Wolfram Burgard

Wolfram Burgard
University of Freiburg | Albert-Ludwigs-Universität Freiburg · Department of Computer Science

Dr.

About

795
Publications
312,841
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
65,385
Citations
Additional affiliations
April 2002 - October 2002
Carnegie Mellon University
April 1999 - present
University of Freiburg
June 1990 - March 1999
University of Bonn
Education
November 1989 - January 1991
University of Bonn
Field of study
  • Computer Science
November 1989 - January 1991
University of Bonn
Field of study
  • Computer Science
May 1987 - October 1989
Technische Universität Dortmund
Field of study
  • Computer Science

Publications

Publications (795)
Preprint
Full-text available
Setting up robot environments to quickly test newly developed algorithms is still a difficult and time consuming process. This presents a significant hurdle to researchers interested in performing real-world robotic experiments. RobotIO is a python library designed to solve this problem. It focuses on providing common, simple, and well structured p...
Preprint
Full-text available
In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic information for improved regularization of depth and optical flow maps, multimodal fusion and occlusion filling...
Preprint
Reliable scene understanding is indispensable for modern autonomous systems. Current learning-based methods typically try to maximize their performance based on segmentation metrics that only consider the quality of the segmentation. However, for the safe operation of a system in the real world it is crucial to consider the uncertainty in the predi...
Preprint
Full-text available
A long-standing goal in robotics is to build robots that can perform a wide range of daily tasks from perceptions obtained with their onboard sensors and specified only via natural language. While recently substantial advances have been achieved in language-driven robotics by leveraging end-to-end learning from pixels, there is no clear and well-un...
Article
Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Although deep reinforcement learning algorithms have recently demonstrated impressive results in this context, they still require an impractical amount of time-consuming trial-and-error iterations. In this work, we consider t...
Preprint
Full-text available
While lifelong SLAM addresses the capability of a robot to adapt to changes within a single environment over time, in this paper we introduce the task of continual SLAM. Here, a robot is deployed sequentially in a variety of different environments and has to transfer its knowledge of previously experienced environments to thus far unseen environmen...
Preprint
Full-text available
Robots operating in human-centered environments should have the ability to understand how objects function: what can be done with each object, where this interaction may occur, and how the object is used to achieve a goal. To this end, we propose a novel approach that extracts a self-supervised visual affordance model from human teleoperated play d...
Preprint
Full-text available
Robust detection of moving vehicles is a critical task for any autonomously operating outdoor robot or self-driving vehicle. Most modern approaches for solving this task rely on training image-based detectors using large-scale vehicle detection datasets such as nuScenes or the Waymo Open Dataset. Providing manual annotations is an expensive and lab...
Preprint
Full-text available
General-purpose robots coexisting with humans in their environment must learn to relate human language to their perceptions and actions to be useful in a range of daily tasks. Moreover, they need to acquire a diverse repertoire of general-purpose skills that allow composing long-horizon tasks by following unconstrained language instructions. In thi...
Preprint
Full-text available
A core challenge for an autonomous agent acting in the real world is to adapt its repertoire of skills to cope with its noisy perception and dynamics. To scale learning of skills to long-horizon tasks, robots should be able to learn and later refine their skills in a structured manner through trajectories rather than making instantaneous decisions...
Preprint
Accurate value estimates are important for off-policy reinforcement learning. Algorithms based on temporal difference learning typically are prone to an over- or underestimation bias building up over time. In this paper, we propose a general method called Adaptively Calibrated Critics (ACC) that uses the most recent high variance but unbiased on-po...
Article
Full-text available
Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top–down approaches tackle this problem by either combining independent task-specific networks or translating methods from the image domain ignoring the intricacies of...
Preprint
Robust localization in dense urban scenarios using a low-cost sensor setup and sparse HD maps is highly relevant for the current advances in autonomous driving, but remains a challenging topic in research. We present a novel monocular localization approach based on a sliding-window pose graph that leverages predicted uncertainties for increased pre...
Preprint
Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Deep reinforcement learning algorithms have recently demonstrated impressive results, although they still require an impractical amount of time-consuming trial-and-error iterations. In this work, we consider the promising alt...
Article
Lane-level scene annotations provide invaluable data in autonomous vehicles for trajectory planning in complex environments such as urban areas and cities. However, obtaining such data is time-consuming and expensive since lane annotations have to be annotated manually by humans and are as such hard to scale to large areas. In this work, we propose...
Article
Full-text available
Dynamic illumination is a challenging problem for visual robot localization and tracking. In indoor environments, the main source of light during the day is outdoor illumination. We propose a method that estimates the appearance of an indoor scene in real-time based on a reflectance map and the current outdoor lighting. Our outdoor illumination mod...
Preprint
The transition from today's mostly human-driven traffic to a purely automated one will be a gradual evolution, with the effect that we will likely experience mixed traffic in the near future. Connected and automated vehicles can benefit human-driven ones and the whole traffic system in different ways, for example by improving collision avoidance an...
Preprint
Full-text available
Lane-level scene annotations provide invaluable data in autonomous vehicles for trajectory planning in complex environments such as urban areas and cities. However, obtaining such data is time-consuming and expensive since lane annotations have to be annotated manually by humans and are as such hard to scale to large areas. In this work, we propose...
Preprint
Full-text available
Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots. However, domain randomization and augmentation hamper the training of a policy. As reinforcement learning struggles with a noisy training signal, this additional nuisance can drastically impede training. For diffi...
Chapter
Controlling robots to perform tasks via natural language is one of the most challenging topics in human-robot interaction. In this work, we present a robot system that follows unconstrained language instructions to pick and place arbitrary objects and effectively resolves ambiguities through dialogues. Our approach infers objects and their relation...
Preprint
Full-text available
Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either combining independent task-specific networks or translating methods from the image domain ignoring the intricacies of...
Preprint
Controlling robots to perform tasks via natural language is one of the most challenging topics in human-robot interaction. In this work, we present a robot system that follows unconstrained language instructions to pick and place arbitrary objects and effectively resolves ambiguities through dialogues. Our approach infers objects and their relation...
Article
Due to their ubiquity and long-term stability, pole-like objects are well suited to serve as landmarks for vehicle localization in urban environments. In this work, we present a complete mapping and long-term localization system based on pole landmarks extracted from 3-D lidar data. Our approach features a novel pole detector, a mapping module, and...
Chapter
Individually controllable and steerable wheels provide vehicles with greater flexibility and efficiency. A key challenge in the context of such vehicles lies in the effective planning of the motion commands in order to properly deal with the potentially large required changes in the steering angles and to properly incorporate the given motion const...
Article
The transition from today's mostly human-driven traffic to a purely automated one will be a gradual evolution, with the effect that we will likely experience mixed traffic in the near future. Connected and automated vehicles can benefit human-driven ones and the whole traffic system in different ways, for example by improving collision avoidance an...
Preprint
Real-time object detection in videos using lightweight hardware is a crucial component of many robotic tasks. Detectors using different modalities and with varying computational complexities offer different trade-offs. One option is to have a very lightweight model that can predict from all modalities at once for each frame. However, in some situat...
Article
Full-text available
The growing world population calls for more efficient and sustainable farming technologies. Automating agricultural tasks has great potential to improve farming technologies. A key requirement for full automation is the ability of agricultural vehicles to accurately navigate entire fields without damaging value crops. One important precondition for...
Article
Full-text available
Mobile robots operating in unknown urban environments encounter a wide range of complex terrains to which they must adapt their planned trajectory for safe and efficient navigation. Most existing approaches utilize supervised learning to classify terrains from either an exteroceptive or a proprioceptive sensor modality. However, this requires a tre...
Article
Full-text available
For mobile robots navigating on sidewalks, the ability to safely cross street intersections is essential. Most existing approaches rely on the recognition of the traffic light signal to make an informed crossing decision. Although these approaches have been crucial enablers for urban navigation, the capabilities of robots employing such approaches...
Preprint
Full-text available
A key challenge for an agent learning to interact with the world is to reason about physical properties of objects and to foresee their dynamics under the effect of applied forces. In order to scale learning through interaction to many objects and scenes, robots should be able to improve their own performance from real-world experience without requ...
Preprint
Full-text available
Single encoder-decoder methodologies for semantic segmentation are reaching their peak in terms of segmentation quality and efficiency per number of layers. To address these limitations, we propose a new architecture based on a decoder which uses a set of shallow networks for capturing more information content. The new decoder has a new topology of...
Preprint
Imitation learning is a powerful family of techniques for learning sensorimotor coordination in immersive environments. We apply imitation learning to attain state-of-the-art performance on hard exploration problems in the Minecraft environment. We report experiments that highlight the influence of network architecture, loss function, and data augm...
Preprint
Instance segmentation of unknown objects from images is regarded as relevant for several robot skills including grasping, tracking and object sorting. Recent results in computer vision have shown that large hand-labeled datasets enable high segmentation performance. To overcome the time-consuming process of manually labeling data for new environmen...
Article
Full-text available
Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions. Leveraging complementary modalities can enable learning of semanticall...
Article
Full-text available
Brain signals represent a communication modality that can allow users of assistive robots to specify high-level goals, such as the object to fetch and deliver. In this paper, we consider a screen-free Brain-Computer Interface (BCI), where the robot highlights candidate objects in the environment using a laser pointer, and the user goal is decoded f...
Preprint
Full-text available
The majority of learning-based semantic segmentation methods are optimized for daytime scenarios and favorable lighting conditions. Real-world driving scenarios, however, entail adverse environmental conditions such as nighttime illumination or glare which remain a challenge for existing approaches. In this work, we propose a multimodal semantic se...
Preprint
Full-text available
Traffic signal controllers play an essential role in the traffic system, while the current majority of them are not sufficiently flexible or adaptive to make optimal traffic schedules. In this paper we present an approach to learn policies for the signal controllers using deep reinforcement learning. Our method uses a novel formulation of the rewar...
Article
Full-text available
Background: Classic motion abnormalities in Parkinson's disease (PD), such as tremor, bradykinesia, or rigidity, are well-covered by standard clinical assessments such as the Unified Parkinson's Disease Rating Scale (UPDRS). However, PD includes motor abnormalities beyond the symptoms and signs as measured by UPDRS, such as the lack of anticipatory...
Preprint
Robots coexisting with humans in their environment and performing services for them need the ability to interact with them. One particular requirement for such robots is that they are able to understand spatial relations and can place objects in accordance with the spatial relations expressed by their user. In this work, we present a convolutional...
Chapter
Navigating autonomously underwater, where a priori information on the environment is sparse and changing ambient conditions complicate perception, requires robust sensing capabilities as well as advanced signal processing strategies. Multimodality in sensing as well as data processing is considered as an approach to strengthen the robustness of dec...
Chapter
This position paper presents initial thoughts on how some techniques from general robotics can help for autonomous underwater vehicle (AUV) navigation in confined spaces by exploiting in particular the spatial borders and considering information that is not available in open waters. There are natural confined spaces, e.g. caves, as well as artifici...
Chapter
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 however their accuracy and reliability is typically inferior to LiDAR-based methods. In this work, we propose a vision-based localization approach that learns...
Chapter
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 rob...
Chapter
Full-text available
In the last decade, deep learning has revolutionized various components of the conventional robot autonomy stack including aspects of perception, navigation and manipulation. There have been numerous advances in perfecting individual tasks such as scene understanding, visual localization, end-to-end navigation and grasping, which has given us a cri...
Preprint
Full-text available
Mobile robots operating in unknown urban environments encounter a wide range of complex terrains to which they must adapt their planned trajectory for safe and efficient navigation. Most existing approaches utilize supervised learning to classify terrains from either an exteroceptive or a proprioceptive sensor modality. However, this requires a tre...
Preprint
Full-text available
The application of autonomous robots in agriculture is gaining more and more popularity thanks to the high impact it may have on food security, sustainability, resource use efficiency, reduction of chemical treatments, minimization of the human effort and maximization of yield. The Flourish research project faced this challenge by developing an ada...