no code implementations • 22 Mar 2023 • Tianhang Wang, Guang Chen, Kai Chen, Zhengfa Liu, Bo Zhang, Alois Knoll, Changjun Jiang
To verify our algorithm, we conducted experiments on the V2X-Sim and OPV2V datasets.
no code implementations • 21 Mar 2023 • Haotian Liu, Guang Chen, Sanqing Qu, Yanping Zhang, Zhijun Li, Alois Knoll, Changjun Jiang
Event cameras have the ability to record continuous and detailed trajectories of objects with high temporal resolution, thereby providing intuitive motion cues for optical flow estimation.
no code implementations • 15 Mar 2023 • Liguo Zhou, Tianhao Lin, Alois Knoll
To address the above challenges, based on extensive literature research, this paper analyzes methods for improving and optimizing mainstream object detection algorithms from the perspective of evolution of one-stage and two-stage object detection algorithms.
no code implementations • 12 Mar 2023 • Haichuan Li, Liguo Zhou, Zhenshan Bing, Marzana Khatun, Rolf Jung, Alois Knoll
Several autonomous driving strategies have been applied to autonomous vehicles, especially in the collision avoidance area.
no code implementations • 12 Mar 2023 • Haichuan Li, Liguo Zhou, Alois Knoll
In this paper, we propose a CNN-based method that overcomes the limitation by establishing feature correlations between regions in sequential images using variants of attention.
no code implementations • 25 Feb 2023 • Shangding Gu, Alap Kshirsagar, Yali Du, Guang Chen, Jan Peters, Alois Knoll
Safe robot reinforcement learning (SRRL) is a crucial step towards achieving human-robot coexistence.
no code implementations • 23 Feb 2023 • Hanzhen Zhang, Liguo Zhou, Ruining Wang, Alois Knoll
Using real road testing to optimize autonomous driving algorithms is time-consuming and capital-intensive.
no code implementations • 31 Dec 2022 • Wei Cao, Liguo Zhou, Yuhong Huang, Alois Knoll
There are many artificial intelligence algorithms for autonomous driving, but directly installing these algorithms on vehicles is unrealistic and expensive.
no code implementations • 11 Dec 2022 • Rui Song, Liguo Zhou, Lingjuan Lyu, Andreas Festag, Alois Knoll
To address this bottleneck, we introduce a residual-based federated learning framework (ResFed), where residuals rather than model parameters are transmitted in communication networks for training.
1 code implementation • 21 Nov 2022 • Fengyi Shen, Zador Pataki, Akhil Gurram, Ziyuan Liu, He Wang, Alois Knoll
In this paper, we propose LoopDA for domain adaptive nighttime semantic segmentation.
no code implementations • 21 Sep 2022 • Xiangtong Yao, Zhenshan Bing, Genghang Zhuang, KeJia Chen, Hongkuan Zhou, Kai Huang, Alois Knoll
We thus propose a dual-MDP meta-reinforcement learning method that enables learning new tasks efficiently with symmetric data and language instructions.
no code implementations • 21 Sep 2022 • Hsuan-Cheng Liao, Chih-Hong Cheng, Hasan Esen, Alois Knoll
State-of-the-art object detectors are commonly evaluated based on accuracy metrics such as mean Average Precision (mAP).
1 code implementation • 7 Sep 2022 • Syed Qutub, Florian Geissler, Yang Peng, Ralf Grafe, Michael Paulitsch, Gereon Hinz, Alois Knoll
The evaluation of several representative object detection models shows that even a single bit flip can lead to a severe silent data corruption event with potentially critical safety implications, with e. g., up to (much greater than) 100 FPs generated, or up to approx.
1 code implementation • 24 Aug 2022 • Rui Song, Dai Liu, Dave Zhenyu Chen, Andreas Festag, Carsten Trinitis, Martin Schulz, Alois Knoll
We introduce a novel federated learning framework, FedD3, which reduces the overall communication volume and with that opens up the concept of federated learning to more application scenarios in network-constrained environments.
no code implementations • 28 Jun 2022 • Haitao Meng, Changcai Li, Gang Chen, Alois Knoll
In the experiments, we develop a system with a less powerful stereo matching predictor and adopt the proposed refinement schemes to improve the accuracy.
no code implementations • 17 Jun 2022 • Rui Song, Anupama Hegde, Numan Senel, Alois Knoll, Andreas Festag
Specifically, when the measurement error from the sensors (also referred as measurement noise) is unknown and time varying, the performance of the data fusion process is restricted, which represents a major challenge in the calibration of sensors.
no code implementations • 13 Jun 2022 • Josip Josifovski, Mohammadhossein Malmir, Noah Klarmann, Bare Luka Žagar, Nicolás Navarro-Guerrero, Alois Knoll
Fully randomized simulations and fine-tuning show differentiated results and translate better to the real robot than the other approaches tested.
1 code implementation • 20 May 2022 • Shangding Gu, Long Yang, Yali Du, Guang Chen, Florian Walter, Jun Wang, Yaodong Yang, Alois Knoll
To establish a good foundation for future research in this thread, in this paper, we provide a review for safe RL from the perspectives of methods, theory and applications.
1 code implementation • 2 May 2022 • Ekim Yurtsever, Emeç Erçelik, MingYu Liu, Zhijie Yang, Hanzhen Zhang, Pınar Topçam, Maximilian Listl, Yılmaz Kaan Çaylı, Alois Knoll
Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a supervised 3D detection head.
no code implementations • 13 Apr 2022 • Christian Creß, Walter Zimmer, Leah Strand, Venkatnarayanan Lakshminarasimhan, Maximilian Fortkord, Siyi Dai, Alois Knoll
As part of the first set of data, which we describe in this paper, we provide camera and LiDAR frames from two overhead gantry bridges on the A9 autobahn with the corresponding objects labeled with 3D bounding boxes.
1 code implementation • 1 Apr 2022 • Rui Song, Liguo Zhou, Venkatnarayanan Lakshminarasimhan, Andreas Festag, Alois Knoll
Considering the individual heterogeneity of data distribution, computational and communication capabilities across traffic agents and roadside units, we employ a novel method that addresses the heterogeneity of different aggregation layers of the framework architecture, i. e., aggregation in layers of roadside units and cloud.
no code implementations • 31 Mar 2022 • Walter Zimmer, Emec Ercelik, Xingcheng Zhou, Xavier Jair Diaz Ortiz, Alois Knoll
The purpose of this work is to review the state-of-the-art LiDAR-based 3D object detection methods, datasets, and challenges.
no code implementations • 31 Mar 2022 • Walter Zimmer, Marcus Grabler, Alois Knoll
This work aims to address the challenges in domain adaptation of 3D object detection using infrastructure LiDARs.
no code implementations • 11 Mar 2022 • Marco Oliva, Soubarna Banik, Josip Josifovski, Alois Knoll
We derive a graph representation that models the physical structure of the manipulator and combines the robot's internal state with a low-dimensional description of the visual scene generated by an image encoding network.
1 code implementation • 25 Feb 2022 • Javier López-Randulfe, Nico Reeb, Negin Karimi, Chen Liu, Hector A. Gonzalez, Robin Dietrich, Bernhard Vogginger, Christian Mayr, Alois Knoll
After several decades of continuously optimizing computing systems, the Moore's law is reaching itsend.
no code implementations • 8 Feb 2022 • Hsuan-Cheng Liao, Chih-Hong Cheng, Hasan Esen, Alois Knoll
Attention Networks (ATNs) such as Transformers are used in many domains ranging from Natural Language Processing to Autonomous Driving.
no code implementations • 14 Jan 2022 • Benedikt Feldotto, Cristian Soare, Alois Knoll, Piyanee Sriya, Sarah Astill, Marc de Kamps, Samit Chakrabarty
We use our framework to analyze raw EMG data collected during an isometric knee extension study to identify synergies that drive a musculoskeletal lower limb model.
1 code implementation • 30 Nov 2021 • Fengyi Shen, Akhil Gurram, Ahmet Faruk Tuna, Onay Urfalioglu, Alois Knoll
Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation.
no code implementations • 27 Oct 2021 • Stefan Böhm, Martin Neumayer, Oliver Kramer, Alexander Schiendorfer, Alois Knoll
Cutting and Packing problems are occurring in different industries with a direct impact on the revenue of businesses.
3 code implementations • 6 Oct 2021 • Shangding Gu, Jakub Grudzien Kuba, Munning Wen, Ruiqing Chen, Ziyan Wang, Zheng Tian, Jun Wang, Alois Knoll, Yaodong Yang
To fill these gaps, in this work, we formulate the safe MARL problem as a constrained Markov game and solve it with policy optimisation methods.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 22 Sep 2021 • Zhenshan Bing, Amir EI Sewisy, Genghang Zhuang, Florian Walter, Fabrice O. Morin, Kai Huang, Alois Knoll
As a vital cognitive function of animals, the navigation skill is first built on the accurate perception of the directional heading in the environment.
no code implementations • 23 Aug 2021 • Soubarna Banik, Alejandro Mendoza Garcia, Lorenz Kiwull, Steffen Berweck, Alois Knoll
We evaluate it on our rehab datasets, and observe that the performance degrades significantly from non-rehab to rehab, highlighting the need for these datasets.
1 code implementation • 8 Aug 2021 • Zhenshan Bing, Lukas Knak, Fabrice Oliver Robin, Kai Huang, Alois Knoll
Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills.
no code implementations • 21 May 2021 • Soubarna Banik, Alejandro Mendoza Gracia, Alois Knoll
We propose one such graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses.
no code implementations • 21 May 2021 • Chih-Hong Cheng, Alois Knoll, Hsuan-Cheng Liao
Within the context of autonomous driving, safety-related metrics for deep neural networks have been widely studied for image classification and object detection.
1 code implementation • 25 Apr 2021 • Emeç Erçelik, Ekim Yurtsever, Alois Knoll
Furthermore, ablation studies reinforce that the subject of improvement is temporal fusion and show the effects of different placements of TFM in the object detection pipeline.
no code implementations • 12 Apr 2021 • Corvin Deboeser, Jordan Ivanchev, Thomas Braud, Alois Knoll, David Eckhoff, Alberto Sangiovanni-Vincentelli
This paper introduces the SEAD framework that simplifies the process of designing and describing autonomous vehicle platooning manoeuvres.
2 code implementations • 7 Apr 2021 • Sanqing Qu, Guang Chen, Zhijun Li, Lijun Zhang, Fan Lu, Alois Knoll
Traditional methods mainly focus on foreground and background frames separation with only a single attention branch and class activation sequence.
Weakly Supervised Action Localization Weakly-supervised Temporal Action Localization +1
no code implementations • 10 Mar 2021 • Damir Bojadžić, Julian Kunze, Dinko Osmanković, Mohammadhossein Malmir, Alois Knoll
Therefore, the algorithm presented in this paper needs to anticipate and avoid dynamic obstacles, such as pedestrians or bicycles, but also be fast enough in order to work in real-time so that it can adapt to changes in the environment.
Motion Planning Trajectory Planning Robotics
no code implementations • 5 Mar 2021 • Christoph Schöller, Alois Knoll
In our work, we model motion prediction directly as a density estimation problem with a normalizing flow between a noise distribution and the future motion distribution.
1 code implementation • 10 Feb 2021 • Kai Chen, Guang Chen, Dan Xu, Lijun Zhang, Yuyao Huang, Alois Knoll
Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge.
no code implementations • 5 Feb 2021 • Julian Bernhard, Stefan Pollok, Alois Knoll
Specifically, we first learn an optimal policy in an uncertain environment with Deep Distributional Reinforcement Learning.
Distributional Reinforcement Learning Reinforcement Learning (RL)
no code implementations • 5 Feb 2021 • Julian Bernhard, Alois Knoll
In this work, we adopt this safety objective for interactive planning.
no code implementations • 5 Feb 2021 • Julian Bernhard, Robert Gieselmann, Klemens Esterle, Alois Knoll
With Deep Reinforcement Learning, optimal driving strategies for such problems can be derived also for higher-dimensional problems.
no code implementations • 25 Jan 2021 • Hu Cao, Guang Chen, Zhijun Li, Jianjie Lin, Alois Knoll
Extensive experiments on two public grasping datasets, Cornell and Jacquard demonstrate the state-of-the-art performance of our method in balancing accuracy and inference speed.
Ranked #1 on Robotic Grasping on Jacquard dataset
no code implementations • 18 Jan 2021 • Emmanouil Angelidis, Emanuel Buchholz, Jonathan Patrick Arreguit O'Neil, Alexis Rougè, Terrence Stewart, Axel von Arnim, Alois Knoll, Auke Ijspeert
In this work we propose a spiking CPG neural network and its implementation on neuromorphic hardware as a means to control a simulated lamprey model.
1 code implementation • 18 Dec 2020 • Fan Lu, Guang Chen, Sanqing Qu, Zhijun Li, Yinlong Liu, Alois Knoll
Generally, the frame rates of mechanical LiDAR sensors are 10 to 20 Hz, which is much lower than other commonly used sensors like cameras.
no code implementations • 16 Nov 2020 • Sanqing Qu, Guang Chen, Dan Xu, Jinhu Dong, Fan Lu, Alois Knoll
At each time step, this sampling strategy first estimates current action progression and then decide what temporal ranges should be used to aggregate the optimal supplementary features.
1 code implementation • NeurIPS 2020 • Fan Lu, Guang Chen, Yinlong Liu, Zhongnan Qu, Alois Knoll
To tackle the information loss of random sampling, we exploit a novel random dilation cluster strategy to enlarge the receptive field of each sampled point and an attention mechanism to aggregate the positions and features of neighbor points.
no code implementations • 28 Sep 2020 • Benedikt Feldotto, Heiko Lengenfelder, Alois Knoll
We analyze the individual neuron activity distribution in the network, introduce a pruning algorithm to reduce network size keeping the performance, and with these dense network representations we spot correlations of neuron activity patterns among networks trained for robot manipulators with different joint number.
1 code implementation • 27 Jul 2020 • Zhenshan Bing, Matthias Brucker, Fabrice O. Morin, Kai Huang, Alois Knoll
In this paper, we propose graph-based hindsight goal generation (G-HGG), an extension of HGG selecting hindsight goals based on shortest distances in an obstacle-avoiding graph, which is a discrete representation of the environment.
2 code implementations • 1 Jul 2020 • Klemens Esterle, Luis Gressenbuch, Alois Knoll
We contribute a formalized set of traffic rules for single-direction carriageways, such as on highways.
no code implementations • 27 Jun 2020 • Maximilian Kraus, Seyed Majid Azimi, Emec Ercelik, Reza Bahmanyar, Peter Reinartz, Alois Knoll
Due to the challenges such as the large number and the tiny size of the pedestrians (e. g., 4 x 4 pixels) with their similar appearances as well as different scales and atmospheric conditions of the images with their extremely low frame rates (e. g., 2 fps), current state-of-the-art algorithms including the deep learning-based ones are unable to perform well.
2 code implementations • 22 Jun 2020 • Patrick Hart, Alois Knoll
We show that graph neural networks are capable of handling scenarios with a varying number and order of vehicles during training and application.
2 code implementations • 20 Mar 2020 • Patrick Hart, Alois Knoll
If a policy can handle all counterfactual worlds well, it either has seen similar situations during training or it generalizes well and is deemed to be fit enough to be executed in the actual world.
no code implementations • 17 Mar 2020 • Elie Aljalbout, Florian Walter, Florian Röhrbein, Alois Knoll
This model is the main focus of this work, as its contribution is not limited to engineering but also applicable to neuroscience.
no code implementations • 10 Mar 2020 • Zhenshan Bing, Claus Meschede, Guang Chen, Alois Knoll, Kai Huang
Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications.
no code implementations • 2 Mar 2020 • Michael Hammann, Maximilian Kraus, Sina Shafaei, Alois Knoll
Identity recognition in a car cabin is a critical task nowadays and offers a great field of applications ranging from personalizing intelligent cars to suit drivers physical and behavioral needs to increasing safety and security.
no code implementations • 16 Jun 2019 • Annkathrin Krämmer, Christoph Schöller, Dhiraj Gulati, Venkatnarayanan Lakshminarasimhan, Franz Kurz, Dominik Rosenbaum, Claus Lenz, Alois Knoll
An Intelligent Infrastructure System can fill in the gaps in a vehicle's perception and extend its field of view by providing additional detailed information about its surroundings, in the form of a digital model of the current traffic situation, i. e. a digital twin.
1 code implementation • 14 Jun 2019 • Thomas Brunner, Frederik Diehl, Alois Knoll
Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail.
no code implementations • 19 May 2019 • Thomas Brunner, Frederik Diehl, Michael Truong Le, Alois Knoll
Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning.
1 code implementation • 29 Apr 2019 • Yinlong Liu, Alois Knoll, Guang Chen
Accordingly, we propose a vertical direction estimation method by considering the relationship between the vertical frame and horizontal frames.
1 code implementation • 18 Apr 2019 • Christoph Schöller, Maximilian Schnettler, Annkathrin Krämmer, Gereon Hinz, Maida Bakovic, Müge Güzet, Alois Knoll
Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception.
no code implementations • 25 Mar 2019 • Yinlong Liu, Xuechen Li, Manning Wang, Guang Chen, Zhijian Song, Alois Knoll
In this paper, we consider pairwise constraints and propose a globally optimal algorithm for solving the absolute pose estimation problem.
2 code implementations • 19 Mar 2019 • Christoph Schöller, Vincent Aravantinos, Florian Lay, Alois Knoll
Our work shows how neural networks for pedestrian motion prediction can be thoroughly evaluated and our results indicate which research directions for neural motion prediction are promising in future.
no code implementations • 4 Mar 2019 • Frederik Diehl, Thomas Brunner, Michael Truong Le, Alois Knoll
We show that prediction error in scenarios with much interaction decreases by 30% compared to a model that does not take interactions into account.
3 code implementations • ICCV 2019 • Thomas Brunner, Frederik Diehl, Michael Truong Le, Alois Knoll
We consider adversarial examples for image classification in the black-box decision-based setting.
no code implementations • 17 Aug 2018 • Mingchuan Zhou, Mahdi Hamad, Jakob Weiss, Abouzar Eslami, Kai Huang, Mathias Maier, Chris P. Lohmann, Nassir Navab, Alois Knoll, M. Ali Nasseri
Ophthalmic microsurgery is known to be a challenging operation, which requires very precise and dexterous manipulation.
no code implementations • 6 Dec 2017 • Guang Chen, Shu Liu, Kejia Ren, Zhongnan Qu, Changhong Fu, Gereon Hinz, Alois Knoll
However, the mobile sensing perception brings new challenges for how to efficiently analyze and intelligently interpret the deluge of IoT data in mission- critical services.
no code implementations • ICCV 2015 • Philipp Heise, Brian Jensen, Sebastian Klose, Alois Knoll
We formulate the combined multi-view stereo reconstruction and refinement as a variational optimization problem.