Standard robot grippers are not designed for material recognition. We experimentally evaluated the accuracy with which material properties can be estimated through object compression by two standard parallel jaw grippers and a force/torque sensor mounted at the robot wrist, with a professional biaxial compression device used as reference. Gripper effort versus position curves were obtained and transformed into stress/strain curves. The modulus of elasticity was estimated at different strain points and the effect of multiple compression cycles (precycling), compression speed, and the gripper surface area on estimation was studied. Viscoelasticity was estimated using the energy absorbed in a compression/decompression cycle, the Kelvin-Voigt, and Hunt-Crossley models. We found that: (1) slower compression speeds improved elasticity estimation, while precycling or surface area did not; (2) the robot grippers, even after calibration, were found to have a limited capability of delivering accurate estimates of absolute values of Young's modulus and viscoelasticity; (3) relative ordering of material characteristics was largely consistent across different grippers; (4) despite the nonlinear characteristics of deformable objects, fitting linear stress/strain approximations led to more stable results than local estimates of Young's modulus; (5) the Hunt-Crossley model worked best to estimate viscoelasticity, from a single object compression. A two-dimensional space formed by elasticity and viscoelasticity estimates obtained from a single grasp is advantageous for the discrimination of the object material properties. We demonstrated the applicability of our findings in a mock single stream recycling scenario, where plastic, paper, and metal objects were correctly separated from a single grasp, even when compressed at different locations on the object. The data and code are publicly available.
相關內容
The main challenge in learning image-conditioned robotic policies is acquiring a visual representation conducive to low-level control. Due to the high dimensionality of the image space, learning a good visual representation requires a considerable amount of visual data. However, when learning in the real world, data is expensive. Sim2Real is a promising paradigm for overcoming data scarcity in the real-world target domain by using a simulator to collect large amounts of cheap data closely related to the target task. However, it is difficult to transfer an image-conditioned policy from sim to real when the domains are very visually dissimilar. To bridge the sim2real visual gap, we propose using natural language descriptions of images as a unifying signal across domains that captures the underlying task-relevant semantics. Our key insight is that if two image observations from different domains are labeled with similar language, the policy should predict similar action distributions for both images. We demonstrate that training the image encoder to predict the language description or the distance between descriptions of a sim or real image serves as a useful, data-efficient pretraining step that helps learn a domain-invariant image representation. We can then use this image encoder as the backbone of an IL policy trained simultaneously on a large amount of simulated and a handful of real demonstrations. Our approach outperforms widely used prior sim2real methods and strong vision-language pretraining baselines like CLIP and R3M by 25 to 40%.
Neural scaling laws characterize how model performance improves as the model size scales up. Inspired by empirical observations, we introduce a resource model of neural scaling. A task is usually composite hence can be decomposed into many subtasks, which compete for resources (measured by the number of neurons allocated to subtasks). On toy problems, we empirically find that: (1) The loss of a subtask is inversely proportional to its allocated neurons. (2) When multiple subtasks are present in a composite task, the resources acquired by each subtask uniformly grow as models get larger, keeping the ratios of acquired resources constants. We hypothesize these findings to be generally true and build a model to predict neural scaling laws for general composite tasks, which successfully replicates the neural scaling law of Chinchilla models reported in arXiv:2203.15556. We believe that the notion of resource used in this paper will be a useful tool for characterizing and diagnosing neural networks.
Anomaly detection and localization without any manual annotations and prior knowledge is a challenging task under the setting of unsupervised learning. The existing works achieve excellent performance in the anomaly detection, but with complex networks or cumbersome pipelines. To address this issue, this paper explores a simple but effective architecture in the anomaly detection. It consists of a well pre-trained encoder to extract hierarchical feature representations and a decoder to reconstruct these intermediate features from the encoder. In particular, it does not require any data augmentations and anomalous images for training. The anomalies can be detected when the decoder fails to reconstruct features well, and then errors of hierarchical feature reconstruction are aggregated into an anomaly map to achieve anomaly localization. The difference comparison between those features of encoder and decode lead to more accurate and robust localization results than the comparison in single feature or pixel-by-pixel comparison in the conventional works. Experiment results show that the proposed method outperforms the state-of-the-art methods on MNIST, Fashion-MNIST, CIFAR-10, and MVTec Anomaly Detection datasets on both anomaly detection and localization.
Despite significant technological advancements, the process of programming robots for adaptive assembly remains labor-intensive, demanding expertise in multiple domains and often resulting in task-specific, inflexible code. This work explores the potential of Large Language Models (LLMs), like ChatGPT, to automate this process, leveraging their ability to understand natural language instructions, generalize examples to new tasks, and write code. In this paper, we suggest how these abilities can be harnessed and applied to real-world challenges in the manufacturing industry. We present a novel system that uses ChatGPT to automate the process of programming robots for adaptive assembly by decomposing complex tasks into simpler subtasks, generating robot control code, executing the code in a simulated workcell, and debugging syntax and control errors, such as collisions. We outline the architecture of this system and strategies for task decomposition and code generation. Finally, we demonstrate how our system can autonomously program robots for various assembly tasks in a real-world project.
Understanding degraded speech is demanding, requiring increased listening effort (LE). Evaluating processed and unprocessed speech with respect to LE can objectively indicate if speech enhancement systems benefit listeners. However, existing methods for measuring LE are complex and not widely applicable. In this study, we propose a simple method to evaluate speech intelligibility and LE simultaneously without additional strain on subjects or operators. We assess this method using results from two independent studies in Norway and Denmark, testing 76 (50+26) subjects across 9 (6+3) processing conditions. Despite differences in evaluation setups, subject recruitment, and processing systems, trends are strikingly similar, demonstrating the proposed method's robustness and ease of implementation into existing practices.
Decision diagrams (DDs) are powerful tools to represent effectively propositional formulas, which are largely used in many domains, in particular in formal verification and in knowledge compilation. Some forms of DDs (e.g., OBDDs, SDDs) are canonical, that is, (under given conditions on the atom list) they univocally represent equivalence classes of formulas. Given the limited expressiveness of propositional logic, a few attempts to leverage DDs to SMT level have been presented in the literature. Unfortunately, these techniques still suffer from some limitations: most procedures are theory-specific; some produce theory DDs (T-DDs) which do not univocally represent T-valid formulas or T-inconsistent formulas; none of these techniques provably produces theory-canonical T-DDs, which (under given conditions on the T-atom list) univocally represent T-equivalence classes of formulas. Also, these procedures are not easy to implement, and very few implementations are actually available. In this paper, we present a novel very-general technique to leverage DDs to SMT level, which has several advantages: it is very easy to implement on top of an AllSMT solver and a DD package, which are used as blackboxes; it works for every form of DDs and every theory, or combination thereof, supported by the AllSMT solver; it produces theory-canonical T-DDs if the propositional DD is canonical. We have implemented a prototype tool for both T-OBDDs and T-SDDs on top of OBDD and SDD packages and the MathSAT SMT solver. Some preliminary empirical evaluation supports the effectiveness of the approach.
We propose the characteristic generator, a novel one-step generative model that combines the efficiency of sampling in Generative Adversarial Networks (GANs) with the stable performance of flow-based models. Our model is driven by characteristics, along which the probability density transport can be described by ordinary differential equations (ODEs). Specifically, We estimate the velocity field through nonparametric regression and utilize Euler method to solve the probability flow ODE, generating a series of discrete approximations to the characteristics. We then use a deep neural network to fit these characteristics, ensuring a one-step mapping that effectively pushes the prior distribution towards the target distribution. In the theoretical aspect, we analyze the errors in velocity matching, Euler discretization, and characteristic fitting to establish a non-asymptotic convergence rate for the characteristic generator in 2-Wasserstein distance. To the best of our knowledge, this is the first thorough analysis for simulation-free one step generative models. Additionally, our analysis refines the error analysis of flow-based generative models in prior works. We apply our method on both synthetic and real datasets, and the results demonstrate that the characteristic generator achieves high generation quality with just a single evaluation of neural network.
Notation conventions for rigid transformations are as diverse as they are fundamental to the field of robotics. A well-defined convention that is practical, consistent and unambiguous is essential for the clear communication of ideas and to foster collaboration between researchers. This work presents an analysis of conventions used in state-of-the-art robotics research, defines a new notation convention, and provides software packages to facilitate its use. To shed some light on the current state of notation conventions in robotics research, this work presents an analysis of the ICRA 2023 proceedings, focusing on the notation conventions used for rigid transformations. A total of 1655 papers were inspected to identify the convention used, and key insights about trends and usage preferences are derived. Based on this analysis, a new notation convention called RIGID is defined, which complies with the "ISO 80000 Standard on Quantities and Units". The RIGID convention is designed to be concise yet unambiguous and easy to use. Additionally, this work introduces a LaTeX package that facilitates the use of the RIGID notation in manuscripts preparation through simple customizable commands that can be easily translated into variable names for software development.
Generative AI models are often used to perform mimicry attacks, where a pretrained model is fine-tuned on a small sample of images to learn to mimic a specific artist of interest. While researchers have introduced multiple anti-mimicry protection tools (Mist, Glaze, Anti-Dreambooth), recent evidence points to a growing trend of mimicry models using videos as sources of training data. This paper presents our experiences exploring techniques to disrupt style mimicry on video imagery. We first validate that mimicry attacks can succeed by training on individual frames extracted from videos. We show that while anti-mimicry tools can offer protection when applied to individual frames, this approach is vulnerable to an adaptive countermeasure that removes protection by exploiting randomness in optimization results of consecutive (nearly-identical) frames. We develop a new, tool-agnostic framework that segments videos into short scenes based on frame-level similarity, and use a per-scene optimization baseline to remove inter-frame randomization while reducing computational cost. We show via both image level metrics and an end-to-end user study that the resulting protection restores protection against mimicry (including the countermeasure). Finally, we develop another adaptive countermeasure and find that it falls short against our framework.
We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder for shape generation, aimed at improving the visual quality of the generated shapes. An implicit field assigns a value to each point in 3D space, so that a shape can be extracted as an iso-surface. Our implicit field decoder is trained to perform this assignment by means of a binary classifier. Specifically, it takes a point coordinate, along with a feature vector encoding a shape, and outputs a value which indicates whether the point is outside the shape or not. By replacing conventional decoders by our decoder for representation learning and generative modeling of shapes, we demonstrate superior results for tasks such as shape autoencoding, generation, interpolation, and single-view 3D reconstruction, particularly in terms of visual quality.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191