J. Marius Zöllner

J. Marius Zöllner
Karlsruhe Institute of Technology | KIT · Institute of Applied Informatics and Formal Description Methods

Prof. Dr.-Ing.

About

244
Publications
73,947
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
3,890
Citations
Citations since 2016
84 Research Items
2930 Citations
20162017201820192020202120220100200300400500600
20162017201820192020202120220100200300400500600
20162017201820192020202120220100200300400500600
20162017201820192020202120220100200300400500600
Additional affiliations
March 2008 - present
Karlsruhe Institute of Technology
Position
  • Professor
January 2001 - present
February 1999 - present
FZI Forschungszentrum Informatik
Position
  • Managing Director

Publications

Publications (244)
Conference Paper
Full-text available
Connected, cooperative autonomous driving and mobility promises increased comfort and safety for public transportation and logistics in urban and suburban regions. Stationary roadside infrastructure equipped with intelligent perception sensors and communication units has the potential to increase the field of view and mitigate occlusions in percept...
Conference Paper
Full-text available
Cooperative trajectory planning methods for automated vehicles can solve traffic scenarios that require a high degree of cooperation between traffic participants. However, for cooperative systems to integrate into human-centered traffic, the automated systems must behave human-like so that humans can anticipate the system's decisions. While Reinfor...
Conference Paper
Full-text available
Tracking-by-Detection has become the major paradigm in Multi Object Tracking (MOT) for a large variety of sensors. Regardless of the type of tracking system, hyper parameters are often chosen manually instead of doing a structured search to reveal the full potential of the system.In this work we tackle this problem by utilizing Bayesian Optimizatio...
Conference Paper
Full-text available
Data driven approaches for decision making applied to automated driving require appropriate generalization strategies, to ensure applicability to the world's variability. Current approaches either do not generalize well beyond the training data or are not capable to consider a variable number of traffic participants. Therefore we propose an invaria...
Conference Paper
Not only correct scene understanding, but also ability to understand the decision making process of neural networks is essential for safe autonomous driving. Current work mainly focuses on uncertainty measures, often based on Monte Carlo dropout, to gain at least some insight into a models confidence. We investigate a mixture of experts architectur...
Preprint
Efficient driving in urban traffic scenarios requires foresight. The observation of other traffic participants, and the inference of their possible next actions depending on the own action is considered cooperative prediction and planning. Humans are well equipped with the capability to predict the actions of multiple interacting traffic participan...
Conference Paper
Various approaches to end-to-end vehicle control using deep neural networks have been proposed recently, examining various architectures to predict steering angles based on raw sensor data. However, most of these approaches are only used as black boxes, which work well in most scenarios and drive vehicles in real traffic, but it is unclear when the...
Conference Paper
Simulation-based testing is seen as a major requirement for the safety validation of highly automated driving. One crucial part of such test architectures are models of environment perception sensors such as camera, lidar and radar sensors. Currently, an objective evaluation and the comparison of different modeling approaches for automotive lidar s...
Preprint
State-of-the-art approaches for the semantic labeling of LiDAR point clouds heavily rely on the use of deep Convolutional Neural Networks (CNNs). However, transferring network architectures across different LiDAR sensor types represents a significant challenge, especially due to sensor specific design choices with regard to network architecture as...
Preprint
This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Second, we align the quality of our...
Conference Paper
Full-text available
In autonomous driving, the detection of objects like surrounding vehicles based on monocular RGB images is usually performed by 2D bounding box detectors. The resulting 2D objects can be used for a first coarse 3D position estimate but for a precise location, additional sensor data has to be taken into account. For further use in sensor fusion syst...
Preprint
Full-text available
Current state-of-the-art object detection algorithms still suffer the problem of imbalanced distribution of training data over object classes and background. Recent work introduced a new loss function called focal loss to mitigate this problem, but at the cost of an additional hyperparameter. Manually tuning this hyperparameter for each training ta...
Article
Full-text available
This report proposes a novel approach to learn from demonstrations and classify contextual tasks the human operator executes by remotely controlling a mobile robot with joystick, aiming to assist mobile robot teleoperation within a shared autonomy system in a task-appropriate manner. The proposed classifier is implemented with the Gaussian Process...
Chapter
This paper presents the concept, realization and evaluation of a flexible and scalable setup for smart infrastructure at the example of the Test Area Autonomous Driving Baden-Württemberg.
Chapter
Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central component of state-of-the-art perception systems. In addition to accurate spatial perception, a comprehensive semantic understanding of the environment is essential for efficien...
Chapter
This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-established Stixel model originally developed for stereo vision applications. We extend this Stixel concept to incorporate data from multiple sensor modalities. The resulting mid...
Preprint
Sampling-based motion planning is an effective tool to compute safe trajectories for automated vehicles in complex environments. However, a fast convergence to the optimal solution can only be ensured with the use of problem-specific sampling distributions. Due to the large variety of driving situations within the context of automated driving, it i...
Conference Paper
Full-text available
Reliable traffic light detection is one crucial key component for autonomous driving in urban areas. This includes the extraction of direction arrows contained within the traffic lights as an autonomous car will need this information for selecting the traffic light corresponding to its current lane. Current state of the art traffic light detection...
Conference Paper
Full-text available
Urban traffic scenarios often require a high degree of cooperation between traffic participants to ensure safety and efficiency. Observing the behavior of others, humans infer whether or not others are cooperating. This work aims to extend the capabilities of automated vehicles, enabling them to cooperate implicitly in heterogeneous environments. C...
Conference Paper
Full-text available
Many modern approaches for autonomous vehicles are still limited to a low-level data representation without considering complex relational information about their environment. This often leads to a generalization problem in complex situations where algorithms only perform well in tailored scenes. The general challenge lies in combining probabilisti...
Conference Paper
With the steady rise of advanced driver assistance systems (ADAS), more and more aspects of the driving task are transferred from the human driver to the vehicle’s control system. In order to handle many of these responsibilities, vehicles need to understand their environment and adjust their behavior according to it. An important aspect of the veh...
Preprint
This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-established Stixel model originally developed for stereo vision applications. We extend this Stixel concept to incorporate data from multiple sensor modalities. The resulting mid...
Preprint
Urban traffic scenarios often require a high degree of cooperation between traffic participants to ensure safety and efficiency. Observing the behavior of others, humans infer whether or not others are cooperating. This work aims to extend the capabilities of automated vehicles, enabling them to cooperate implicitly in heterogeneous environments. C...
Preprint
Making the right decision in traffic is a challenging task that is highly dependent on individual preferences as well as the surrounding environment. Therefore it is hard to model solely based on expert knowledge. In this work we use Deep Reinforcement Learning to learn maneuver decisions based on a compact semantic state representation. This ensur...
Preprint
Today's automated vehicles lack the ability to cooperate implicitly with others. This work presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative planning using macro-actions for automated vehicles in heterogeneous environments. Based on cooperative modeling of other agents and Decoupled-UCT (a variant of MCTS), the...
Conference Paper
Full-text available
Making the right decision in traffic is a challenging task that is highly dependent on individual preferences as well as the surrounding environment. Therefore it is hard to model solely based on expert knowledge. In this work we use Deep Reinforcement Learning to learn maneuver decisions based on a compact semantic state representation. This ensur...
Conference Paper
Full-text available
Today's automated vehicles lack the ability to cooperate implicitly with others. This work presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative planning using macro-actions for automated vehicles in heterogeneous environments. Based on cooperative mod-eling of other agents and Decoupled-UCT (a variant of MCTS), the...
Conference Paper
Advanced driver assistance systems allow for increasing user comfort and safety by sensing the environment and anticipating upcoming hazards. Often, this requires to accurately predict how situations will change. Recent approaches make simplifying assumptions on the predictive model of the Ego-Vehicle motion or assume prior knowledge, such as road...
Preprint
Full-text available
Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central component of state-of-the-art perception systems. In addition to accurate spatial perception, a comprehensive semantic understanding of the environment is essential for efficien...
Conference Paper
Full-text available
Representation and execution of movement in biology is an active field of research relevant to neurorobotics. Humans can remember grasp motions and modify them during execution based on the shape and the intended interaction with objects. We present a hierarchical spiking neural network with a biologically inspired architecture for representing dif...
Conference Paper
Full-text available
We propose an integrated approach of combining end-to-end learned trajectory proposals with a probabilistic sampling based planning algorithm for autonomous driving. A convolutional neural network is trained based on monocular image data to predict prospective steering angles. By using a local history of image data, we achieve an implicit spatial r...
Conference Paper
Full-text available
Making Convolutional Neural Networks (CNNs) successful in learning problems like image based ego motion estimation, highly depends on the ability of the network to extract the temporal information from videos. Therefore, the architecture of a network needs the capability to learn temporal features. We propose two CNN architectures which are able to...
Conference Paper
Full-text available
Navigation and obstacle avoidance are two problems that are not easily incorporated into direct control of autonomous vehicles solely based on visual input. However, they are required if lane following given proper lane markings is not enough to incorporate trained systems into larger architectures. This paper presents a method to allow for obstacl...
Conference Paper
Full-text available
In this paper, we present a method to estimate abstract parameters of high definition (HD) maps from sensor data. Parameters we estimate include the distance from ego-vehicle to road boundary, orientation of the ego-vehicle with respect to lanes, number of lanes, and street type. Our method is realized as a Convolutional Neural Network (CNN) that t...
Article
This paper presents the concepts and methods utilized by Team AnnieWAY for the 2016 Grand Cooperative Driving Challenge. The paper introduces the automated vehicle BerthaOne. The vehicle, even though being based on the Bertha platform, distinguishes itself from its siblings by its software modules and algorithms. We, therefore, describe its system...
Article
Grid maps are widely used in robotics to represent obstacles in the environment and differentiating dynamic objects from static infrastructure is essential for many practical applications. In this work, we present a methods that uses a deep convolutional neural network (CNN) to infer whether grid cells are covering a moving object or not. Compared...
Conference Paper
We focus on assisting mobile robot teleoperation in a task-appropriate way, where we model the user intention as an action primitive to perform a contextual task, e.g. doorway crossing and object inspection, and provide motion assistance according to the task recognition. This paper contributes to formulating motion assistance in a data-driven mann...
Conference Paper
Full-text available
Artificial neural networks are known to perform function approximation but with increasingly large non-redundant input spaces, the number of required neurons grows drastically. Functions have to be sampled densely leading to large data sets which imposes problems for applications such as neurorobotics, and requires a long time for training. Further...
Conference Paper
Full-text available
We present a reinforcement learning approach using Deep Q-Networks to steer a vehicle in a 3D physics simulation. Relying solely on camera image input the approach directly learns steering the vehicle in an end-to-end manner. The system is able to learn human driving behavior without the need of any labeled training data. An action-based reward fun...
Conference Paper
Full-text available
Vector Symbolic Architectures (VSAs) define a set of operations for association, storage, manipulation and retrieval of symbolic concepts, represented as fixed-length vectors in IRn. A specific instance of VSAs, Holographic Reduced Representations (HRRs), have proven to exhibit properties similar to human short-term memory and as such are interesti...
Article
Full-text available
While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture...