arXiv subjects

Vijay Kumar

Publications and source records attributed to Vijay Kumar.

At least 217 records · Page 12Linked to original sources

arXiv2018

Experiments in Fast, Autonomous, GPS-Denied Quadrotor Flight

High speed navigation through unknown environments is a challenging problem in robotics. It requires fast computation and tight integration of all the subsystems on the robot such that the latency in the perception-action loop is as small as possible. Aerial robots add a limitation of payload capacity, which restricts the amount of computation that can be carried onboard. This requires efficient algorithms for each component in the navigation system. In this paper, we describe our quadrotor system which is able to smoothly navigate through mixed indoor and outdoor environments and is able to fly at speeds of more than 18 m/s. We provide an overview of our system and details about the specific component technologies that enable the high speed navigation capability of our platform. We demonstrate the robustness of our system through high speed autonomous flights and navigation through a variety of obstacle rich environments.

cs.RO↗

arXiv2018

Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients

In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these methods do not scale well. To address this, we propose casting the multi-agent reinforcement learning problem as a distributed optimization problem. Our algorithm assumes that for multi-agent settings, policies of individual agents in a given population live close to each other in parameter space and can be approximated by a single policy. With this simple assumption, we show our algorithm to be extremely effective for reinforcement learning in multi-agent settings. We demonstrate its effectiveness against existing comparable approaches on co-operative and competitive tasks.

cs.LG↗

arXiv2018

Spin-Hall effect in the scattering of structured light from plasmonic nanowire

Spin-orbit interactions are subwavelength phenomena which can potentially lead to numerous device related applications in nanophotonics. Here, we report Spin-Hall effect in the forward scattering of Hermite-Gaussian and Gaussian beams from a plasmonic nanowire. Asymmetric scattered radiation distribution was observed for circularly polarized beams. Asymmetry in the scattered radiation distribution changes the sign when the polarization handedness inverts. We found a significant enhancement in the Spin-Hall effect for Hermite-Gaussian beam as compared to Gaussian beam for constant input power. The difference between scattered powers perpendicular to the long axis of the plasmonic nanowire was used to quantify the enhancement. In addition to it, nodal line of HG beam acts as the marker for the Spin-Hall shift. Numerical calculations corroborate experimental observations and suggest that the Spin flow component of Poynting vector associated with the circular polarization is responsible for the Spin-Hall effect and its enhancement.

physics.optics↗

arXiv2018

Human Motion Capture Using a Drone

Current motion capture (MoCap) systems generally require markers and multiple calibrated cameras, which can be used only in constrained environments. In this work we introduce a drone-based system for 3D human MoCap. The system only needs an autonomously flying drone with an on-board RGB camera and is usable in various indoor and outdoor environments. A reconstruction algorithm is developed to recover full-body motion from the video recorded by the drone. We argue that, besides the capability of tracking a moving subject, a flying drone also provides fast varying viewpoints, which is beneficial for motion reconstruction. We evaluate the accuracy of the proposed system using our new DroCap dataset and also demonstrate its applicability for MoCap in the wild using a consumer drone.

cs.CV↗

arXiv2018

Learning Sample-Efficient Target Reaching for Mobile Robots

In this paper, we propose a novel architecture and a self-supervised policy gradient algorithm, which employs unsupervised auxiliary tasks to enable a mobile robot to learn how to navigate to a given goal. The dependency on the global information is eliminated by providing only sparse range-finder measurements to the robot. The partially observable planning problem is addressed by splitting it into a hierarchical process. We use convolutional networks to plan locally, and a differentiable memory to provide information about past time steps in the trajectory. These modules, combined in our network architecture, produce globally consistent plans. The sparse reward problem is mitigated by our modified policy gradient algorithm. We model the robots uncertainty with unsupervised tasks to force exploration. The novel architecture we propose with the modified version of the policy gradient algorithm allows our robot to reach the goal in a sample efficient manner, which is orders of magnitude faster than the current state of the art policy gradient algorithm. Simulation and experimental results are provided to validate the proposed approach.

cs.RO↗

arXiv2018

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

Homography estimation between multiple aerial images can provide relative pose estimation for collaborative autonomous exploration and monitoring. The usage on a robotic system requires a fast and robust homography estimation algorithm. In this study, we propose an unsupervised learning algorithm that trains a Deep Convolutional Neural Network to estimate planar homographies. We compare the proposed algorithm to traditional feature-based and direct methods, as well as a corresponding supervised learning algorithm. Our empirical results demonstrate that compared to traditional approaches, the unsupervised algorithm achieves faster inference speed, while maintaining comparable or better accuracy and robustness to illumination variation. In addition, on both a synthetic dataset and representative real-world aerial dataset, our unsupervised method has superior adaptability and performance compared to the supervised deep learning method.

cs.CV↗

arXiv2018

The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception

Event based cameras are a new passive sensing modality with a number of benefits over traditional cameras, including extremely low latency, asynchronous data acquisition, high dynamic range and very low power consumption. There has been a lot of recent interest and development in applying algorithms to use the events to perform a variety of 3D perception tasks, such as feature tracking, visual odometry, and stereo depth estimation. However, there currently lacks the wealth of labeled data that exists for traditional cameras to be used for both testing and development. In this paper, we present a large dataset with a synchronized stereo pair event based camera system, carried on a handheld rig, flown by a hexacopter, driven on top of a car and mounted on a motorcycle, in a variety of different illumination levels and environments. From each camera, we provide the event stream, grayscale images and IMU readings. In addition, we utilize a combination of IMU, a rigidly mounted lidar system, indoor and outdoor motion capture and GPS to provide accurate pose and depth images for each camera at up to 100Hz. For comparison, we also provide synchronized grayscale images and IMU readings from a frame based stereo camera system.

cs.RO↗

arXiv2018

Memory Augmented Control Networks

Planning problems in partially observable environments cannot be solved directly with convolutional networks and require some form of memory. But, even memory networks with sophisticated addressing schemes are unable to learn intelligent reasoning satisfactorily due to the complexity of simultaneously learning to access memory and plan. To mitigate these challenges we introduce the Memory Augmented Control Network (MACN). The proposed network architecture consists of three main parts. The first part uses convolutions to extract features and the second part uses a neural network-based planning module to pre-plan in the environment. The third part uses a network controller that learns to store those specific instances of past information that are necessary for planning. The performance of the network is evaluated in discrete grid world environments for path planning in the presence of simple and complex obstacles. We show that our network learns to plan and can generalize to new environments.

cs.AI↗

arXiv2018

Dense 3-D Mapping with Spatial Correlation via Gaussian Filtering

Constructing an occupancy representation of the environment is a fundamental problem for robot autonomy. Many accurate and efficient methods exist that address this problem but most assume that the occupancy states of different elements in the map representation are statistically independent. The focus of this paper is to provide a model that captures correlation of the occupancy of map elements. Correlation is important not only for improved accuracy but also for quantifying uncertainty in the map and for planning autonomous mapping trajectories based on the correlation among known and unknown areas. Recent work proposes Gaussian Process (GP) regression to capture covariance information and enable resolution-free occupancy estimation. The drawback of techniques based on GP regression (or classification) is that the computation complexity scales cubically with the length of the measurement history. Our main contribution is a new approach for occupancy mapping that models the binary nature of occupancy measurements precisely, via a Bernoulli distribution, and provides an efficient approximation of GP classification with complexity that does not scale with time. We prove that the error between the estimates provided by our method and those provided by GP classification is negligible. The proposed method is evaluated using both simulated data and real data collected using a Velodyne Puck 3-D range sensor.

cs.RO↗

arXiv2018

Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight

In recent years, vision-aided inertial odometry for state estimation has matured significantly. However, we still encounter challenges in terms of improving the computational efficiency and robustness of the underlying algorithms for applications in autonomous flight with micro aerial vehicles in which it is difficult to use high quality sensors and pow- erful processors because of constraints on size and weight. In this paper, we present a filter-based stereo visual inertial odometry that uses the Multi-State Constraint Kalman Filter (MSCKF) [1]. Previous work on stereo visual inertial odometry has resulted in solutions that are computationally expensive. We demonstrate that our Stereo Multi-State Constraint Kalman Filter (S-MSCKF) is comparable to state-of-art monocular solutions in terms of computational cost, while providing signifi- cantly greater robustness. We evaluate our S-MSCKF algorithm and compare it with state-of-art methods including OKVIS, ROVIO, and VINS-MONO on both the EuRoC dataset, and our own experimental datasets demonstrating fast autonomous flight with maximum speed of 17.5m/s in indoor and outdoor environments. Our implementation of the S-MSCKF is available at https://github.com/KumarRobotics/msckf_vio.

cs.RO↗

arXiv2017

Fast, Autonomous Flight in GPS-Denied and Cluttered Environments

One of the most challenging tasks for a flying robot is to autonomously navigate between target locations quickly and reliably while avoiding obstacles in its path, and with little to no a-priori knowledge of the operating environment. This challenge is addressed in the present paper. We describe the system design and software architecture of our proposed solution, and showcase how all the distinct components can be integrated to enable smooth robot operation. We provide critical insight on hardware and software component selection and development, and present results from extensive experimental testing in real-world warehouse environments. Experimental testing reveals that our proposed solution can deliver fast and robust aerial robot autonomous navigation in cluttered, GPS-denied environments.

cs.RO↗

arXiv2017

Search-based Motion Planning for Aggressive Flight in SE(3)

Quadrotors with large thrust-to-weight ratios are able to track aggressive trajectories with sharp turns and high accelerations. In this work, we develop a search-based trajectory planning approach that exploits the quadrotor maneuverability to generate sequences of motion primitives in cluttered environments. We model the quadrotor body as an ellipsoid and compute its flight attitude along trajectories in order to check for collisions against obstacles. The ellipsoid model allows the quadrotor to pass through gaps that are smaller than its diameter with non-zero pitch or roll angles. Without any prior information about the location of gaps and associated attitude constraints, our algorithm is able to find a safe and optimal trajectory that guides the robot to its goal as fast as possible. To accelerate planning, we first perform a lower dimensional search and use it as a heuristic to guide the generation of a final dynamically feasible trajectory. We analyze critical discretization parameters of motion primitive planning and demonstrate the feasibility of the generated trajectories in various simulations and real-world experiments.

cs.RO↗

arXiv2017

Search-based Motion Planning for Quadrotors using Linear Quadratic Minimum Time Control

In this work, we propose a search-based planning method to compute dynamically feasible trajectories for a quadrotor flying in an obstacle-cluttered environment. Our approach searches for smooth, minimum-time trajectories by exploring the map using a set of short-duration motion primitives. The primitives are generated by solving an optimal control problem and induce a finite lattice discretization on the state space which can be explored using a graph-search algorithm. The proposed approach is able to generate resolution-complete (i.e., optimal in the discretized space), safe, dynamically feasibility trajectories efficiently by exploiting the explicit solution of a Linear Quadratic Minimum Time problem. It does not assume a hovering initial condition and, hence, is suitable for fast online re-planning while the robot is moving. Quadrotor navigation with online re-planning is demonstrated using the proposed approach in simulation and physical experiments and comparisons with trajectory generation based on state-of-art quadratic programming are presented.

cs.RO↗

arXiv2017

End-to-End Navigation in Unknown Environments using Neural Networks

We investigate how a neural network can learn perception actions loops for navigation in unknown environments. Specifically, we consider how to learn to navigate in environments populated with cul-de-sacs that represent convex local minima that the robot could fall into instead of finding a set of feasible actions that take it to the goal. Traditional methods rely on maintaining a global map to solve the problem of over coming a long cul-de-sac. However, due to errors induced from local and global drift, it is highly challenging to maintain such a map for long periods of time. One way to mitigate this problem is by using learning techniques that do not rely on hand engineered map representations and instead output appropriate control policies directly from their sensory input. We first demonstrate that such a problem cannot be solved directly by deep reinforcement learning due to the sparse reward structure of the environment. Further, we demonstrate that deep supervised learning also cannot be used directly to solve this problem. We then investigate network models that offer a combination of reinforcement learning and supervised learning and highlight the significance of adding fully differentiable memory units to such networks. We evaluate our networks on their ability to generalize to new environments and show that adding memory to such networks offers huge jumps in performance

cs.RO↗

arXiv2017

Pose-Aware Person Recognition

Person recognition methods that use multiple body regions have shown significant improvements over traditional face-based recognition. One of the primary challenges in full-body person recognition is the extreme variation in pose and view point. In this work, (i) we present an approach that tackles pose variations utilizing multiple models that are trained on specific poses, and combined using pose-aware weights during testing. (ii) For learning a person representation, we propose a network that jointly optimizes a single loss over multiple body regions. (iii) Finally, we introduce new benchmarks to evaluate person recognition in diverse scenarios and show significant improvements over previously proposed approaches on all the benchmarks including the photo album setting of PIPA.

cs.CV↗

arXiv2017

Neural Network Memory Architectures for Autonomous Robot Navigation

This paper highlights the significance of including memory structures in neural networks when the latter are used to learn perception-action loops for autonomous robot navigation. Traditional navigation approaches rely on global maps of the environment to overcome cul-de-sacs and plan feasible motions. Yet, maintaining an accurate global map may be challenging in real-world settings. A possible way to mitigate this limitation is to use learning techniques that forgo hand-engineered map representations and infer appropriate control responses directly from sensed information. An important but unexplored aspect of such approaches is the effect of memory on their performance. This work is a first thorough study of memory structures for deep-neural-network-based robot navigation, and offers novel tools to train such networks from supervision and quantify their ability to generalize to unseen scenarios. We analyze the separation and generalization abilities of feedforward, long short-term memory, and differentiable neural computer networks. We introduce a new method to evaluate the generalization ability by estimating the VC-dimension of networks with a final linear readout layer. We validate that the VC estimates are good predictors of actual test performance. The reported method can be applied to deep learning problems beyond robotics.

cs.RO↗

arXiv2017

Scattering of Poincare beams: polarization speckles

Polarization speckle is a fine granular light pattern having spatially varying random polarization profile. We generate these speckle patterns by using the scattering of Poincaré beams, a special class of vector vortex beams, through a ground glass plate. Here, the Poincaré beams are generated using a polarization sensitive spatial light modulator displaying an on-axis hologram corresponding to an optical vortex phase profile. The different inhomogeneities of the rough surface experience different polarizations, which control the ability for scattered waves to interfere at the detection plane and causes a spatially varying polarization profile. We experimentally determined the spatial variation of local degree of polarization and orientation of the polarization ellipse for these speckle patterns from the Stokes analysis. We also determined the size of scalar speckles using the auto-correlation function of Stokes parameter S0 and the size of polarization speckles using the sum of auto-correlation functions of remaining three Stokes parameters. We found that the scalar speckle size is independent of index of the vector beam but the size of polarization speckles decreases with the increase in index of the vector beam.

physics.optics↗

arXiv2017

Privacy-Preserving Vehicle Assignment for Mobility-on-Demand Systems

Urban transportation is being transformed by mobility-on-demand (MoD) systems. One of the goals of MoD systems is to provide personalized transportation services to passengers. This process is facilitated by a centralized operator that coordinates the assignment of vehicles to individual passengers, based on location data. However, current approaches assume that accurate positioning information for passengers and vehicles is readily available. This assumption raises privacy concerns. In this work, we address this issue by proposing a method that protects passengers' drop-off locations (i.e., their travel destinations). Formally, we solve a batch assignment problem that routes vehicles at obfuscated origin locations to passenger locations (since origin locations correspond to previous drop-off locations), such that the mean waiting time is minimized. Our main contributions are two-fold. First, we formalize the notion of privacy for continuous vehicle-to-passenger assignment in MoD systems, and integrate a privacy mechanism that provides formal guarantees. Second, we present a scalable algorithm that takes advantage of superfluous (idle) vehicles in the system, combining multiple iterations of the Hungarian algorithm to allocate a redundant number of vehicles to a single passenger. As a result, we are able to reduce the performance deterioration induced by the privacy mechanism. We evaluate our methods on a real, large-scale data set consisting of over 11 million taxi rides (specifying vehicle availability and passenger requests), recorded over a month's duration, in the area of Manhattan, New York. Our work demonstrates that privacy can be integrated into MoD systems without incurring a significant loss of performance, and moreover, that this loss can be further minimized at the cost of deploying additional (redundant) vehicles into the fleet.

cs.CR↗