additive manufacturing process based on dry powders. By using dry powder‐based processing, the solvent and its associated drying processes in conventional battery process can be removed, allowing for large‐scale Li‐ion battery production to be more economically viable in markets such as automotive energy storage systems. Uniform mixing distribution of the additive materials throughout the active material is the driving factor for manufacturing dry powder‐based Li‐ion batteries. Therefore, this article focuses on developing a physical model based on interfacial energies to understand the mixing characteristics of the dry mixed particulate materials. The mixing studies show that functional electrodes can be manufactured using dry processing with binder and conductive additive materials as low as 1 wt% due to the uniformly distributed particles. Electrochemical performance of the dry manufactured electrodes with reduced conductive and binder additive is promising as the cells retained 77% capacity after 100 cycles. While not representative of the best possible electrochemical performance of Li‐ion batteries, the achieved electrochemical performance of the reduced conductive and binder additive electrodes with LiCoO₂as the active material confirms the well distributed nature of the additive particles throughout the electrode matrix.