Search

Your search keyword '"Stachniss, Cyrill"' showing total 673 results
Start Over Author "Stachniss, Cyrill"
673 results on '"Stachniss, Cyrill"'

162. Learning Mixed Strategies in Trajectory Games

Author

Peters, L. (author), Fridovich-Keil, David (author), Ferranti, L. (author), Stachniss, Cyrill (author), Alonso Mora, J. (author), Laine, Forrest (author), Peters, L. (author), Fridovich-Keil, David (author), Ferranti, L. (author), Stachniss, Cyrill (author), Alonso Mora, J. (author), and Laine, Forrest (author)

Abstract

In multi-agent settings, game theory is a natural framework for describing the strategic interactions of agents whose objectives depend upon one another’s behavior. Trajectory games capture these complex effects by design. In competitive settings, this makes them a more faithful interaction model than traditional “predict then plan” approaches. However, current game-theoretic planning methods have important limitations. In this work, we propose two main contributions. First, we introduce an offline training phase which reduces the online computational burden of solving trajectory games. Second, we formulate a lifted game which allows players to optimize multiple candidate trajectories in unison and thereby construct more competitive “mixed” strategies. We validate our approach on a number of experiments using the pursuit-evasion game “tag.”, Learning & Autonomous Control

Published
2022

170. Learning Mixed Strategies in Trajectory Games

Author

Peters, L., Fridovich-Keil, David, Ferranti, L., Stachniss, Cyrill, Alonso Mora, J., Laine, Forrest, Hauser, Kris, Shell, Dylan, and Huang, Shoudong

Abstract

In multi-agent settings, game theory is a natural framework for describing the strategic interactions of agents whose objectives depend upon one another’s behavior. Trajectory games capture these complex effects by design. In competitive settings, this makes them a more faithful interaction model than traditional “predict then plan” approaches. However, current game-theoretic planning methods have important limitations. In this work, we propose two main contributions. First, we introduce an offline training phase which reduces the online computational burden of solving trajectory games. Second, we formulate a lifted game which allows players to optimize multiple candidate trajectories in unison and thereby construct more competitive “mixed” strategies. We validate our approach on a number of experiments using the pursuit-evasion game “tag.”

Published
2022

173. Autonomous Parking Using Previous Paths

Author

Siedentop, Christoph, primary, Laukart, Viktor, additional, Krastev, Boris, additional, Kasper, Dietmar, additional, Wedel, Andreas, additional, Breuel, Gabi, additional, and Stachniss, Cyrill, additional

Published
2015
Full Text
View/download PDF

184. Building an Aerial–Ground Robotics System for Precision Farming: An Adaptable Solution

Author

Pretto, Alberto, primary, Aravecchia, Stephanie, additional, Burgard, Wolfram, additional, Chebrolu, Nived, additional, Dornhege, Christian, additional, Falck, Tillmann, additional, Fleckenstein, Freya, additional, Fontenla, Alessandra, additional, Imperoli, Marco, additional, Khanna, Raghav, additional, Liebisch, Frank, additional, Lottes, Philipp, additional, Milioto, Andres, additional, Nardi, Daniele, additional, Nardi, Sandro, additional, Pfeifer, Johannes, additional, Popovic, Marija, additional, Potena, Ciro, additional, Pradalier, Cedric, additional, Rothacker-Feder, Elisa, additional, Sa, Inkyu, additional, Schaefer, Alexander, additional, Siegwart, Roland, additional, Stachniss, Cyrill, additional, Walter, Achim, additional, Winterhalter, Wera, additional, Wu, Xiaolong, additional, and Nieto, Juan, additional

Published
2021
Full Text
View/download PDF

193. 4D Panoptic LiDAR Segmentation

Author

Aygun, Mehmet, primary, Osep, Aljosa, additional, Weber, Mark, additional, Maximov, Maxim, additional, Stachniss, Cyrill, additional, Behley, Jens, additional, and Leal-Taixe, Laura, additional

Published
2021
Full Text
View/download PDF

200. Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data

Author

Chen, Xieyuanli, Li, Shijie, Mersch, Benedikt, Wiesmann, Louis, Gall, Jürgen, Behley, Jens, Stachniss, Cyrill, Chen, Xieyuanli, Li, Shijie, Mersch, Benedikt, Wiesmann, Louis, Gall, Jürgen, Behley, Jens, and Stachniss, Cyrill

Abstract

The ability to detect and segment moving objects in a scene is essential for building consistent maps, making future state predictions, avoiding collisions, and planning. In this paper, we address the problem of moving object segmentation from 3D LiDAR scans. We propose a novel approach that pushes the current state of the art in LiDAR-only moving object segmentation forward to provide relevant information for autonomous robots and other vehicles. Instead of segmenting the point cloud semantically, i.e., predicting the semantic classes such as vehicles, pedestrians, roads, etc., our approach accurately segments the scene into moving and static objects, i.e., also distinguishing between moving cars vs. parked cars. Our proposed approach exploits sequential range images from a rotating 3D LiDAR sensor as an intermediate representation combined with a convolutional neural network and runs faster than the frame rate of the sensor. We compare our approach to several other state-of-the-art methods showing superior segmentation quality in urban environments. Additionally, we created a new benchmark for LiDAR-based moving object segmentation based on SemanticKITTI. We published it to allow other researchers to compare their approaches transparently and we furthermore published our code., Comment: Accepted by RA-L with IROS 2021

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results