arXiv subjects

Vijay Kumar

Publications and source records attributed to Vijay Kumar.

At least 199 records · Page 11Linked to original sources

arXiv2019

DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance

Depth estimation is an important capability for autonomous vehicles to understand and reconstruct 3D environments as well as avoid obstacles during the execution. Accurate depth sensors such as LiDARs are often heavy, expensive and can only provide sparse depth while lighter depth sensors such as stereo cameras are noiser in comparison. We propose an end-to-end learning algorithm that is capable of using sparse, noisy input depth for refinement and depth completion. Our model also produces the camera pose as a byproduct, making it a great solution for autonomous systems. We evaluate our approach on both indoor and outdoor datasets. Empirical results show that our method performs well on the KITTI~\cite{kitti_geiger2012we} dataset when compared to other competing methods, while having superior performance in dealing with sparse, noisy input depth on the TUM~\cite{sturm12iros} dataset.

cs.CV↗

arXiv2019

Smallest Fullerene-like Structures of Boron with Cr, Mo, and W Encapsulation

Using density functional theory calculations, we study doping of a Cr, Mo, and W atom in boron clusters in the size range of 18-24 atoms and report the finding of metal atom encapsulated fullerene-like cage structures with 20 to 24 boron atoms in contrast to a fullerene-like structure of pure boron with 40 atoms. Our results show that bicapped drum-shaped structures are favored for neutral Cr@B$_{18}$, Mo@B$_{20}$, and W@B$_{20}$ clusters whereas a drum-shaped structure is preferred for neutral, cation, and anion of Mo@B$_{18}$ and W@B$_{18}$. Further, we find that B$_{20}$ is the smallest cage for Cr encapsulation, while B$_{22}$ is the smallest symmetric cage for Mo and W encapsulation and it is magic. Symmetric cage structures are also obtained for Mo@B$_{24}$ and W@B$_{24}$. A detailed analysis of the bonding character and molecular orbitals suggests that Cr@B$_{18}$, Cr@B$_{20}$, M@B$_{22}$ (M = Cr, Mo, and W) and M@B$_{24}$ (M = Mo and W) cages are stabilized with 18 $π$-bonded valence electrons whereas the drum-shaped M@B$_{18}$ (M = Mo and W) clusters are stabilized by 20 $π$-bonded valence electrons. Calculations with PBE0 functional in Gaussian 09 code show that in all cases of neutral clusters there is a large highest occupied molecular orbital-lowest unoccupied molecular orbital (HOMO-LUMO) gap. In some cases the lowest energy isomer of the charged clusters is different from the one for the neutral. We discuss the calculated infrared and Raman spectra for the neutral and cation clusters as well as the electronic structure of the anion clusters. Also we report results for isoelectronic anion and neutral clusters doped with V, Nb, and Ta which are generally similar to those obtained for Mo and W doped clusters. These results would be helpful to confirm the formation of these doped boron clusters experimentally.

physics.atm-clus↗

arXiv2019

Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints

In this paper, we present a learning approach to goal assignment and trajectory planning for unlabeled robots operating in 2D, obstacle-filled workspaces. More specifically, we tackle the unlabeled multi-robot motion planning problem with motion constraints as a multi-agent reinforcement learning problem with some sparse global reward. In contrast with previous works, which formulate an entirely new hand-crafted optimization cost or trajectory generation algorithm for a different robot dynamic model, our framework is a general approach that is applicable to arbitrary robot models. Further, by using the velocity obstacle, we devise a smooth projection that guarantees collision free trajectories for all robots with respect to their neighbors and obstacles. The efficacy of our algorithm is demonstrated through varied simulations.

cs.RO↗

arXiv2019

DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion

In this paper we propose a convolutional neural network that is designed to upsample a series of sparse range measurements based on the contextual cues gleaned from a high resolution intensity image. Our approach draws inspiration from related work on super-resolution and in-painting. We propose a novel architecture that seeks to pull contextual cues separately from the intensity image and the depth features and then fuse them later in the network. We argue that this approach effectively exploits the relationship between the two modalities and produces accurate results while respecting salient image structures. We present experimental results to demonstrate that our approach is comparable with state of the art methods and generalizes well across multiple datasets.

cs.CV↗

arXiv2019

MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks

Real-time semantic image segmentation on platforms subject to size, weight and power (SWaP) constraints is a key area of interest for air surveillance and inspection. In this work, we propose MAVNet: a small, light-weight, deep neural network for real-time semantic segmentation on micro Aerial Vehicles (MAVs). MAVNet, inspired by ERFNet, features 400 times fewer parameters and achieves comparable performance with some reference models in empirical experiments. Our model achieves a trade-off between speed and accuracy, achieving up to 48 FPS on an NVIDIA 1080Ti and 9 FPS on the NVIDIA Jetson Xavier when processing high resolution imagery. Additionally, we provide two novel datasets that represent challenges in semantic segmentation for real-time MAV tracking and infrastructure inspection tasks and verify MAVNet on these datasets. Our algorithm and datasets are made publicly available.

cs.CV↗

arXiv2019

A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning

We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a naive optimization of the triplet loss function has a run-time complexity O(N^3), where N is the number of training samples. Such optimization scales poorly, and the most common approach proposed to address this high complexity issue is based on sub-sampling the set of triplets needed for the training process. Another approach explored in the field relies on an ad-hoc linearization (in terms of N) of the triplet loss that introduces class centroids, which must be optimized using the whole training set for each mini-batch - this means that a naive implementation of this approach has run-time complexity O(N^2). This complexity issue is usually mitigated with poor, but computationally cheap, approximate centroid optimization methods. In this paper, we first propose a solid theory on the linearization of the triplet loss with the use of class centroids, where the main conclusion is that our new linear loss represents a tight upper-bound to the triplet loss. Furthermore, based on the theory above, we propose a training algorithm that no longer requires the centroid optimization step, which means that our approach is the first in the field with a guaranteed linear run-time complexity. We show that the training of deep distance metric learning methods using the proposed upper-bound is substantially faster than triplet-based methods, while producing competitive retrieval accuracy results on benchmark datasets (CUB-200-2011 and CAR196).

cs.CV↗

arXiv2019

Decentralization of Multiagent Policies by Learning What to Communicate

Effective communication is required for teams of robots to solve sophisticated collaborative tasks. In practice it is typical for both the encoding and semantics of communication to be manually defined by an expert; this is true regardless of whether the behaviors themselves are bespoke, optimization based, or learned. We present an agent architecture and training methodology using neural networks to learn task-oriented communication semantics based on the example of a communication-unaware expert policy. A perimeter defense game illustrates the system's ability to handle dynamically changing numbers of agents and its graceful degradation in performance as communication constraints are tightened or the expert's observability assumptions are broken.

cs.RO↗

arXiv2019

Inverse Optimal Planning for Air Traffic Control

We envision a system that concisely describes the rules of air traffic control, assists human operators and supports dense autonomous air traffic around commercial airports. We develop a method to learn the rules of air traffic control from real data as a cost function via maximum entropy inverse reinforcement learning. This cost function is used as a penalty for a search-based motion planning method that discretizes both the control and the state space. We illustrate the methodology by showing that our approach can learn to imitate the airport arrival routes and separation rules of dense commercial air traffic. The resulting trajectories are shown to be safe, feasible, and efficient.

cs.RO↗

arXiv2019

Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association

We present a cheap, lightweight, and fast fruit counting pipeline that uses a single monocular camera. Our pipeline that relies only on a monocular camera, achieves counting performance comparable to state-of-the-art fruit counting system that utilizes an expensive sensor suite including LiDAR and GPS/INS on a mango dataset. Our monocular camera pipeline begins with a fruit detection component that uses a deep neural network. It then uses semantic structure from motion (SFM) to convert these detections into fruit counts by estimating landmark locations of the fruit in 3D, and using these landmarks to identify double counting scenarios. There are many benefits of developing a low cost and lightweight fruit counting system, including applicability to agriculture in developing countries, where monetary constraints or unstructured environments necessitate cheaper hardware solutions.

cs.RO↗

arXiv2019

Nuclear Environments Inspection with Micro Aerial Vehicles: Algorithms and Experiments

In this work, we address the estimation, planning, control and mapping problems to allow a small quadrotor to autonomously inspect the interior of hazardous damaged nuclear sites. These algorithms run onboard on a computationally limited CPU. We investigate the effect of varying illumination on the system performance. To the best of our knowledge, this is the first fully autonomous system of this size and scale applied to inspect the interior of a full scale mock-up of a Primary Containment Vessel (PCV). The proposed solution opens up new ways to inspect nuclear reactors and to support nuclear decommissioning, which is well known to be a dangerous, long and tedious process. Experimental results with varying illumination conditions show the ability to navigate a full scale mock-up PCV pedestal and create a map of the environment, while concurrently avoiding obstacles.

cs.RO↗

arXiv2019

Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion

In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instantaneous camera pose. Given the flow and disparity predictions from the network, we apply a RANSAC outlier rejection scheme to find an inlier set of flows and disparities, which we use to solve for the relative camera pose in a least squares fashion. We show that this pipeline is fully differentiable, allowing us to combine the pose with the network outputs as an additional unsupervised training loss to further refine the predicted flows and disparities. This method not only allows us to directly regress relative pose from the network outputs, but also automatically segments away pixels that do not fit the rigid scene assumptions that many unsupervised structure from motion methods apply, such as on independently moving objects. We evaluate our method on the KITTI dataset, and demonstrate state of the art results, even in the presence of challenging independently moving objects.

cs.CV↗

arXiv2018

Towards Search-based Motion Planning for Micro Aerial Vehicles

Search-based motion planning has been used for mobile robots in many applications. However, it has not been fully developed and applied for planning full state trajectories of Micro Aerial Vehicles (MAVs) due to their complicated dynamics and the requirement of real-time computation. In this paper, we explore a search-based motion planning framework that plans dynamically feasible, collision-free, and resolution optimal and complete trajectories. This paper extends the search-based planning approach to address three important scenarios for MAVs navigation: (i) planning safe trajectories in the presence of motion uncertainty; (ii) planning with constraints on field-of-view and (iii) planning in dynamic environments. We show that these problems can be solved effectively and efficiently using the proposed search-based planning with motion primitives.

cs.RO↗

arXiv2018

Stochastic 2-D Motion Planning with a POMDP Framework

Motion planning is challenging when it comes to the case of imperfect state information. Decision should be made based on belief state which evolves according to the noise from the system dynamics and sensor measurement. In this paper, we propose the QV-Tree Search algorithm which combines the state-of-art offline and online approximation methods for POMDP. Instead of full node expansions in the tree search, only probable future observations are considered through forward sampling. This modification helps reduce online computation time and allows for GPU acceleration. We show using repre- sentative examples that the proposed QV-Tree Search is able to actively localize the robot in order to reach the goal location with high probability. The results of the proposed method is also compared with the A* and MDP algorithms, neither of which handles state uncertainty directly. The comparison shows that QV-Tree Search is able to drive the robot to the goal with higher success rate and fewer steps.

cs.RO↗

arXiv2018

The Open Vision Computer: An Integrated Sensing and Compute System for Mobile Robots

In this paper we describe the Open Vision Computer (OVC) which was designed to support high speed, vision guided autonomous drone flight. In particular our aim was to develop a system that would be suitable for relatively small-scale flying platforms where size, weight, power consumption and computational performance were all important considerations. This manuscript describes the primary features of our OVC system and explains how they are used to support fully autonomous indoor and outdoor exploration and navigation operations on our Falcon 250 quadrotor platform.

cs.RO↗

arXiv2018

Real Time Dense Depth Estimation by Fusing Stereo with Sparse Depth Measurements

We present an approach to depth estimation that fuses information from a stereo pair with sparse range measurements derived from a LIDAR sensor or a range camera. The goal of this work is to exploit the complementary strengths of the two sensor modalities, the accurate but sparse range measurements and the ambiguous but dense stereo information. These two sources are effectively and efficiently fused by combining ideas from anisotropic diffusion and semi-global matching. We evaluate our approach on the KITTI 2015 and Middlebury 2014 datasets, using randomly sampled ground truth range measurements as our sparse depth input. We achieve significant performance improvements with a small fraction of range measurements on both datasets. We also provide qualitative results from our platform using the PMDTec Monstar sensor. Our entire pipeline runs on an NVIDIA TX-2 platform at 5Hz on 1280x1024 stereo images with 128 disparity levels.

cs.CV↗

arXiv2018

U-Net for MAV-based Penstock Inspection: an Investigation of Focal Loss in Multi-class Segmentation for Corrosion Identification

Periodical inspection and maintenance of critical infrastructure such as dams, penstocks, and locks are of significant importance to prevent catastrophic failures. Conventional manual inspection methods require inspectors to climb along a penstock to spot corrosion, rust and crack formation which is unsafe, labor-intensive, and requires intensive training. This work presents an alternative approach using a Micro Aerial Vehicle (MAV) that autonomously flies to collect imagery which is then fed into a pretrained deep-learning model to identify corrosion. Our simplified U-Net trained with less than 40 image samples can do inference at 12 fps on a single GPU. We analyze different loss functions to solve the class imbalance problem, followed by a discussion on choosing proper metrics and weights for object classes. Results obtained with the dataset collected from Center Hill Dam, TN show that focal loss function, combined with a proper set of class weights yield better segmentation results than the base loss, Softmax cross entropy. Our method can be used in combination with planning algorithm to offer a complete, safe and cost-efficient solution to autonomous infrastructure inspection.

cs.CV↗

arXiv2018

Robust Fruit Counting: Combining Deep Learning, Tracking, and Structure from Motion

We present a novel fruit counting pipeline that combines deep segmentation, frame to frame tracking, and 3D localization to accurately count visible fruits across a sequence of images. Our pipeline works on image streams from a monocular camera, both in natural light, as well as with controlled illumination at night. We first train a Fully Convolutional Network (FCN) and segment video frame images into fruit and non-fruit pixels. We then track fruits across frames using the Hungarian Algorithm where the objective cost is determined from a Kalman Filter corrected Kanade-Lucas-Tomasi (KLT) Tracker. In order to correct the estimated count from tracking process, we combine tracking results with a Structure from Motion (SfM) algorithm to calculate relative 3D locations and size estimates to reject outliers and double counted fruit tracks. We evaluate our algorithm by comparing with ground-truth human-annotated visual counts. Our results demonstrate that our pipeline is able to accurately and reliably count fruits across image sequences, and the correction step can significantly improve the counting accuracy and robustness. Although discussed in the context of fruit counting, our work can extend to detection, tracking, and counting of a variety of other stationary features of interest such as leaf-spots, wilt, and blossom.

cs.CV↗

arXiv2018

Spin-Boson Model to Demonstrate Quantum Tunneling in Biomolecules using IBM Quantum Computer

Efficient simulation of quantum mechanical problems can be performed in a quantum computer where the interactions of qubits lead to the realization of various problems possessing quantum nature. Spin-Boson Model (SBM) is one of the striking models in quantum physics that enables to describe the dynamics of most of the two-level quantum systems through the bath of harmonic oscillators. Here we simulate the SBM and illustrate its applications in a biological system by designing appropriate quantum circuits for the Hamiltonian of photosynthetic reaction centers in IBM's 5-qubit quantum computer. We consider both two-level and four-level biomolecular quantum systems to observe the effect of quantum tunnelling in the reaction dynamics. We study the behaviour of tunneling by changing different parameters in the Hamiltonian of the system. The results of SBM can be applied to various two-, four- and multi-level quantum systems explicating electron transfer process.

quant-ph↗