Combining data-driven models that adapt online and model predictive control (MPC) has enabled effective control of nonlinear systems. However, when deployed on unstable systems, online adaptation may not be fast enough to ensure reliable simultaneous learning and control. For example, controllers on a vehicle executing highly dynamic maneuvers may push the tires to their friction limits, destabilizing the vehicle and allowing modeling errors to quickly compound and cause a loss of control. In this work, we present a Bayesian meta-learning MPC framework. We propose an expressive vehicle dynamics model that leverages Bayesian last-layer meta-learning to enable rapid online adaptation. The model's uncertainty estimates are used to guide informative data collection and quickly improve the model prior to deployment. Experiments on a Toyota Supra show that (i) the framework enables reliable control in dynamic drifting maneuvers, (ii) online adaptation alone may not suffice for zero-shot control of a vehicle at the edge of stability, and (iii) active data collection helps achieve reliable performance.
Accurate dynamic models are crucial for many robotic applications. Traditional approaches to deriving these models are based on the application of Lagrangian or Newtonian mechanics. Although these methods provide a good insight into the physical behaviour of the system, they rely on the exact knowledge of parameters such as inertia, friction and joint flexibility. In addition, the system is often affected by uncertain and nonlinear effects, such as saturation and dead zones, which can be difficult to model. A popular alternative is the application of Machine Learning (ML) techniques - e.g., Neural Networks (NNs) - in the context of a "black-box" methodology. This paper reports on our experience with this approach for a real-life 6 degrees of freedom (DoF) manipulator. Specifically, we considered several NN architectures: single NN, multiple NNs, and cascade NN. We compared the performance of the system by using different policies for selecting the NN hyperparameters. Our experiments reveal that the best accuracy and performance are obtained by a cascade NN, in which we encode our prior physical knowledge about the dependencies between joints, complemented by an appropriate optimisation of the hyperparameters.
Robotic manipulation of volumetric elastoplastic deformable materials, from foods such as dough to construction materials like clay, is in its infancy, largely due to the difficulty of modelling and perception in a high-dimensional space. Simulating the dynamics of such materials is computationally expensive. It tends to suffer from inaccurately estimated physics parameters of the materials and the environment, impeding high-precision manipulation. Estimating such parameters from raw point clouds captured by optical cameras suffers further from heavy occlusions. To address this challenge, this work introduces a novel Differentiable Physics-based System Identification (DPSI) framework that enables a robot arm to infer the physics parameters of elastoplastic materials and the environment using simple manipulation motions and incomplete 3D point clouds, aligning the simulation with the real world. Extensive experiments show that with only a single real-world interaction, the estimated parameters, Young's modulus, Poisson's ratio, yield stress and friction coefficients, can accurately simulate visually and physically realistic deformation behaviours induced by unseen and long-horizon manipulation motions. Additionally, the DPSI framework inherently provides physically intuitive interpretations for the parameters in contrast to black-box approaches such as deep neural networks. The project is fully open-sourced via https://ianyangchina.github.io/SI4RP-data/.
Surface electromyography (sEMG) non-invasively measures signals generated by muscle activity with sufficient sensitivity to detect individual spinal neurons and richness to identify dozens of gestures and their nuances. Wearable wrist-based sEMG sensors have the potential to offer low friction, subtle, information rich, always available human-computer inputs. To this end, we introduce emg2qwerty, a large-scale dataset of non-invasive electromyographic signals recorded at the wrists while touch typing on a QWERTY keyboard, together with ground-truth annotations and reproducible baselines. With 1,135 sessions spanning 108 users and 346 hours of recording, this is the largest such public dataset to date. These data demonstrate non-trivial, but well defined hierarchical relationships both in terms of the generative process, from neurons to muscles and muscle combinations, as well as in terms of domain shift across users and user sessions. Applying standard modeling techniques from the closely related field of Automatic Speech Recognition (ASR), we show strong baseline performance on predicting key-presses using sEMG signals alone. We believe the richness of this task and dataset will facilitate progress in several problems of interest to both the machine learning and neuroscientific communities. Dataset and code can be accessed at https://github.com/facebookresearch/emg2qwerty.
The rise in capability and ubiquity of generative artificial intelligence (AI) technologies has enabled its application to the field of Socially Interactive Agents (SIAs). Despite rising interest in modern AI-powered components used for real-time SIA research, substantial friction remains due to the absence of a standardized and universal SIA framework. To target this absence, we developed Estuary: a multimodal (text, audio, and soon video) framework which facilitates the development of low-latency, real-time SIAs. Estuary seeks to reduce repeat work between studies and to provide a flexible platform that can be run entirely off-cloud to maximize configurability, controllability, reproducibility of studies, and speed of agent response times. We are able to do this by constructing a robust multimodal framework which incorporates current and future components seamlessly into a modular and interoperable architecture.
Soft robots offer a frontier in robotics with enormous potential for safe human-robot interaction and agility in uncertain environments. A stepping stone towards unlocking their potential is a control theory tailored to soft robotics, including a principled framework for gait design. We analyze the problem of optimal gait design for a soft crawling body - the crawler. The crawler is an elastic body with the control signal defined as actuation forces between segments of the body. We consider the simplest such crawler: a two-segmented body with a passive mechanical connection modeling the viscoelastic body dynamics and a symmetric control force modeling actuation between the two body segments. The model accounts for the nonlinear asymmetric friction with the ground, which together with the symmetric actuation forces enable the crawler's locomotion. Using a describing-function analysis, we show that when the body is forced sinusoidally, the optimal actuator contraction frequency corresponds to the body's natural frequency when operating with only passive dynamics. We then use the framework of Optimal Periodic Control (OPC) to design optimal force cycles of arbitrary waveform and the corresponding crawling gaits. We provide a hill-climbing algorithm to solve the OPC problem numerically. Our proposed methods and results inform the design of optimal forcing and gaits for more complex and multi-segmented crawling soft bodies.
The dynamic properties of materials utilized in architecture or engineering applications can significantly affect their performance under dynamic or impact loading conditions. To evaluate such behavior, force transducers are commonly employed in testing. However, the calibration of force transducers is typically limited to static conditions and relies solely on gravitational forces exerted on standard masses. Thus, assessing the uncertainty in force measurements using force transducers during dynamic loading conditions remains a challenging task, presenting a significant obstacle in accurately characterizing the dynamic behavior of materials. In this work, an optical technique to evaluate the mechanical properties of wires subjected to impact tensile loads is presented. The wire under test is subjected to an impact tensile load by applying the inertial force of a rigid mass, which is supported by utilizing an aerostatic linear bearing with sufficiently small friction. The inertial force applied to the wire can be determined by multiplying the mass of the rigid mass by its acceleration, where the acceleration can be measured employing a Michelson type optical interferometer. The performance of the proposed method is demonstrated through experiments and analysis of the dynamic characteristics of a tungsten wire under impact tensile loading conditions.
Novice programmers are increasingly relying on Large Language Models (LLMs) to generate code for learning programming concepts. However, this interaction can lead to superficial engagement, giving learners an illusion of learning and hindering skill development. To address this issue, we conducted a systematic design exploration to develop seven cognitive engagement techniques aimed at promoting deeper engagement with AI-generated code. In this paper, we describe our design process, the initial seven techniques and results from a between-subjects study (N=82). We then iteratively refined the top techniques and further evaluated them through a within-subjects study (N=42). We evaluate the friction each technique introduces, their effectiveness in helping learners apply concepts to isomorphic tasks without AI assistance, and their success in aligning learners' perceived and actual coding abilities. Ultimately, our results highlight the most effective technique: guiding learners through the step-by-step problem-solving process, where they engage in an interactive dialog with the AI, prompting what needs to be done at each stage before the corresponding code is revealed.
QR codes have become ubiquitous in daily life, enabling rapid information exchange. With the increasing adoption of smart wearable devices, there is a need for efficient, and friction-less QR code reading capabilities from Egocentric point-of-views. However, adapting existing phone-based QR code readers to egocentric images poses significant challenges. Code reading from egocentric images bring unique challenges such as wide field-of-view, code distortion and lack of visual feedback as compared to phones where users can adjust the position and framing. Furthermore, wearable devices impose constraints on resources like compute, power and memory. To address these challenges, we present EgoQR, a novel system for reading QR codes from egocentric images, and is well suited for deployment on wearable devices. Our approach consists of two primary components: detection and decoding, designed to operate on high-resolution images on the device with minimal power consumption and added latency. The detection component efficiently locates potential QR codes within the image, while our enhanced decoding component extracts and interprets the encoded information. We incorporate innovative techniques to handle the specific challenges of egocentric imagery, such as varying perspectives, wider field of view, and motion blur. We evaluate our approach on a dataset of egocentric images, demonstrating 34% improvement in reading the code compared to an existing state of the art QR code readers.
Manipulation of large objects over long horizons (such as carts in a warehouse) is an essential skill for deployable robotic systems. Large objects require mobile manipulation which involves simultaneous manipulation, navigation, and movement with the object in tow. In many real-world situations, object dynamics are incredibly complex, such as the interaction of an office chair (with a rotating base and five caster wheels) and the ground. We present a hierarchical algorithm for long-horizon robot manipulation problems in which the dynamics are partially unknown. We observe that diffusion-based behavior cloning is highly effective for short-horizon problems with unknown dynamics, so we decompose the problem into an abstract high-level, obstacle-aware motion-planning problem that produces a waypoint sequence. We use a short-horizon, relative-motion diffusion policy to achieve the waypoints in sequence. We train mobile manipulation policies on a Spot robot that has to push and pull an office chair. Our hierarchical manipulation policy performs consistently better, especially when the horizon increases, compared to a diffusion policy trained on long-horizon demonstrations or motion planning assuming a rigidly-attached object (success rate of 8 (versus 0 and 5 respectively) out of 10 runs). Importantly, our learned policy generalizes to new layouts, grasps, chairs, and flooring that induces more friction, without any further training, showing promise for other complex mobile manipulation problems. Project Page: https://yravan.github.io/plannerorderedpolicy/
Ads Content Safety at Google requires classifying billions of ads for Google Ads content policies. Consistent and accurate policy enforcement is important for advertiser experience and user safety and it is a challenging problem, so there is a lot of value for improving it for advertisers and users. Inconsistent policy enforcement causes increased policy friction and poor experience with good advertisers, and bad advertisers exploit the inconsistency by creating multiple similar ads in the hope that some will get through our defenses. This study proposes a method to understand advertiser's intent for content policy violations, using Large Language Models (LLMs). We focus on identifying good advertisers to reduce content over-flagging and improve advertiser experience, though the approach can easily be extended to classify bad advertisers too. We generate advertiser's content profile based on multiple signals from their ads, domains, targeting info, etc. We then use LLMs to classify the advertiser content profile, along with relying on any knowledge the LLM has of the advertiser, their products or brand, to understand whether they are likely to violate a certain policy or not. After minimal prompt tuning our method was able to reach 95\% accuracy on a small test set.
The increased use of information retrieval in recruitment, primarily through job recommender systems (JRSs), can have a large impact on job seekers, recruiters, and companies. As a result, such systems have been determined to be high-risk in recent legislature. This requires JRSs to be trustworthy and transparent, allowing stakeholders to understand why specific recommendations were made. To fulfill this requirement, the stakeholders' exact preferences and needs need to be determined. To do so, we evaluated an explainable job recommender system using a realistic, task-based, mixed-design user study (n=30) in which stakeholders had to make decisions based on the model's explanations. This mixed-methods evaluation consisted of two objective metrics - correctness and efficiency, along with three subjective metrics - trust, transparency, and usefulness. These metrics were evaluated twice per participant, once using real explanations and once using random explanations. The study included a qualitative analysis following a think-aloud protocol while performing tasks adapted to each stakeholder group. We find that providing stakeholders with real explanations does not significantly improve decision-making speed and accuracy. Our results showed a non-significant trend for the real explanations to outperform the random ones on perceived trust, usefulness, and transparency of the system for all stakeholder types. We determine that stakeholders benefit more from interacting with explanations as decision support capable of providing healthy friction, rather than as previously-assumed persuasive tools.
Mobile robots should be capable of planning cost-efficient paths for autonomous navigation. Typically, the terrain and robot properties are subject to variations. For instance, properties of the terrain such as friction may vary across different locations. Also, properties of the robot may change such as payloads or wear and tear, e.g., causing changing actuator gains or joint friction. Autonomous navigation approaches should thus be able to adapt to such variations. In this article, we propose a novel approach for learning a probabilistic, terrain- and robot-aware forward dynamics model (TRADYN) which can adapt to such variations and demonstrate its use for navigation. Our learning approach extends recent advances in meta-learning forward dynamics models based on Neural Processes for mobile robot navigation. We evaluate our method in simulation for 2D navigation of a robot with uni-cycle dynamics with varying properties on terrain with spatially varying friction coefficients. In our experiments, we demonstrate that TRADYN has lower prediction error over long time horizons than model ablations which do not adapt to robot or terrain variations. We also evaluate our model for navigation planning in a model-predictive control framework and under various sources of noise. We demonstrate that our approach yields improved performance in planning control-efficient paths by taking robot and terrain properties into account.
Interactions of polyelectrolytes (PEs) with proteins play a crucial role in numerous biological processes, such as the internalization of virus particles into host cells. Although docking, machine learning methods, and molecular dynamics (MD) simulations are utilized to estimate binding poses and binding free energies of small-molecule drugs to proteins, quantitative prediction of the binding thermodynamics of PE-based drugs presents a significant obstacle in computer-aided drug design. This is due to the sluggish dynamics of PEs caused by their size and strong charge-charge correlations. In this paper, we introduce advanced sampling methods based on a force-spectroscopy setup and theoretical modeling to overcome this barrier. We exemplify our method with explicit solvent all-atom MD simulations of interactions of anionic PEs that show antiviral properties, namely heparin and linear polyglycerol sulfate (LPGS), with the SARS-CoV-2 spike protein receptor binding domain (RBD). Our prediction for the binding free energy of LPGS to the wild-type RBD matches experimentally measured dissociation constants within thermal energy, kT, and correctly reproduces the experimental PE-length dependence. We find that LPGS binds to the Delta-variant RBD with an additional free-energy gain of 2.4 kT, compared to the wild-type RBD, in accord with electrostatic arguments. We show that the LPGS-RBD binding is solvent-dominated and enthalpy-driven, though with a large entropy-enthalpy compensation. Our method is applicable to general polymer adsorption phenomena and predicts precise binding free energies and re-configurational friction as needed for drug and drug-delivery design.
The accurate quantification of wall-shear stress dynamics is of substantial importance for various applications in fundamental and applied research, spanning areas from human health to aircraft design and optimization. Despite significant progress in experimental measurement techniques and post-processing algorithms, temporally resolved wall-shear stress dynamics with adequate spatial resolution and within a suitable spatial domain remain an elusive goal. To address this gap, we introduce a deep learning architecture that ingests wall-parallel velocity fields from the logarithmic layer of turbulent wall-bounded flows and outputs the corresponding 2D wall-shear stress fields with identical spatial resolution and domain size. From a physical perspective, our framework acts as a surrogate model encapsulating the various mechanisms through which highly energetic outer-layer flow structures influence the governing wall-shear stress dynamics. The network is trained in a supervised fashion on a unified dataset comprising direct numerical simulations of statistically 1D turbulent channel and spatially developing turbulent boundary layer flows at friction Reynolds numbers ranging from 390 to 1,500. We demonstrate a zero-shot applicability to experimental velocity fields obtained from Particle-Image Velocimetry measurements and verify the physical accuracy of the wall-shear stress estimates with synchronized wall-shear stress measurements using the Micro-Pillar Shear-Stress Sensor for Reynolds numbers up to 2,000. In summary, the presented framework lays the groundwork for extracting inaccessible experimental wall-shear stress information from readily available velocity measurements and thus, facilitates advancements in a variety of experimental applications.
We present a rapid binary evolution algorithm that enables modelling of even the most complex binary systems. In addition to all aspects of single star evolution, features such as mass transfer, mass accretion, common-envelope evolution, collisions, supernova kicks and angular momentum loss mechanisms are included. In particular, circularization and synchronization of the orbit by tidal interactions are calculated for convective, radiative and degenerate damping mechanisms. We use this algorithm to study the formation and evolution of various binary systems. We also investigate the effect that tidal friction has on the outcome of binary evolution. Using the rapid binary code, we generate a series of large binary populations and evaluate the formation rate of interesting individual species and events. By comparing the results for populations with and without tidal friction we quantify the hitherto ignored systematic effect of tides and show that modelling of tidal evolution in binary systems is necessary in order to draw accurate conclusions from population synthesis work. Tidal synchronism is important but because orbits generally circularize before Roche-lobe overflow the outcome of the interactions of systems with the same semi-latus rectum is almost independent of eccentricity. It is not necessary to include a distribution of eccentricities in population synthesis of interacting binaries, however, the initial separations should be distributed according to the observed distribution of semi-latera recta rather than periods or semi-major axes.
Identifying the physical properties of the surrounding environment is essential for robotic locomotion and navigation to deal with non-geometric hazards, such as slippery and deformable terrains. It would be of great benefit for robots to anticipate these extreme physical properties before contact; however, estimating environmental physical parameters from vision is still an open challenge. Animals can achieve this by using their prior experience and knowledge of what they have seen and how it felt. In this work, we propose a cross-modal self-supervised learning framework for vision-based environmental physical parameter estimation, which paves the way for future physical-property-aware locomotion and navigation. We bridge the gap between existing policies trained in simulation and identification of physical terrain parameters from vision. We propose to train a physical decoder in simulation to predict friction and stiffness from multi-modal input. The trained network allows the labeling of real-world images with physical parameters in a self-supervised manner to further train a visual network during deployment, which can densely predict the friction and stiffness from image data. We validate our physical decoder in simulation and the real world using a quadruped ANYmal robot, outperforming an existing baseline method. We show that our visual network can predict the physical properties in indoor and outdoor experiments while allowing fast adaptation to new environments.
Adaptive optimizers are pivotal in guiding the weight updates of deep neural networks, yet they often face challenges such as poor generalization and oscillation issues. To counter these, we introduce sigSignGrad and tanhSignGrad, two novel optimizers that integrate adaptive friction coefficients based on the Sigmoid and Tanh functions, respectively. These algorithms leverage short-term gradient information, a feature overlooked in traditional Adam variants like diffGrad and AngularGrad, to enhance parameter updates and convergence.Our theoretical analysis demonstrates the wide-ranging adjustment capability of the friction coefficient S, which aligns with targeted parameter update strategies and outperforms existing methods in both optimization trajectory smoothness and convergence rate. Extensive experiments on CIFAR-10, CIFAR-100, and Mini-ImageNet datasets using ResNet50 and ViT architectures confirm the superior performance of our proposed optimizers, showcasing improved accuracy and reduced training time. The innovative approach of integrating adaptive friction coefficients as plug-ins into existing optimizers, exemplified by the sigSignAdamW and sigSignAdamP variants, presents a promising strategy for boosting the optimization performance of established algorithms. The findings of this study contribute to the advancement of optimizer design in deep learning.
This study presents a novel approach to predicting mechanical properties of Additive Friction Stir Deposited (AFSD) aluminum alloy walled structures using biomimetic machine learning. The research combines numerical modeling of the AFSD process with genetic algorithm-optimized machine learning models to predict von Mises stress and logarithmic strain. Finite element analysis was employed to simulate the AFSD process for five aluminum alloys: AA2024, AA5083, AA5086, AA7075, and AA6061, capturing complex thermal and mechanical interactions. A dataset of 200 samples was generated from these simulations. Subsequently, Decision Tree (DT) and Random Forest (RF) regression models, optimized using genetic algorithms, were developed to predict key mechanical properties. The GA-RF model demonstrated superior performance in predicting both von Mises stress (R square = 0.9676) and logarithmic strain (R square = 0.7201). This innovative approach provides a powerful tool for understanding and optimizing the AFSD process across multiple aluminum alloys, offering insights into material behavior under various process parameters.
This study investigates the application of deep residual networks for predicting the dynamics of interacting three-dimensional rigid bodies. We present a framework combining a 3D physics simulator implemented in C++ with a deep learning model constructed using PyTorch. The simulator generates training data encompassing linear and angular motion, elastic collisions, fluid friction, gravitational effects, and damping. Our deep residual network, consisting of an input layer, multiple residual blocks, and an output layer, is designed to handle the complexities of 3D dynamics. We evaluate the network's performance using a datasetof 10,000 simulated scenarios, each involving 3-5 interacting rigid bodies. The model achieves a mean squared error of 0.015 for position predictions and 0.022 for orientation predictions, representing a 25% improvement over baseline methods. Our results demonstrate the network's ability to capture intricate physical interactions, with particular success in predicting elastic collisions and rotational dynamics. This work significantly contributes to physics-informed machine learning by showcasing the immense potential of deep residual networks in modeling complex 3D physical systems. We discuss our approach's limitations and propose future directions for improving generalization to more diverse object shapes and materials.