arXiv subjects

Dhruv Shah

Publications and source records attributed to Dhruv Shah.

81 records · Page 5Linked to original sources

arXiv2021

Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments

Geometric methods for solving open-world off-road navigation tasks, by learning occupancy and metric maps, provide good generalization but can be brittle in outdoor environments that violate their assumptions (e.g., tall grass). Learning-based methods can directly learn collision-free behavior from raw observations, but are difficult to integrate with standard geometry-based pipelines. This creates an unfortunate conflict -- either use learning and lose out on well-understood geometric navigational components, or do not use it, in favor of extensively hand-tuned geometry-based cost maps. In this work, we reject this dichotomy by designing the learning and non-learning-based components in a way such that they can be effectively combined in a self-supervised manner. Both components contribute to a planning criterion: the learned component contributes predicted traversability as rewards, while the geometric component contributes obstacle cost information. We instantiate and comparatively evaluate our system in both in-distribution and out-of-distribution environments, showing that this approach inherits complementary gains from the learned and geometric components and significantly outperforms either of them. Videos of our results are hosted at https://sites.google.com/view/hybrid-imitative-planning

cs.RO↗

arXiv2021

ViNG: Learning Open-World Navigation with Visual Goals

We propose a learning-based navigation system for reaching visually indicated goals and demonstrate this system on a real mobile robot platform. Learning provides an appealing alternative to conventional methods for robotic navigation: instead of reasoning about environments in terms of geometry and maps, learning can enable a robot to learn about navigational affordances, understand what types of obstacles are traversable (e.g., tall grass) or not (e.g., walls), and generalize over patterns in the environment. However, unlike conventional planning algorithms, it is harder to change the goal for a learned policy during deployment. We propose a method for learning to navigate towards a goal image of the desired destination. By combining a learned policy with a topological graph constructed out of previously observed data, our system can determine how to reach this visually indicated goal even in the presence of variable appearance and lighting. Three key insights, waypoint proposal, graph pruning and negative mining, enable our method to learn to navigate in real-world environments using only offline data, a setting where prior methods struggle. We instantiate our method on a real outdoor ground robot and show that our system, which we call ViNG, outperforms previously-proposed methods for goal-conditioned reinforcement learning, including other methods that incorporate reinforcement learning and search. We also study how \sysName generalizes to unseen environments and evaluate its ability to adapt to such an environment with growing experience. Finally, we demonstrate ViNG on a number of real-world applications, such as last-mile delivery and warehouse inspection. We encourage the reader to visit the project website for videos of our experiments and demonstrations sites.google.com/view/ving-robot.

cs.RO↗

arXiv2020

Low Density Parity Check Code (LDPC Codes) Overview

This paper basically expresses the core fundamentals and brief overview of the research of R. G. GALLAGER [1] on Low-Density Parity-Check (LDPC) codes and various parameters related to LDPC codes like, encoding and decoding of LDPC codes, code rate, parity check matrix, tanner graph. We also discuss advantages and applications as well as the usage of LDPC codes in 5G technology. We have simulated encoding and decoding of LDPC codes and have acquired results in terms of BER vs SNR graph in MATLAB software. This report was submitted as an assignment in Nirma University

cs.IT↗

arXiv2020

Effect Of Weather Conditions On FSO Link

Free Space Optics (FSO) is a developing technology for Line of Sight communication that uses light propagation in free space that provides various advantages like high bandwidth, high data rate, ease of installation, free licensing and secure communication. Thus, FSO is a developing technology that can be used in numerous applications for Line of Sight Communication. But the diverse effects like attenuation on FSO communication link due to environmental factors and weather conditions like fog, rain, dust, sand storms, clouds, temperature and the other factors like range, effects of physical obstructions are an essential topic for study which is discussed in this paper. We have done the simulation for the effects of fog and rain on the FSO communication link in Opti system software [1]. This is submitted in leu of FOC assignment at Nirma University.

eess.SP↗

arXiv2020

Aerial Manipulation Using Hybrid Force and Position NMPC Applied to Aerial Writing

Aerial manipulation aims at combining the manoeuvrability of aerial vehicles with the manipulation capabilities of robotic arms. This, however, comes at the cost of the additional control complexity due to the coupling of the dynamics of the two systems. In this paper we present a NMPC specifically designed for MAVs equipped with a robotic arm. We formulate a hybrid control model for the combined MAV-arm system which incorporates interaction forces acting on the end effector. We explain the practical implementation of our algorithm and show extensive experimental results of our custom built system performing multiple aerial-writing tasks on a whiteboard, revealing accuracy in the order of millimetres.

cs.RO↗

arXiv2020

The Ingredients of Real-World Robotic Reinforcement Learning

The success of reinforcement learning for real world robotics has been, in many cases limited to instrumented laboratory scenarios, often requiring arduous human effort and oversight to enable continuous learning. In this work, we discuss the elements that are needed for a robotic learning system that can continually and autonomously improve with data collected in the real world. We propose a particular instantiation of such a system, using dexterous manipulation as our case study. Subsequently, we investigate a number of challenges that come up when learning without instrumentation. In such settings, learning must be feasible without manually designed resets, using only on-board perception, and without hand-engineered reward functions. We propose simple and scalable solutions to these challenges, and then demonstrate the efficacy of our proposed system on a set of dexterous robotic manipulation tasks, providing an in-depth analysis of the challenges associated with this learning paradigm. We demonstrate that our complete system can learn without any human intervention, acquiring a variety of vision-based skills with a real-world three-fingered hand. Results and videos can be found at https://sites.google.com/view/realworld-rl/

cs.LG↗

arXiv2020

Toward A Neuro-inspired Creative Decoder

Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by this seminal finding, in this study we propose a creative decoder within a deep generative framework, which involves direct modulation of the neuronal activation pattern after sampling from the learned latent space. The proposed approach is fully unsupervised and can be used off-the-shelf. Several novelty metrics and human evaluation were used to evaluate the creative capacity of the deep decoder. Our experiments on different image datasets (MNIST, FMNIST, MNIST+FMNIST, WikiArt and CelebA) reveal that atypical co-activation of highly activated and weakly activated neurons in a deep decoder promotes generation of novel and meaningful artifacts.

cs.AI↗

arXiv2020

Machine learning based co-creative design framework

We propose a flexible, co-creative framework bringing together multiple machine learning techniques to assist human users to efficiently produce effective creative designs. We demonstrate its potential with a perfume bottle design case study, including human evaluation and quantitative and qualitative analyses.

cs.HC↗

arXiv2018

Robust Localization of an Arbitrary Distribution of Radioactive Sources for Aerial Inspection

Radiation source detection has seen various applications in the past decade, ranging from the detection of dirty bombs in public places to scanning critical nuclear facilities for leakage or flaws, and in the autonomous inspection of nuclear sites. Despite the success in detecting single point sources or a small number of spatially separated point sources, most of the existing algorithms fail to localize sources in complex scenarios with a large number of point sources or non-trivial distributions & bulk sources. Even in simpler environments, most existing algorithms are not scalable to larger regions and/or higher dimensional spaces. For effective autonomous inspection, we not only need to estimate the positions of the sources, but also the number, distribution, and intensities of each of them. In this paper, we present a novel algorithm for the robust localization of an arbitrary distribution of radiation sources using multi-layer sequential Monte Carlo methods coupled with suitable clustering algorithms. We achieve near-perfect accuracy, in terms of F1-scores (> 0.95), while allowing the algorithm to scale, both to large regions in space and to higher dimensional spaces (5 tested).

cs.RO↗