Search Results for author: J. Marius Zöllner

Found 53 papers, 12 papers with code

Fully Convolutional Neural Networks for Dynamic Object Detection in Grid Maps

no code implementations10 Sep 2017 Florian Piewak, Timo Rehfeld, Michael Weber, J. Marius Zöllner

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.

object-detection Object Detection

Decentralized Cooperative Planning for Automated Vehicles with Hierarchical Monte Carlo Tree Search

no code implementations25 Jul 2018 Karl Kurzer, Chenyang Zhou, J. Marius Zöllner

This work presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative planning using macro-actions for automated vehicles in heterogeneous environments.

Adaptive Behavior Generation for Autonomous Driving using Deep Reinforcement Learning with Compact Semantic States

no code implementations10 Sep 2018 Peter Wolf, Karl Kurzer, Tobias Wingert, Florian Kuhnt, J. Marius Zöllner

This ensures a consistent model of the environment across scenarios as well as a behavior adaptation function, enabling on-line changes of desired behaviors without re-training.

Autonomous Driving Reinforcement Learning (RL)

Decentralized Cooperative Planning for Automated Vehicles with Continuous Monte Carlo Tree Search

1 code implementation10 Sep 2018 Karl Kurzer, Florian Engelhorn, J. Marius Zöllner

Urban traffic scenarios often require a high degree of cooperation between traffic participants to ensure safety and efficiency.

Learning to Predict Ego-Vehicle Poses for Sampling-Based Nonholonomic Motion Planning

no code implementations3 Dec 2018 Holger Banzhaf, Paul Sanzenbacher, Ulrich Baumann, J. Marius Zöllner

This paper introduces therefore a data-driven approach utilizing a deep convolutional neural network (CNN): Given the current driving situation, future ego-vehicle poses can be directly generated from the output of the CNN allowing to guide the motion planner efficiently towards the optimal solution.

Motion Planning

Automated Focal Loss for Image based Object Detection

no code implementations19 Apr 2019 Michael Weber, Michael Fürst, J. Marius Zöllner

With automated focal loss we introduce a new loss function which substitutes this hyperparameter by a parameter that is automatically adapted during the training progress and controls the amount of focusing on hard training examples.

Object object-detection +2

Accelerating Cooperative Planning for Automated Vehicles with Learned Heuristics and Monte Carlo Tree Search

no code implementations2 Feb 2020 Karl Kurzer, Marcus Fechner, J. Marius Zöllner

Humans are well equipped with the capability to predict the actions of multiple interacting traffic participants and plan accordingly, without the need to directly communicate with others.

Parallelization of Monte Carlo Tree Search in Continuous Domains

1 code implementation30 Mar 2020 Karl Kurzer, Christoph Hörtnagl, J. Marius Zöllner

Monte Carlo Tree Search (MCTS) has proven to be capable of solving challenging tasks in domains such as Go, chess and Atari.

Trajectory Planning

Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study

no code implementations6 Apr 2020 Larissa T. Triess, David Peter, Christoph B. Rist, J. Marius Zöllner

Autonomous vehicles need to have a semantic understanding of the three-dimensional world around them in order to reason about their environment.

Autonomous Vehicles Semantic Segmentation

Generalizing Decision Making for Automated Driving with an Invariant Environment Representation using Deep Reinforcement Learning

no code implementations12 Feb 2021 Karl Kurzer, Philip Schörner, Alexander Albers, Hauke Thomsen, Karam Daaboul, J. Marius Zöllner

Data driven approaches for decision making applied to automated driving require appropriate generalization strategies, to ensure applicability to the world's variability.

Decision Making Navigate

Temporal Feature Networks for CNN based Object Detection

no code implementations22 Mar 2021 Michael Weber, Tassilo Wald, J. Marius Zöllner

For reliable environment perception, the use of temporal information is essential in some situations.

Object object-detection +2

Safe Continuous Control with Constrained Model-Based Policy Optimization

1 code implementation14 Apr 2021 Moritz A. Zanger, Karam Daaboul, J. Marius Zöllner

Further, we provide theoretical and empirical analyses regarding the implications of model-usage on constrained policy optimization problems and introduce a practical algorithm that accelerates policy search with model-generated data.

Continuous Control Reinforcement Learning (RL) +1

Description of Corner Cases in Automated Driving: Goals and Challenges

no code implementations20 Sep 2021 Daniel Bogdoll, Jasmin Breitenstein, Florian Heidecker, Maarten Bieshaar, Bernhard Sick, Tim Fingscheidt, J. Marius Zöllner

Scaling the distribution of automated vehicles requires handling various unexpected and possibly dangerous situations, termed corner cases (CC).

Self-Supervised Action-Space Prediction for Automated Driving

no code implementations21 Sep 2021 Faris Janjoš, Maxim Dolgov, J. Marius Zöllner

In this paper, we present a novel learned multi-modal trajectory prediction architecture for automated driving.

Trajectory Prediction

Quantifying point cloud realism through adversarially learned latent representations

no code implementations24 Sep 2021 Larissa T. Triess, David Peter, Stefan A. Baur, J. Marius Zöllner

In a series of experiments, we confirm the soundness of our metric by applying it in controllable task setups and on unseen data.

Anomaly Detection Metric Learning +1

Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models

1 code implementation5 Nov 2021 Daniel Bogdoll, Johannes Jestram, Jonas Rauch, Christin Scheib, Moritz Wittig, J. Marius Zöllner

Due to the massive volume of sensor data that must be sent in real-time, highly efficient data compression is elementary to prevent an overload of network infrastructure.

Autonomous Vehicles Data Compression

Towards Traffic Scene Description: The Semantic Scene Graph

no code implementations19 Nov 2021 Maximilian Zipfl, J. Marius Zöllner

Depending on the relative location between two traffic participants with respect to the road topology, semantically classified edges are created between the corresponding nodes.

Semi-Local Convolutions for LiDAR Scan Processing

no code implementations NeurIPS Workshop ICBINB 2021 Larissa T. Triess, David Peter, J. Marius Zöllner

A number of applications, such as mobile robots or automated vehicles, use LiDAR sensors to obtain detailed information about their three-dimensional surroundings.

Ad-datasets: a meta-collection of data sets for autonomous driving

1 code implementation3 Feb 2022 Daniel Bogdoll, Felix Schreyer, J. Marius Zöllner

In this paper, we present ad-datasets, an online tool that provides such an overview for more than 150 data sets.

Autonomous Driving

Quantification of Actual Road User Behavior on the Basis of Given Traffic Rules

1 code implementation7 Feb 2022 Daniel Bogdoll, Moritz Nekolla, Tim Joseph, J. Marius Zöllner

Driving on roads is restricted by various traffic rules, aiming to ensure safety for all traffic participants.

Autonomous Driving

Learning Reward Models for Cooperative Trajectory Planning with Inverse Reinforcement Learning and Monte Carlo Tree Search

1 code implementation14 Feb 2022 Karl Kurzer, Matthias Bitzer, J. Marius Zöllner

Cooperative trajectory planning methods for automated vehicles can solve traffic scenarios that require a high degree of cooperation between traffic participants.

Decision Making reinforcement-learning +2

Cooperative Trajectory Planning in Uncertain Environments with Monte Carlo Tree Search and Risk Metrics

no code implementations9 Mar 2022 Philipp Stegmaier, Karl Kurzer, J. Marius Zöllner

It can be demonstrated that the integration of risk metrics in the final selection policy consistently outperforms a baseline in uncertain environments, generating considerably safer trajectories.

Trajectory Planning

Is Neuron Coverage Needed to Make Person Detection More Robust?

no code implementations21 Apr 2022 Svetlana Pavlitskaya, Şiyar Yıkmış, J. Marius Zöllner

Coverage-guided testing (CGT) is an approach that applies mutation or fuzzing according to a predefined coverage metric to find inputs that cause misbehavior.

Autonomous Driving Human Detection

Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability

no code implementations22 Apr 2022 Svetlana Pavlitska, Christian Hubschneider, Lukas Struppek, J. Marius Zöllner

In this work, we apply sparse MoE layers to CNNs for computer vision tasks and analyze the resulting effect on model interpretability.

Image Classification Language Modelling +2

Multimodal Detection of Unknown Objects on Roads for Autonomous Driving

1 code implementation3 May 2022 Daniel Bogdoll, Enrico Eisen, Maximilian Nitsche, Christin Scheib, J. Marius Zöllner

Tremendous progress in deep learning over the last years has led towards a future with autonomous vehicles on our roads.

Anomaly Detection Autonomous Driving

Experiments on Anomaly Detection in Autonomous Driving by Forward-Backward Style Transfers

no code implementations13 Jul 2022 Daniel Bogdoll, Meng Zhang, Maximilian Nitsche, J. Marius Zöllner

As a safety-critical problem, however, anomaly detection is a huge hurdle towards a large-scale deployment of autonomous vehicles in the real world.

Anomaly Detection Autonomous Driving +2

Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

no code implementations15 Jul 2022 Svetlana Pavlitskaya, Bianca-Marina Codău, J. Marius Zöllner

We have evaluated two approaches to generate naturalistic patches: by incorporating patch generation into the GAN training process and by using the pretrained GAN.

object-detection Object Detection

Adversarial Vulnerability of Temporal Feature Networks for Object Detection

no code implementations23 Aug 2022 Svetlana Pavlitskaya, Nikolai Polley, Michael Weber, J. Marius Zöllner

In this work, we study whether temporal feature networks for object detection are vulnerable to universal adversarial attacks.

Autonomous Driving Object +2

A Realism Metric for Generated LiDAR Point Clouds

no code implementations31 Aug 2022 Larissa T. Triess, Christoph B. Rist, David Peter, J. Marius Zöllner

In a series of experiments, we demonstrate the application of our metric to determine the realism of generated LiDAR data and compare the realism estimation of our metric to the performance of a segmentation model.

Segmentation

Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

no code implementations27 Sep 2022 Svetlana Pavlitskaya, Jonas Hendl, Sebastian Kleim, Leopold Müller, Fabian Wylczoch, J. Marius Zöllner

Adversarial patch-based attacks aim to fool a neural network with an intentionally generated noise, which is concentrated in a particular region of an input image.

object-detection Object Detection +1

Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise

no code implementations27 Sep 2022 Svetlana Pavlitskaya, Joël Oswald, J. Marius Zöllner

Motivated by the fact that overfitted neural networks tend to rather memorize noise in the training data than generalize to unseen data, we examine how the training accuracy changes in the presence of increasing data perturbations and study the connection to overfitting.

Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perception

no code implementations26 Oct 2022 Marc Uecker, Tobias Fleck, Marcel Pflugfelder, J. Marius Zöllner

To this end, we propose a novel computational taxonomy of LiDAR point cloud representations used in modern deep neural networks for 3D point cloud processing.

Autonomous Vehicles Computational Efficiency +1

Self Supervised Clustering of Traffic Scenes using Graph Representations

no code implementations24 Nov 2022 Maximilian Zipfl, Moritz Jarosch, J. Marius Zöllner

Examining graphs for similarity is a well-known challenge, but one that is mandatory for grouping graphs together.

Clustering Graph Embedding

Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey

1 code implementation6 Feb 2023 Daniel Bogdoll, Svenja Uhlemeyer, Kamil Kowol, J. Marius Zöllner

Deep neural networks (DNN) which are employed in perception systems for autonomous driving require a huge amount of data to train on, as they must reliably achieve high performance in all kinds of situations.

Anomaly Detection Autonomous Driving

From Model-Based to Data-Driven Simulation: Challenges and Trends in Autonomous Driving

no code implementations23 May 2023 Ferdinand Mütsch, Helen Gremmelmaier, Nicolas Becker, Daniel Bogdoll, Marc René Zofka, J. Marius Zöllner

Simulation is an integral part in the process of developing autonomous vehicles and advantageous for training, validation, and verification of driving functions.

Autonomous Driving

Unscented Autoencoder

2 code implementations8 Jun 2023 Faris Janjoš, Lars Rosenbaum, Maxim Dolgov, J. Marius Zöllner

The Variational Autoencoder (VAE) is a seminal approach in deep generative modeling with latent variables.

Adversarial Attacks on Traffic Sign Recognition: A Survey

no code implementations17 Jul 2023 Svetlana Pavlitska, Nico Lambing, J. Marius Zöllner

In this work, we survey existing works performing either digital or real-world attacks on traffic sign detection and classification models.

Adversarial Attack Traffic Sign Detection +1

Exploring the Potential of World Models for Anomaly Detection in Autonomous Driving

no code implementations10 Aug 2023 Daniel Bogdoll, Lukas Bosch, Tim Joseph, Helen Gremmelmaier, Yitian Yang, J. Marius Zöllner

We provide a characterization of world models and relate individual components to previous works in anomaly detection to facilitate further research in the field.

Anomaly Detection Autonomous Driving +1

Conditioning Latent-Space Clusters for Real-World Anomaly Classification

no code implementations18 Sep 2023 Daniel Bogdoll, Svetlana Pavlitska, Simon Klaus, J. Marius Zöllner

Anomalies in the domain of autonomous driving are a major hindrance to the large-scale deployment of autonomous vehicles.

Anomaly Classification Autonomous Driving +1

Traffic Scene Similarity: a Graph-based Contrastive Learning Approach

no code implementations18 Sep 2023 Maximilian Zipfl, Moritz Jarosch, J. Marius Zöllner

Ensuring validation for highly automated driving poses significant obstacles to the widespread adoption of highly automated vehicles.

Contrastive Learning

KI-PMF: Knowledge Integrated Plausible Motion Forecasting

no code implementations18 Oct 2023 Abhishek Vivekanandan, Ahmed Abouelazm, Philip Schörner, J. Marius Zöllner

Accurately forecasting the motion of traffic actors is crucial for the deployment of autonomous vehicles at a large scale.

Autonomous Vehicles Motion Forecasting +1

Conditional Unscented Autoencoders for Trajectory Prediction

1 code implementation30 Oct 2023 Faris Janjoš, Marcel Hallgarten, Anthony Knittel, Maxim Dolgov, Andreas Zell, J. Marius Zöllner

We leverage recent advances in the space of the VAE, the foundation of the CVAE, which show that a simple change in the sampling procedure can greatly benefit performance.

Trajectory Prediction

MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations

no code implementations20 Nov 2023 Daniel Bogdoll, Yitian Yang, J. Marius Zöllner

Learning unsupervised world models for autonomous driving has the potential to improve the reasoning capabilities of today's systems dramatically.

Autonomous Driving

Heterogeneous Graph-based Trajectory Prediction using Local Map Context and Social Interactions

no code implementations30 Nov 2023 Daniel Grimm, Maximilian Zipfl, Felix Hertlein, Alexander Naumann, Jürgen Lüttin, Steffen Thoma, Stefan Schmid, Lavdim Halilaj, Achim Rettinger, J. Marius Zöllner

Precisely predicting the future trajectories of surrounding traffic participants is a crucial but challenging problem in autonomous driving, due to complex interactions between traffic agents, map context and traffic rules.

Autonomous Driving Relation +1

Can you see me now? Blind spot estimation for autonomous vehicles using scenario-based simulation with random reference sensors

1 code implementation1 Feb 2024 Marc Uecker, J. Marius Zöllner

In this paper, we introduce a method for estimating blind spots for sensor setups of autonomous or automated vehicles and/or robotics applications.

Autonomous Vehicles

Cannot find the paper you are looking for? You can Submit a new open access paper.