Diffusion models based on stochastic differential equations (SDEs) gradually perturb a data distribution $p(\mathbf{x})$ over time by adding noise to it. A neural network is trained to approximate the score $\nabla_\mathbf{x} \log p_t(\mathbf{x})$ at time $t$, which can be used to reverse the corruption process. In this paper, we focus on learning the score field that is associated with the time evolution according to a physics operator in the presence of natural non-deterministic physical processes like diffusion. A decisive difference to previous methods is that the SDE underlying our approach transforms the state of a physical system to another state at a later time. For that purpose, we replace the drift of the underlying SDE formulation with a differentiable simulator or a neural network approximation of the physics. We propose different training strategies based on the so-called probability flow ODE to fit a training set of simulation trajectories and discuss their relation to the score matching objective. For inference, we sample plausible trajectories that evolve towards a given end state using the reverse-time SDE and demonstrate the competitiveness of our approach for different challenging inverse problems.
To assist underwater object detection for better performance, image enhancement technology is often used as a pre-processing step. However, most of the existing enhancement methods tend to pursue the visual quality of an image, instead of providing effective help for detection tasks. In fact, image enhancement algorithms should be optimized with the goal of utility improvement. In this paper, to adapt to the underwater detection tasks, we proposed a lightweight dynamic enhancement algorithm using a contribution dictionary to guide low-level corrections. Dynamic solutions are designed to capture differences in detection preferences. In addition, it can also balance the inconsistency between the contribution of correction operations and their time complexity. Experimental results in real underwater object detection tasks show the superiority of our proposed method in both generalization and real-time performance.
Given a dataset on actions and resulting long-term rewards, a direct estimation approach fits value functions that minimize prediction error on the training data. Temporal difference learning (TD) methods instead fit value functions by minimizing the degree of temporal inconsistency between estimates made at successive time-steps. Focusing on finite state Markov chains, we provide a crisp asymptotic theory of the statistical advantages of this approach. First, we show that an intuitive inverse trajectory pooling coefficient completely characterizes the percent reduction in mean-squared error of value estimates. Depending on problem structure, the reduction could be enormous or nonexistent. Next, we prove that there can be dramatic improvements in estimates of the difference in value-to-go for two states: TD's errors are bounded in terms of a novel measure - the problem's trajectory crossing time - which can be much smaller than the problem's time horizon.
For grasp network algorithms, generating grasp datasets for a large number of 3D objects is a crucial task. However, generating grasp datasets for hundreds of objects can be very slow and consume a lot of storage resources, which hinders algorithm iteration and promotion. For point cloud grasp network algorithms, the network input is essentially the internal point cloud of the grasp area that intersects with the object in the gripper coordinate system. Due to the existence of a large number of completely consistent gripper area point clouds based on the gripper coordinate system in the grasp dataset generated for hundreds of objects, it is possible to remove the consistent gripper area point clouds from many objects and assemble them into a single object to generate the grasp dataset, thus replacing the enormous workload of generating grasp datasets for hundreds of objects. We propose a new approach to map the repetitive features of a large number of objects onto a finite set.To this end, we propose a method for extracting the gripper area point cloud that intersects with the object from the simulator and design a gripper feature filter to remove the shape-repeated gripper space area point clouds, and then assemble them into a single object. The experimental results show that the time required to generate the new object grasp dataset is greatly reduced compared to generating the grasp dataset for hundreds of objects, and it performs well in real machine grasping experiments. We will release the data and tools after the paper is accepted.
Explosive Ordnance Disposal (EOD) suits are widely used to protect human operators to execute emergency tasks such as bomb disposal and neutralization. Current suit designs still need to be improved in terms of wearer comfort, which can be assessed based on the interaction forces at the human-suit contact regions. This paper introduces a simulation-based modeling framework that computes the interaction loads at the human-suit interface based on a wearer's kinematic movement data. The proposed modeling framework consists of three primary components: a) inertial and geometric modeling of the EOD suit, b) state estimation of the wearer's in-suit movement, and c) inverse dynamics analysis to calculate the human-suit interface forces based on the simulated human-suit model and the estimated human movement data. This simulation-based modeling method could be used to complement experimental testing for improving the time and cost efficiency of EOD suit evaluation. The accuracy of the simulated interface load was experimentally benchmarked during three different human tasks (each with three trials), by comparing the predicted interface forces with that measured by commercial pressure sensors.
Collective decision-making is an essential capability of large-scale multi-robot systems to establish autonomy on the swarm level. A large portion of literature on collective decision-making in swarm robotics focuses on discrete decisions selecting from a limited number of options. Here we assign a decentralized robot system with the task of exploring an unbounded environment, finding consensus on the mean of a measurable environmental feature, and aggregating at areas where that value is measured (e.g., a contour line). A unique quality of this task is a causal loop between the robots' dynamic network topology and their decision-making. For example, the network's mean node degree influences time to convergence while the currently agreed-on mean value influences the swarm's aggregation location, hence, also the network structure as well as the precision error. We propose a control algorithm and study it in real-world robot swarm experiments in different environments. We show that our approach is effective and achieves higher precision than a control experiment. We anticipate applications, for example, in containing pollution with surface vehicles.
The transformer is a widely-used building block in modern neural networks. However, when applied to audio data, the transformer's acausal behaviour, which we term Acausal Attention (AA), has generally limited its application to offline tasks. In this paper we introduce Streaming Attention (SA), which operates causally with fixed latency, and requires lower compute and memory resources than AA to train. Next, we introduce Low Latency Streaming Attention (LLSA), a method which combines multiple SA layers without latency build-up proportional to the layer count. Comparative analysis between AA, SA and LLSA on Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER) tasks are presented. The results show that causal SA-based networks with fixed latencies of a few seconds (e.g. 1.8 seconds) and LLSA networks with latencies as short as 300 ms can perform comparably with acausal (AA) networks. We conclude that SA and LLSA methods retain many of the benefits of conventional acausal transformers, but with latency characteristics that make them practical to run in real-time streaming applications.
A new class of iterated linearization-based nonlinear filters, dubbed dynamically iterated filters, is presented. Contrary to regular iterated filters such as the iterated extended Kalman filter (IEKF), iterated unscented Kalman filter (IUKF) and iterated posterior linearization filter (IPLF), dynamically iterated filters also take nonlinearities in the transition model into account. The general filtering algorithm is shown to essentially be a (locally over one time step) iterated Rauch-Tung-Striebel smoother. Three distinct versions of the dynamically iterated filters are especially investigated: analogues to the IEKF, IUKF and IPLF. The developed algorithms are evaluated on 25 different noise configurations of a tracking problem with a nonlinear transition model and linear measurement model, a scenario where conventional iterated filters are not useful. Even in this "simple" scenario, the dynamically iterated filters are shown to have superior root mean-squared error performance as compared to their respective baselines, the EKF and UKF. Particularly, even though the EKF diverges in 22 out of 25 configurations, the dynamically iterated EKF remains stable in 20 out of 25 scenarios, only diverging under high noise.
Recommendation systems are a core feature of social media companies with their uses including recommending organic and promoted contents. Many modern recommendation systems are split into multiple stages - candidate generation and heavy ranking - to balance computational cost against recommendation quality. We focus on the candidate generation phase of a large-scale ads recommendation problem in this paper, and present a machine learning first heterogeneous re-architecture of this stage which we term TwERC. We show that a system that combines a real-time light ranker with sourcing strategies capable of capturing additional information provides validated gains. We present two strategies. The first strategy uses a notion of similarity in the interaction graph, while the second strategy caches previous scores from the ranking stage. The graph based strategy achieves a 4.08% revenue gain and the rankscore based strategy achieves a 1.38% gain. These two strategies have biases that complement both the light ranker and one another. Finally, we describe a set of metrics that we believe are valuable as a means of understanding the complex product trade offs inherent in industrial candidate generation systems.
Numerous real-world problems from a diverse set of application areas exist that exhibit temporal dependencies. We focus on a specific type of time series classification which we refer to as aggregated time series classification. We consider an aggregated sequence of a multi-variate time series, and propose a methodology to make predictions based solely on the aggregated information. As a case study, we apply our methodology to the challenging problem of household water end-use dissagregation when using non-intrusive water monitoring. Our methodology does not require a-priori identification of events, and to our knowledge, it is considered for the first time. We conduct an extensive experimental study using a residential water-use simulator, involving different machine learning classifiers, multi-label classification methods, and successfully demonstrate the effectiveness of our methodology.