arXiv subjects

Kartic Subr

Publications and source records attributed to Kartic Subr.

27 records · Page 2Linked to original sources

arXiv2021

Q-NET: A Network for Low-Dimensional Integrals of Neural Proxies

Many applications require the calculation of integrals of multidimensional functions. A general and popular procedure is to estimate integrals by averaging multiple evaluations of the function. Often, each evaluation of the function entails costly computations. The use of a \emph{proxy} or surrogate for the true function is useful if repeated evaluations are necessary. The proxy is even more useful if its integral is known analytically and can be calculated practically. We propose the use of a versatile yet simple class of artificial neural networks -- sigmoidal universal approximators -- as a proxy for functions whose integrals need to be estimated. We design a family of fixed networks, which we call Q-NETs, that operate on parameters of a trained proxy to calculate exact integrals over \emph{any subset of dimensions} of the input domain. We identify transformations to the input space for which integrals may be recalculated without resampling the integrand or retraining the proxy. We highlight the benefits of this scheme for a few applications such as inverse rendering, generation of procedural noise, visualization and simulation. The proposed proxy is appealing in the following contexts: the dimensionality is low ($<10$D); the estimation of integrals needs to be decoupled from the sampling strategy; sparse, adaptive sampling is used; marginal functions need to be known in functional form; or when powerful Single Instruction Multiple Data/Thread (SIMD/SIMT) pipelines are available for computation.

stat.ML↗

arXiv2021

Action sequencing using visual permutations

Humans can easily reason about the sequence of high level actions needed to complete tasks, but it is particularly difficult to instil this ability in robots trained from relatively few examples. This work considers the task of neural action sequencing conditioned on a single reference visual state. This task is extremely challenging as it is not only subject to the significant combinatorial complexity that arises from large action sets, but also requires a model that can perform some form of symbol grounding, mapping high dimensional input data to actions, while reasoning about action relationships. This paper takes a permutation perspective and argues that action sequencing benefits from the ability to reason about both permutations and ordering concepts. Empirical analysis shows that neural models trained with latent permutations outperform standard neural architectures in constrained action sequencing tasks. Results also show that action sequencing using visual permutations is an effective mechanism to initialise and speed up traditional planning techniques and successfully scales to far greater action set sizes than models considered previously.

cs.RO↗

arXiv2020

IV-Posterior: Inverse Value Estimation for Interpretable Policy Certificates

Model-free reinforcement learning (RL) is a powerful tool to learn a broad range of robot skills and policies. However, a lack of policy interpretability can inhibit their successful deployment in downstream applications, particularly when differences in environmental conditions may result in unpredictable behaviour or generalisation failures. As a result, there has been a growing emphasis in machine learning around the inclusion of stronger inductive biases in models to improve generalisation. This paper proposes an alternative strategy, inverse value estimation for interpretable policy certificates (IV-Posterior), which seeks to identify the inductive biases or idealised conditions of operation already held by pre-trained policies, and then use this information to guide their deployment. IV-Posterior uses MaskedAutoregressive Flows to fit distributions over the set of conditions or environmental parameters in which a policy is likely to be effective. This distribution can then be used as a policy certificate in downstream applications. We illustrate the use of IV-Posterior across a two environments, and show that substantial performance gains can be obtained when policy selection incorporates knowledge of the inductive biases that these policies hold.

cs.LG↗

arXiv2020

Vid2Param: Modelling of Dynamics Parameters from Video

Videos provide a rich source of information, but it is generally hard to extract dynamical parameters of interest. Inferring those parameters from a video stream would be beneficial for physical reasoning. Robots performing tasks in dynamic environments would benefit greatly from understanding the underlying environment motion, in order to make future predictions and to synthesize effective control policies that use this inductive bias. Online physical reasoning is therefore a fundamental requirement for robust autonomous agents. When the dynamics involves multiple modes (due to contacts or interactions between objects) and sensing must proceed directly from a rich sensory stream such as video, then traditional methods for system identification may not be well suited. We propose an approach wherein fast parameter estimation can be achieved directly from video. We integrate a physically based dynamics model with a recurrent variational autoencoder, by introducing an additional loss to enforce desired constraints. The model, which we call Vid2Param, can be trained entirely in simulation, in an end-to-end manner with domain randomization, to perform online system identification, and make probabilistic forward predictions of parameters of interest. This enables the resulting model to encode parameters such as position, velocity, restitution, air drag and other physical properties of the system. We illustrate the utility of this in physical experiments wherein a PR2 robot with a velocity constrained arm must intercept an unknown bouncing ball with partly occluded vision, by estimating the physical parameters of this ball directly from the video trace after the ball is released.

cs.RO↗

arXiv2020

WhoAmI: An Automatic Tool for Visual Recognition of Tiger and Leopard Individuals in the Wild

Photographs of wild animals in their natural habitats can be recorded unobtrusively via cameras that are triggered by motion nearby. The installation of such camera traps is becoming increasingly common across the world. Although this is a convenient source of invaluable data for biologists, ecologists and conservationists, the arduous task of poring through potentially millions of pictures each season introduces prohibitive costs and frustrating delays. We develop automatic algorithms that are able to detect animals, identify the species of animals and to recognize individual animals for two species. we propose the first fully-automatic tool that can recognize specific individuals of leopard and tiger due to their characteristic body markings. We adopt a class of supervised learning approach of machine learning where a Deep Convolutional Neural Network (DCNN) is trained using several instances of manually-labelled images for each of the three classification tasks. We demonstrate the effectiveness of our approach on a data set of camera-trap images recorded in the jungles of Southern India.

cs.CV↗

arXiv2020

Jittering Samples using a kd-Tree Stratification

Monte Carlo sampling techniques are used to estimate high-dimensional integrals that model the physics of light transport in virtual scenes for computer graphics applications. These methods rely on the law of large numbers to estimate expectations via simulation, typically resulting in slow convergence. Their errors usually manifest as undesirable grain in the pictures generated by image synthesis algorithms. It is well known that these errors diminish when the samples are chosen appropriately. A well known technique for reducing error operates by subdividing the integration domain, estimating integrals in each \emph{stratum} and aggregating these values into a stratified sampling estimate. Naïve methods for stratification, based on a lattice (grid) are known to improve the convergence rate of Monte Carlo, but require samples that grow exponentially with the dimensionality of the domain. We propose a simple stratification scheme for $d$ dimensional hypercubes using the kd-tree data structure. Our scheme enables the generation of an arbitrary number of equal volume partitions of the rectangular domain, and $n$ samples can be generated in $O(n)$ time. Since we do not always need to explicitly build a kd-tree, we provide a simple procedure that allows the sample set to be drawn fully in parallel without any precomputation or storage, speeding up sampling to $O(\log n)$ time per sample when executed on $n$ cores. If the tree is implicitly precomputed ($O(n)$ storage) the parallelised run time reduces to $O(1)$ on $n$ cores. In addition to these benefits, we provide an upper bound on the worst case star-discrepancy for $n$ samples matching that of lattice-based sampling strategies, which occur as a special case of our proposed method. We use a number of quantitative and qualitative tests to compare our method against state of the art samplers for image synthesis.

cs.GR↗

arXiv2019

To Stir or Not to Stir: Online Estimation of Liquid Properties for Pouring Actions

Our brains are able to exploit coarse physical models of fluids to solve everyday manipulation tasks. There has been considerable interest in developing such a capability in robots so that they can autonomously manipulate fluids adapting to different conditions. In this paper, we investigate the problem of adaptation to liquids with different characteristics. We develop a simple calibration task (stirring with a stick) that enables rapid inference of the parameters of the liquid from RBG data. We perform the inference in the space of simulation parameters rather than on physically accurate parameters. This facilitates prediction and optimization tasks since the inferred parameters may be fed directly to the simulator. We demonstrate that our "stirring" learner performs better than when the robot is calibrated with pouring actions. We show that our method is able to infer properties of three different liquids -- water, glycerin and gel -- and present experimental results by executing stirring and pouring actions on a UR10. We believe that decoupling of the training actions from the goal task is an important step towards simple, autonomous learning of the behavior of different fluids in unstructured environments.

cs.RO↗

arXiv2019

Active Localization of Gas Leaks using Fluid Simulation

Sensors are routinely mounted on robots to acquire various forms of measurements in spatio-temporal fields. Locating features within these fields and reconstruction (mapping) of the dense fields can be challenging in resource-constrained situations, such as when trying to locate the source of a gas leak from a small number of measurements. In such cases, a model of the underlying complex dynamics can be exploited to discover informative paths within the field. We use a fluid simulator as a model, to guide inference for the location of a gas leak. We perform localization via minimization of the discrepancy between observed measurements and gas concentrations predicted by the simulator. Our method is able to account for dynamically varying parameters of wind flow (e.g., direction and strength), and its effects on the observed distribution of gas. We develop algorithms for off-line inference as well as for on-line path discovery via active sensing. We demonstrate the efficiency, accuracy and versatility of our algorithm using experiments with a physical robot conducted in outdoor environments. We deploy an unmanned air vehicle (UAV) mounted with a CO2 sensor to automatically seek out a gas cylinder emitting CO2 via a nozzle. We evaluate the accuracy of our algorithm by measuring the error in the inferred location of the nozzle, based on which we show that our proposed approach is competitive with respect to state of the art baselines.

cs.RO↗

arXiv2019

Automatic Generation of Constrained Furniture Layouts

Efficient authoring of vast virtual environments hinges on algorithms that are able to automatically generate content while also being controllable. We propose a method to automatically generate furniture layouts for indoor environments. Our method is simple, efficient, human-interpretable and amenable to a wide variety of constraints. We model the composition of rooms into classes of objects and learn joint (co-occurrence) statistics from a database of training layouts. We generate new layouts by performing a sequence of conditional sampling steps, exploiting the statistics learned from the database. The generated layouts are specified as 3D object models, along with their positions and orientations. We show they are of equivalent perceived quality to the training layouts, and compare favorably to a state-of-the-art method. We incorporate constraints using a general mechanism -- rejection sampling -- which provides great flexibility at the cost of extra computation. We demonstrate the versatility of our method by applying a wide variety of constraints relevant to real-world applications.

cs.CV↗