arXiv subjects

Wolfram Burgard

Publications and source records attributed to Wolfram Burgard.

At least 163 records · Page 9Linked to original sources

arXiv2018

Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning

This paper investigates exploration strategies of Deep Reinforcement Learning (DRL) methods to learn navigation policies for mobile robots. In particular, we augment the normal external reward for training DRL algorithms with intrinsic reward signals measured by curiosity. We test our approach in a mapless navigation setting, where the autonomous agent is required to navigate without the occupancy map of the environment, to targets whose relative locations can be easily acquired through low-cost solutions (e.g., visible light localization, Wi-Fi signal localization). We validate that the intrinsic motivation is crucial for improving DRL performance in tasks with challenging exploration requirements. Our experimental results show that our proposed method is able to more effectively learn navigation policies, and has better generalization capabilities in previously unseen environments. A video of our experimental results can be found at https://goo.gl/pWbpcF.

cs.RO↗

arXiv2018

The Limits and Potentials of Deep Learning for Robotics

The application of deep learning in robotics leads to very specific problems and research questions that are typically not addressed by the computer vision and machine learning communities. In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning. We explain the need for better evaluation metrics, highlight the importance and unique challenges for deep robotic learning in simulation, and explore the spectrum between purely data-driven and model-driven approaches. We hope this paper provides a motivating overview of important research directions to overcome the current limitations, and help fulfill the promising potentials of deep learning in robotics.

cs.RO↗

arXiv2018

A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation

Deep learning techniques have been widely applied, achieving state-of-the-art results in various fields of study. This survey focuses on deep learning solutions that target learning control policies for robotics applications. We carry out our discussions on the two main paradigms for learning control with deep networks: deep reinforcement learning and imitation learning. For deep reinforcement learning (DRL), we begin from traditional reinforcement learning algorithms, showing how they are extended to the deep context and effective mechanisms that could be added on top of the DRL algorithms. We then introduce representative works that utilize DRL to solve navigation and manipulation tasks in robotics. We continue our discussion on methods addressing the challenge of the reality gap for transferring DRL policies trained in simulation to real-world scenarios, and summarize robotics simulation platforms for conducting DRL research. For imitation leaning, we go through its three main categories, behavior cloning, inverse reinforcement learning and generative adversarial imitation learning, by introducing their formulations and their corresponding robotics applications. Finally, we discuss the open challenges and research frontiers.

cs.RO↗

arXiv2018

Deep Spatiotemporal Models for Robust Proprioceptive Terrain Classification

Terrain classification is a critical component of any autonomous mobile robot system operating in unknown real-world environments. Over the years, several proprioceptive terrain classification techniques have been introduced to increase robustness or act as a fallback for traditional vision based approaches. However, they lack widespread adaptation due to various factors that include inadequate accuracy, robustness and slow run-times. In this paper, we use vehicle-terrain interaction sounds as a proprioceptive modality and propose a deep Long-Short Term Memory (LSTM) based recurrent model that captures both the spatial and temporal dynamics of such a problem, thereby overcoming these past limitations. Our model consists of a new Convolution Neural Network (CNN) architecture that learns deep spatial features, complemented with LSTM units that learn complex temporal dynamics. Experiments on two extensive datasets collected with different microphones on various indoor and outdoor terrains demonstrate state-of-the-art performance compared to existing techniques. We additionally evaluate the performance in adverse acoustic conditions with high ambient noise and propose a noise-aware training scheme that enables learning of more generalizable models that are essential for robust real-world deployments.

cs.RO↗

arXiv2018

3D Human Pose Estimation in RGBD Images for Robotic Task Learning

We propose an approach to estimate 3D human pose in real world units from a single RGBD image and show that it exceeds performance of monocular 3D pose estimation approaches from color as well as pose estimation exclusively from depth. Our approach builds on robust human keypoint detectors for color images and incorporates depth for lifting into 3D. We combine the system with our learning from demonstration framework to instruct a service robot without the need of markers. Experiments in real world settings demonstrate that our approach enables a PR2 robot to imitate manipulation actions observed from a human teacher.

cs.CV↗

arXiv2018

Deep Auxiliary Learning for Visual Localization and Odometry

Localization is an indispensable component of a robot's autonomy stack that enables it to determine where it is in the environment, essentially making it a precursor for any action execution or planning. Although convolutional neural networks have shown promising results for visual localization, they are still grossly outperformed by state-of-the-art local feature-based techniques. In this work, we propose VLocNet, a new convolutional neural network architecture for 6-DoF global pose regression and odometry estimation from consecutive monocular images. Our multitask model incorporates hard parameter sharing, thus being compact and enabling real-time inference, in addition to being end-to-end trainable. We propose a novel loss function that utilizes auxiliary learning to leverage relative pose information during training, thereby constraining the search space to obtain consistent pose estimates. We evaluate our proposed VLocNet on indoor as well as outdoor datasets and show that even our single task model exceeds the performance of state-of-the-art deep architectures for global localization, while achieving competitive performance for visual odometry estimation. Furthermore, we present extensive experimental evaluations utilizing our proposed Geometric Consistency Loss that show the effectiveness of multitask learning and demonstrate that our model is the first deep learning technique to be on par with, and in some cases outperforms state-of-the-art SIFT-based approaches.

cs.RO↗

arXiv2018

Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning

We present an approach for mobile robots to learn to navigate in dynamic environments with pedestrians via raw depth inputs, in a socially compliant manner. To achieve this, we adopt a generative adversarial imitation learning (GAIL) strategy, which improves upon a pre-trained behavior cloning policy. Our approach overcomes the disadvantages of previous methods, as they heavily depend on the full knowledge of the location and velocity information of nearby pedestrians, which not only requires specific sensors, but also the extraction of such state information from raw sensory input could consume much computation time. In this paper, our proposed GAIL-based model performs directly on raw depth inputs and plans in real-time. Experiments show that our GAIL-based approach greatly improves the safety and efficiency of the behavior of mobile robots from pure behavior cloning. The real-world deployment also shows that our method is capable of guiding autonomous vehicles to navigate in a socially compliant manner directly through raw depth inputs. In addition, we release a simulation plugin for modeling pedestrian behaviors based on the social force model.

cs.RO↗

arXiv2018

Learning to Singulate Objects using a Push Proposal Network

Learning to act in unstructured environments, such as cluttered piles of objects, poses a substantial challenge for manipulation robots. We present a novel neural network-based approach that separates unknown objects in clutter by selecting favourable push actions. Our network is trained from data collected through autonomous interaction of a PR2 robot with randomly organized tabletop scenes. The model is designed to propose meaningful push actions based on over-segmented RGB-D images. We evaluate our approach by singulating up to 8 unknown objects in clutter. We demonstrate that our method enables the robot to perform the task with a high success rate and a low number of required push actions. Our results based on real-world experiments show that our network is able to generalize to novel objects of various sizes and shapes, as well as to arbitrary object configurations. Videos of our experiments can be viewed at http://robotpush.cs.uni-freiburg.de

cs.RO↗

arXiv2018

Deep Transfer Learning for Error Decoding from Non-Invasive EEG

We recorded high-density EEG in a flanker task experiment (31 subjects) and an online BCI control paradigm (4 subjects). On these datasets, we evaluated the use of transfer learning for error decoding with deep convolutional neural networks (deep ConvNets). In comparison with a regularized linear discriminant analysis (rLDA) classifier, ConvNets were significantly better in both intra- and inter-subject decoding, achieving an average accuracy of 84.1 % within subject and 81.7 % on unknown subjects (flanker task). Neither method was, however, able to generalize reliably between paradigms. Visualization of features the ConvNets learned from the data showed plausible patterns of brain activity, revealing both similarities and differences between the different kinds of errors. Our findings indicate that deep learning techniques are useful to infer information about the correctness of action in BCI applications, particularly for the transfer of pre-trained classifiers to new recording sessions or subjects.

cs.LG↗

arXiv2017

The signature of robot action success in EEG signals of a human observer: Decoding and visualization using deep convolutional neural networks

The importance of robotic assistive devices grows in our work and everyday life. Cooperative scenarios involving both robots and humans require safe human-robot interaction. One important aspect here is the management of robot errors, including fast and accurate online robot-error detection and correction. Analysis of brain signals from a human interacting with a robot may help identifying robot errors, but accuracies of such analyses have still substantial space for improvement. In this paper we evaluate whether a novel framework based on deep convolutional neural networks (deep ConvNets) could improve the accuracy of decoding robot errors from the EEG of a human observer, both during an object grasping and a pouring task. We show that deep ConvNets reached significantly higher accuracies than both regularized Linear Discriminant Analysis (rLDA) and filter bank common spatial patterns (FB-CSP) combined with rLDA, both widely used EEG classifiers. Deep ConvNets reached mean accuracies of 75% +/- 9 %, rLDA 65% +/- 10% and FB-CSP + rLDA 63% +/- 6% for decoding of erroneous vs. correct trials. Visualization of the time-domain EEG features learned by the ConvNets to decode errors revealed spatiotemporal patterns that reflected differences between the two experimental paradigms. Across subjects, ConvNet decoding accuracies were significantly correlated with those obtained with rLDA, but not CSP, indicating that in the present context ConvNets behaved more 'rLDA-like' (but consistently better), while in a previous decoding study with another task but the same ConvNet architecture, it was found to behave more 'CSP-like'. Our findings thus provide further support for the assumption that deep ConvNets are a versatile addition to the existing toolbox of EEG decoding techniques, and we discuss steps how ConvNet EEG decoding performance could be further optimized.

cs.HC↗

arXiv2017

Why did the Robot Cross the Road? - Learning from Multi-Modal Sensor Data for Autonomous Road Crossing

We consider the problem of developing robots that navigate like pedestrians on sidewalks through city centers for performing various tasks including delivery and surveillance. One particular challenge for such robots is crossing streets without pedestrian traffic lights. To solve this task the robot has to decide based on its sensory input if the road is clear. In this work, we propose a novel multi-modal learning approach for the problem of autonomous street crossing. Our approach solely relies on laser and radar data and learns a classifier based on Random Forests to predict when it is safe to cross the road. We present extensive experimental evaluations using real-world data collected from multiple street crossing situations which demonstrate that our approach yields a safe and accurate street crossing behavior and generalizes well over different types of situations. A comparison to alternative methods demonstrates the advantages of our approach.

cs.RO↗

arXiv2017

From Plants to Landmarks: Time-invariant Plant Localization that uses Deep Pose Regression in Agricultural Fields

Agricultural robots are expected to increase yields in a sustainable way and automate precision tasks, such as weeding and plant monitoring. At the same time, they move in a continuously changing, semi-structured field environment, in which features can hardly be found and reproduced at a later time. Challenges for Lidar and visual detection systems stem from the fact that plants can be very small, overlapping and have a steadily changing appearance. Therefore, a popular way to localize vehicles with high accuracy is based on ex- pensive global navigation satellite systems and not on natural landmarks. The contribution of this work is a novel image- based plant localization technique that uses the time-invariant stem emerging point as a reference. Our approach is based on a fully convolutional neural network that learns landmark localization from RGB and NIR image input in an end-to-end manner. The network performs pose regression to generate a plant location likelihood map. Our approach allows us to cope with visual variances of plants both for different species and different growth stages. We achieve high localization accuracies as shown in detailed evaluations of a sugar beet cultivation phase. In experiments with our BoniRob we demonstrate that detections can be robustly reproduced with centimeter accuracy.

cs.RO↗

arXiv2017

Brain Responses During Robot-Error Observation

Brain-controlled robots are a promising new type of assistive device for severely impaired persons. Little is however known about how to optimize the interaction of humans and brain-controlled robots. Information about the human's perceived correctness of robot performance might provide a useful teaching signal for adaptive control algorithms and thus help enhancing robot control. Here, we studied whether watching robots perform erroneous vs. correct action elicits differential brain responses that can be decoded from single trials of electroencephalographic (EEG) recordings, and whether brain activity during human-robot interaction is modulated by the robot's visual similarity to a human. To address these topics, we designed two experiments. In experiment I, participants watched a robot arm pour liquid into a cup. The robot performed the action either erroneously or correctly, i.e. it either spilled some liquid or not. In experiment II, participants observed two different types of robots, humanoid and non-humanoid, grabbing a ball. The robots either managed to grab the ball or not. We recorded high-resolution EEG during the observation tasks in both experiments to train a Filter Bank Common Spatial Pattern (FBCSP) pipeline on the multivariate EEG signal and decode for the correctness of the observed action, and for the type of the observed robot. Our findings show that it was possible to decode both correctness and robot type for the majority of participants significantly, although often just slightly, above chance level. Our findings suggest that non-invasive recordings of brain responses elicited when observing robots indeed contain decodable information about the correctness of the robot's action and the type of observed robot.

cs.HC↗

arXiv2017

Deep Detection of People and their Mobility Aids for a Hospital Robot

Robots operating in populated environments encounter many different types of people, some of whom might have an advanced need for cautious interaction, because of physical impairments or their advanced age. Robots therefore need to recognize such advanced demands to provide appropriate assistance, guidance or other forms of support. In this paper, we propose a depth-based perception pipeline that estimates the position and velocity of people in the environment and categorizes them according to the mobility aids they use: pedestrian, person in wheelchair, person in a wheelchair with a person pushing them, person with crutches and person using a walker. We present a fast region proposal method that feeds a Region-based Convolutional Network (Fast R-CNN). With this, we speed up the object detection process by a factor of seven compared to a dense sliding window approach. We furthermore propose a probabilistic position, velocity and class estimator to smooth the CNN's detections and account for occlusions and misclassifications. In addition, we introduce a new hospital dataset with over 17,000 annotated RGB-D images. Extensive experiments confirm that our pipeline successfully keeps track of people and their mobility aids, even in challenging situations with multiple people from different categories and frequent occlusions. Videos of our experiments and the dataset are available at http://www2.informatik.uni-freiburg.de/~kollmitz/MobilityAids

cs.RO↗

arXiv2017

Metric Learning for Generalizing Spatial Relations to New Objects

Human-centered environments are rich with a wide variety of spatial relations between everyday objects. For autonomous robots to operate effectively in such environments, they should be able to reason about these relations and generalize them to objects with different shapes and sizes. For example, having learned to place a toy inside a basket, a robot should be able to generalize this concept using a spoon and a cup. This requires a robot to have the flexibility to learn arbitrary relations in a lifelong manner, making it challenging for an expert to pre-program it with sufficient knowledge to do so beforehand. In this paper, we address the problem of learning spatial relations by introducing a novel method from the perspective of distance metric learning. Our approach enables a robot to reason about the similarity between pairwise spatial relations, thereby enabling it to use its previous knowledge when presented with a new relation to imitate. We show how this makes it possible to learn arbitrary spatial relations from non-expert users using a small number of examples and in an interactive manner. Our extensive evaluation with real-world data demonstrates the effectiveness of our method in reasoning about a continuous spectrum of spatial relations and generalizing them to new objects.

cs.RO↗

arXiv2017

Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

In this paper we consider the problem of robot navigation in simple maze-like environments where the robot has to rely on its onboard sensors to perform the navigation task. In particular, we are interested in solutions to this problem that do not require localization, mapping or planning. Additionally, we require that our solution can quickly adapt to new situations (e.g., changing navigation goals and environments). To meet these criteria we frame this problem as a sequence of related reinforcement learning tasks. We propose a successor feature based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances. Our algorithm substantially decreases the required learning time after the first task instance has been solved, which makes it easily adaptable to changing environments. We validate our method in both simulated and real robot experiments with a Robotino and compare it to a set of baseline methods including classical planning-based navigation.

cs.RO↗

arXiv2017

Topometric Localization with Deep Learning

Compared to LiDAR-based localization methods, which provide high accuracy but rely on expensive sensors, visual localization approaches only require a camera and thus are more cost-effective while their accuracy and reliability typically is inferior to LiDAR-based methods. In this work, we propose a vision-based localization approach that learns from LiDAR-based localization methods by using their output as training data, thus combining a cheap, passive sensor with an accuracy that is on-par with LiDAR-based localization. The approach consists of two deep networks trained on visual odometry and topological localization, respectively, and a successive optimization to combine the predictions of these two networks. We evaluate the approach on a new challenging pedestrian-based dataset captured over the course of six months in varying weather conditions with a high degree of noise. The experiments demonstrate that the localization errors are up to 10 times smaller than with traditional vision-based localization methods.

cs.CV↗

arXiv2017

Deep Semantic Classification for 3D LiDAR Data

Robots are expected to operate autonomously in dynamic environments. Understanding the underlying dynamic characteristics of objects is a key enabler for achieving this goal. In this paper, we propose a method for pointwise semantic classification of 3D LiDAR data into three classes: non-movable, movable and dynamic. We concentrate on understanding these specific semantics because they characterize important information required for an autonomous system. Non-movable points in the scene belong to unchanging segments of the environment, whereas the remaining classes corresponds to the changing parts of the scene. The difference between the movable and dynamic class is their motion state. The dynamic points can be perceived as moving, whereas movable objects can move, but are perceived as static. To learn the distinction between movable and non-movable points in the environment, we introduce an approach based on deep neural network and for detecting the dynamic points, we estimate pointwise motion. We propose a Bayes filter framework for combining the learned semantic cues with the motion cues to infer the required semantic classification. In extensive experiments, we compare our approach with other methods on a standard benchmark dataset and report competitive results in comparison to the existing state-of-the-art. Furthermore, we show an improvement in the classification of points by combining the semantic cues retrieved from the neural network with the motion cues.

cs.RO↗