arXiv subjects

Gregory Dudek

Publications and source records attributed to Gregory Dudek.

72 records · Page 4Linked to original sources

arXiv2020

One-Shot Informed Robotic Visual Search in the Wild

We consider the task of underwater robot navigation for the purpose of collecting scientifically relevant video data for environmental monitoring. The majority of field robots that currently perform monitoring tasks in unstructured natural environments navigate via path-tracking a pre-specified sequence of waypoints. Although this navigation method is often necessary, it is limiting because the robot does not have a model of what the scientist deems to be relevant visual observations. Thus, the robot can neither visually search for particular types of objects, nor focus its attention on parts of the scene that might be more relevant than the pre-specified waypoints and viewpoints. In this paper we propose a method that enables informed visual navigation via a learned visual similarity operator that guides the robot's visual search towards parts of the scene that look like an exemplar image, which is given by the user as a high-level specification for data collection. We propose and evaluate a weakly supervised video representation learning method that outperforms ImageNet embeddings for similarity tasks in the underwater domain. We also demonstrate the deployment of this similarity operator during informed visual navigation in collaborative environmental monitoring scenarios, in large-scale field trials, where the robot and a human scientist collaboratively search for relevant visual content.

cs.RO↗

arXiv2020

Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided by a user without any prior map, all while avoiding obstacles and choosing paths that cover user-informed regions of interest. Our approach is based on recent advances in conditional imitation learning. General-purpose, safe and informative actions are demonstrated by a human expert. The learned policy is subsequently extended to be goal-conditioned by training with hindsight relabelling, guided by the robot's relative localization system, which requires no additional manual annotation. We deployed our method on an underwater vehicle in the open ocean to collect scientifically relevant data of coral reefs, which allowed our robot to operate safely and autonomously, even at very close proximity to the coral. Our field deployments have demonstrated over a kilometer of autonomous visual navigation, where the robot reaches on the order of 40 waypoints, while collecting scientifically relevant data. This is done while travelling within 0.5 m altitude from sensitive corals and exhibiting significant learned agility to overcome turbulent ocean conditions and to actively avoid collisions.

cs.RO↗

arXiv2020

Learning to Drive Off Road on Smooth Terrain in Unstructured Environments Using an On-Board Camera and Sparse Aerial Images

We present a method for learning to drive on smooth terrain while simultaneously avoiding collisions in challenging off-road and unstructured outdoor environments using only visual inputs. Our approach applies a hybrid model-based and model-free reinforcement learning method that is entirely self-supervised in labeling terrain roughness and collisions using on-board sensors. Notably, we provide both first-person and overhead aerial image inputs to our model. We find that the fusion of these complementary inputs improves planning foresight and makes the model robust to visual obstructions. Our results show the ability to generalize to environments with plentiful vegetation, various types of rock, and sandy trails. During evaluation, our policy attained 90% smooth terrain traversal and reduced the proportion of rough terrain driven over by 6.1 times compared to a model using only first-person imagery.

cs.RO↗

arXiv2019

Detecting GAN generated errors

Despite an impressive performance from the latest GAN for generating hyper-realistic images, GAN discriminators have difficulty evaluating the quality of an individual generated sample. This is because the task of evaluating the quality of a generated image differs from deciding if an image is real or fake. A generated image could be perfect except in a single area but still be detected as fake. Instead, we propose a novel approach for detecting where errors occur within a generated image. By collaging real images with generated images, we compute for each pixel, whether it belongs to the real distribution or generated distribution. Furthermore, we leverage attention to model long-range dependency; this allows detection of errors which are reasonable locally but not holistically. For evaluation, we show that our error detection can act as a quality metric for an individual image, unlike FID and IS. We leverage Improved Wasserstein, BigGAN, and StyleGAN to show a ranking based on our metric correlates impressively with FID scores. Our work opens the door for better understanding of GAN and the ability to select the best samples from a GAN model.

eess.IV↗

arXiv2019

Learning Domain Randomization Distributions for Training Robust Locomotion Policies

Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of success stories typically use real world data in order to carefully select the DR distribution, or incorporate real world trajectories to better estimate appropriate randomization distributions. In this paper, we consider the problem of finding good domain randomization parameters for simulation, without prior access to data from the target system. We explore the use of gradient-based search methods to learn a domain randomization with the following properties: 1) The trained policy should be successful in environments sampled from the domain randomization distribution 2) The domain randomization distribution should be wide enough so that the experience similar to the target robot system is observed during training, while addressing the practicality of training finite capacity models. These two properties aim to ensure the trajectories encountered in the target system are close to those observed during training, as existing methods in machine learning are better suited for interpolation than extrapolation. We show how adapting the domain randomization distribution while training context-conditioned policies results in improvements on jump-start and asymptotic performance when transferring a learned policy to the target environment.

cs.LG↗

arXiv2019

Heterogeneous Robot Teams for Informative Sampling

In this paper we present a cooperative multi-robot strategy to adaptively explore and sample environments that are unfavorable for humans. We propose a methodology for a team of heterogeneous robots to collaborate on information based planning for applications like sampling thermal imagery in a wildfire affected site to assist with detecting spot fires and areas of residual fires, fire mapping and monitoring fire progression or applications in marine domain for coral reef monitoring and survey. We use Gabor filter based texture classifier on aerial images from an Unmanned Aerial Vehicle (UAV) to segment the region of interest into classes. A policy gradient based path planner is used on the texture classified aerial image to plan a path for the Unmanned Ground Vehicle (UGV). The UGV then uses a local planner to reach the goals set by the global planner by avoiding obstacles. The UGV also learns the labels for the segmented classes as drivable and non-drivable using the feedback from the performance while reaching the planned waypoints. We evaluated the building blocks of our approach and present the results with application of these strategies to different domains.

cs.RO↗

arXiv2019

Reinforcement Learning with Non-uniform State Representations for Adaptive Search

Efficient spatial exploration is a key aspect of search and rescue. In this paper, we present a search algorithm that generates efficient trajectories that optimize the rate at which probability mass is covered by a searcher. This should allow an autonomous vehicle find one or more lost targets as rapidly as possible. We do this by performing non-uniform sampling of the search region. The path generated minimizes the expected time to locate the missing target by visiting high probability regions using non-myopic path generation based on reinforcement learning. We model the target probability distribution using a classic mixture of Gaussians model with means and mixture coefficients tuned according to the location and time of sightings of the lost target. Key features of our search algorithm are the ability to employ a very general non-deterministic action model and the ability to generate action plans for any new probability distribution using the parameters learned on other similar looking distributions. One of the key contributions of this paper is the use of non-uniform state aggregation for policy search in the context of robotics.

cs.RO↗

arXiv2018

Planning in Dynamic Environments with Conditional Autoregressive Models

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obstacles. The combination of high-quality frame generation and classical planning approaches nearly matches true environment performance for our task, demonstrating the usefulness of this method for model-based planning in dynamic environments.

cs.LG↗

arXiv2018

Autonomous Marine Sampling Enhanced by Strategically Deployed Drifters in Marine Flow Fields

We present a transportable system for ocean observations in which a small autonomous surface vehicle (ASV) adaptively collects spatially diverse samples with aid from a team of inexpensive, passive floating sensors known as drifters. Drifters can provide an increase in spatial coverage at little cost as they are propelled about the survey area by the ambient flow field instead of with actuators. Our iterative planning approach demonstrates how we can use the ASV to strategically deploy drifters into points of the flow field for high expected information gain, while also adaptively sampling the space. In this paper, we examine the performance of this heterogeneous sensing system in simulated flow field experiments.

cs.RO↗

arXiv2018

Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning

We present an algorithm for rapidly learning controllers for robotics systems. The algorithm follows the model-based reinforcement learning paradigm, and improves upon existing algorithms; namely Probabilistic learning in Control (PILCO) and a sample-based version of PILCO with neural network dynamics (Deep-PILCO). We propose training a neural network dynamics model using variational dropout with truncated Log-Normal noise. This allows us to obtain a dynamics model with calibrated uncertainty, which can be used to simulate controller executions via rollouts. We also describe set of techniques, inspired by viewing PILCO as a recurrent neural network model, that are crucial to improve the convergence of the method. We test our method on a variety of benchmark tasks, demonstrating data-efficiency that is competitive with PILCO, while being able to optimize complex neural network controllers. Finally, we assess the performance of the algorithm for learning motor controllers for a six legged autonomous underwater vehicle. This demonstrates the potential of the algorithm for scaling up the dimensionality and dataset sizes, in more complex control tasks.

cs.RO↗

arXiv2018

Scale-Robust Localization Using General Object Landmarks

Visual localization under large changes in scale is an important capability in many robotic mapping applications, such as localizing at low altitudes in maps built at high altitudes, or performing loop closure over long distances. Existing approaches, however, are robust only up to about a 3x difference in scale between map and query images. We propose a novel combination of deep-learning-based object features and state-of-the-art SIFT point-features that yields improved robustness to scale change. This technique is training-free and class-agnostic, and in principle can be deployed in any environment out-of-the-box. We evaluate the proposed technique on the KITTI Odometry benchmark and on a novel dataset of outdoor images exhibiting changes in visual scale of $7\times$ and greater, which we have released to the public. Our technique consistently outperforms localization using either SIFT features or the proposed object features alone, achieving both greater accuracy and much lower failure rates under large changes in scale.

cs.RO↗

arXiv2017

Learning Seasonal Phytoplankton Communities with Topic Models

In this work we develop and demonstrate a probabilistic generative model for phytoplankton communities. The proposed model takes counts of a set of phytoplankton taxa in a timeseries as its training data, and models communities by learning sparse co-occurrence structure between the taxa. Our model is probabilistic, where communities are represented by probability distributions over the species, and each time-step is represented by a probability distribution over the communities. The proposed approach uses a non-parametric, spatiotemporal topic model to encourage the communities to form an interpretable representation of the data, without making strong assumptions about the communities. We demonstrate the quality and interpretability of our method by its ability to improve performance of a simplistic regression model. We show that simple linear regression is sufficient to predict the community distribution learned by our method, and therefore the taxon distributions, from a set of naively chosen environment variables. In contrast, a similar regression model is insufficient to predict the taxon distributions directly or through PCA with the same level of accuracy.

stat.AP↗

arXiv2017

Underwater Multi-Robot Convoying using Visual Tracking by Detection

We present a robust multi-robot convoying approach that relies on visual detection of the leading agent, thus enabling target following in unstructured 3-D environments. Our method is based on the idea of tracking-by-detection, which interleaves efficient model-based object detection with temporal filtering of image-based bounding box estimation. This approach has the important advantage of mitigating tracking drift (i.e. drifting away from the target object), which is a common symptom of model-free trackers and is detrimental to sustained convoying in practice. To illustrate our solution, we collected extensive footage of an underwater robot in ocean settings, and hand-annotated its location in each frame. Based on this dataset, we present an empirical comparison of multiple tracker variants, including the use of several convolutional neural networks, both with and without recurrent connections, as well as frequency-based model-free trackers. We also demonstrate the practicality of this tracking-by-detection strategy in real-world scenarios by successfully controlling a legged underwater robot in five degrees of freedom to follow another robot's independent motion.

cs.RO↗

arXiv2017

Benchmark Environments for Multitask Learning in Continuous Domains

As demand drives systems to generalize to various domains and problems, the study of multitask, transfer and lifelong learning has become an increasingly important pursuit. In discrete domains, performance on the Atari game suite has emerged as the de facto benchmark for assessing multitask learning. However, in continuous domains there is a lack of agreement on standard multitask evaluation environments which makes it difficult to compare different approaches fairly. In this work, we describe a benchmark set of tasks that we have developed in an extendable framework based on OpenAI Gym. We run a simple baseline using Trust Region Policy Optimization and release the framework publicly to be expanded and used for the systematic comparison of multitask, transfer, and lifelong learning in continuous domains.

cs.AI↗

arXiv2017

Phytoplankton Hotspot Prediction With an Unsupervised Spatial Community Model

Many interesting natural phenomena are sparsely distributed and discrete. Locating the hotspots of such sparsely distributed phenomena is often difficult because their density gradient is likely to be very noisy. We present a novel approach to this search problem, where we model the co-occurrence relations between a robot's observations with a Bayesian nonparametric topic model. This approach makes it possible to produce a robust estimate of the spatial distribution of the target, even in the absence of direct target observations. We apply the proposed approach to the problem of finding the spatial locations of the hotspots of a specific phytoplankton taxon in the ocean. We use classified image data from Imaging FlowCytobot (IFCB), which automatically measures individual microscopic cells and colonies of cells. Given these individual taxon-specific observations, we learn a phytoplankton community model that characterizes the co-occurrence relations between taxa. We present experiments with simulated robot missions drawn from real observation data collected during a research cruise traversing the US Atlantic coast. Our results show that the proposed approach outperforms nearest neighbor and k-means based methods for predicting the spatial distribution of hotspots from in-situ observations.

cs.RO↗

arXiv2015

Modeling Curiosity in a Mobile Robot for Long-Term Autonomous Exploration and Monitoring

This paper presents a novel approach to modeling curiosity in a mobile robot, which is useful for monitoring and adaptive data collection tasks, especially in the context of long term autonomous missions where pre-programmed missions are likely to have limited utility. We use a realtime topic modeling technique to build a semantic perception model of the environment, using which, we plan a path through the locations in the world with high semantic information content. The life-long learning behavior of the proposed perception model makes it suitable for long-term exploration missions. We validate the approach using simulated exploration experiments using aerial and underwater data, and demonstrate an implementation on the Aqua underwater robot in a variety of scenarios. We find that the proposed exploration paths that are biased towards locations with high topic perplexity, produce better terrain models with high discriminative power. Moreover, we show that the proposed algorithm implemented on Aqua robot is able to do tasks such as coral reef inspection, diver following, and sea floor exploration, without any prior training or preparation.

cs.RO↗

arXiv2015

Gibbs Sampling Strategies for Semantic Perception of Streaming Video Data

Topic modeling of streaming sensor data can be used for high level perception of the environment by a mobile robot. In this paper we compare various Gibbs sampling strategies for topic modeling of streaming spatiotemporal data, such as video captured by a mobile robot. Compared to previous work on online topic modeling, such as o-LDA and incremental LDA, we show that the proposed technique results in lower online and final perplexity, given the realtime constraints.

cs.RO↗

arXiv2013

Curiosity Based Exploration for Learning Terrain Models

We present a robotic exploration technique in which the goal is to learn to a visual model and be able to distinguish between different terrains and other visual components in an unknown environment. We use ROST, a realtime online spatiotemporal topic modeling framework to model these terrains using the observations made by the robot, and then use an information theoretic path planning technique to define the exploration path. We conduct experiments with aerial view and underwater datasets with millions of observations and varying path lengths, and find that paths that are biased towards locations with high topic perplexity produce better terrain models with high discriminative power, especially with paths of length close to the diameter of the world.

cs.RO↗