Search for: All records

3D perceptual representations are well suited for robot manipulation as they easily encode occlusions and simplify spatial reasoning. Many manipulation tasks require high spatial precision in end-effector pose prediction, which typically demands high-resolution 3D feature grids that are computationally expensive to process. As a result, most manipulation policies operate directly in 2D, foregoing 3D inductive biases. In this paper, we introduce Act3D, a manipulation policy transformer that represents the robot’s workspace using a 3D feature field with adaptive resolutions dependent on the task at hand. The model lifts 2D pre-trained features to 3D using sensed depth, and attends to them to compute features for sampled 3D points. It samples 3D point grids in a coarse to fine manner, featurizes them using relative-position attention, and selects where to focus the next round of point sampling. In this way, it efficiently computes 3D action maps of high spatial resolution. Act3D sets a new state-of-the-art in RLBench, an established manipulation benchmark, where it achieves 10% absolute improvement over the previous SOTA 2D multi-view policy on 74 RLBench tasks and 22% absolute improvement with 3x less compute over the previous SOTA 3D policy. We quantify the importance of relative spatial attention, large-scale vision-language pre-trained 2D backbones, and weight tying across coarse-to-fine attentions in ablative experiments. Code and videos are available at our project site: https://act3d.github.io/. 

Rechargeable Li-CO2 batteries have emerged as promising candidates for next generation batteries due to their low cost, high theoretical capacity, and ability to capture the greenhouse gas CO2. However, these batteries still face challenges such as slow reaction kinetic and short cycle performance due to the accumulation of discharge products. To address this issue, it is necessary to design and develop high efficiency electrocatalysts that can improve CO2 reduction reaction. In this study, we report the use of NiMn2O4 electrocatalysts combined with multiwall carbon nanotubes as a cathode material in the Li-CO2 batteries. This combination proved effective in decomposing discharge products and enhancing cycle performance. The battery shows stable discharge–charge cycles for at least 30 cycles with a high limited capacity of 1000 mAh/g at current density of 100 mA/g. Furthermore, the battery with the NiMn2O4@CNT catalyst exhibits a reversible discharge capacity of 2636 mAh/g. To gain a better understanding of the reaction mechanism of Li-CO2 batteries, spectroscopies and microscopies were employed to identify the chemical composition of the discharge products. This work paves a pathway to increase cycle performance in metal-CO2 batteries, which could have significant implications for energy storage and the reduction of greenhouse gas emissions. 

The National Alzheimer's Coordinating Center Uniform Data Set includes test results from a battery of cognitive exams. Motivated by the need to model the cognitive ability of low‐performing patients we create a composite score from ten tests and propose to model this score using a partially linear quantile regression model for longitudinal studies with non‐ignorable dropouts. Quantile regression allows for modeling non‐central tendencies. The partially linear model accommodates nonlinear relationships between some of the covariates and cognitive ability. The data set includes patients that leave the study prior to the conclusion. Ignoring such dropouts will result in biased estimates if the probability of dropout depends on the response. To handle this challenge, we propose a weighted quantile regression estimator where the weights are inversely proportional to the estimated probability a subject remains in the study. We prove that this weighted estimator is a consistent and efficient estimator of both linear and nonlinear effects. 

Rechargeable Li-CO₂batteries have emerged as promising candidates for next generation batteries due to their low cost, high theoretical capacity, and ability to capture the greenhouse gas CO₂. However, these batteries still face challenges such as slow reaction kinetic and short cycle performance due to the accumulation of discharge products. To address this issue, it is necessary to design and develop high efficiency electrocatalysts that can improve CO₂reduction reaction. In this study, we report the use of NiMn₂O₄electrocatalysts combined with multiwall carbon nanotubes as a cathode material in the Li-CO₂batteries. This combination proved effective in decomposing discharge products and enhancing cycle performance. The battery shows stable discharge–charge cycles for at least 30 cycles with a high limited capacity of 1000 mAh g⁻¹at current density of 100 mA g⁻¹. Furthermore, the battery with the NiMn₂O₄@CNT catalyst exhibits a reversible discharge capacity of 2636 mAh g⁻¹. To gain a better understanding of the reaction mechanism of Li-CO₂batteries, spectroscopies and microscopies were employed to identify the chemical composition of the discharge products. This work paves a pathway to increase cycle performance in metal-CO₂batteries, which could have significant implications for energy storage and the reduction of greenhouse gas emissions.