2023
|
Yadav, Harsh; Xue, Honghu; Rudall, Yan; Bakr, Mohamed; Hein, Benedikt; Rueckert, Elmar; Nguyen, Thinh Deep Reinforcement Learning for Autonomous Navigation in Intralogistics Workshop 2023, (European Control Conference (ECC) Workshop, Extended Abstract.). @workshop{Yadav2023,
title = {Deep Reinforcement Learning for Autonomous Navigation in Intralogistics},
author = {Harsh Yadav and Honghu Xue and Yan Rudall and Mohamed Bakr and Benedikt Hein and Elmar Rueckert and Thinh Nguyen},
url = {https://cloud.cps.unileoben.ac.at/index.php/s/tw4D43WTzG6yLmE},
year = {2023},
date = {2023-03-10},
urldate = {2023-03-10},
abstract = {Even with several advances in autonomous mobile robots, navigation in a highly dynamic environment still remains a challenge. Classical navigation systems, such as Simultaneous Localization and Mapping (SLAM), build a map of the environment and constructing maps of highly dynamic environments is impractical. Deep Reinforcement Learning (DRL) approaches have the ability to learn policies without knowledge of the maps or the transition models of the environment.
The aim of our work is to investigate the potential of using DRL to control an autonomous mobile robot to dock with a load carrier. This paper presents an initial successful training result of the Soft Actor-Critic (SAC) algorithm, which can navigate a robot toward an open door only based on the 360° LiDAR observations. Ongoing work is using visual sensors for load carrier docking.},
howpublished = {European Control Conference (ECC)},
note = {European Control Conference (ECC) Workshop, Extended Abstract.},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
Even with several advances in autonomous mobile robots, navigation in a highly dynamic environment still remains a challenge. Classical navigation systems, such as Simultaneous Localization and Mapping (SLAM), build a map of the environment and constructing maps of highly dynamic environments is impractical. Deep Reinforcement Learning (DRL) approaches have the ability to learn policies without knowledge of the maps or the transition models of the environment.
The aim of our work is to investigate the potential of using DRL to control an autonomous mobile robot to dock with a load carrier. This paper presents an initial successful training result of the Soft Actor-Critic (SAC) algorithm, which can navigate a robot toward an open door only based on the 360° LiDAR observations. Ongoing work is using visual sensors for load carrier docking. |  |
2022
|
Xue, Honghu; Song, Rui; Petzold, Julian; Hein, Benedikt; Hamann, Heiko; Rueckert, Elmar End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments Proceedings Article In: International Conference on Humanoid Robots (Humanoids 2022), 2022. @inproceedings{Xue2022b,
title = {End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments},
author = {Honghu Xue and Rui Song and Julian Petzold and Benedikt Hein and Heiko Hamann and Elmar Rueckert},
url = {https://cloud.cps.unileoben.ac.at/index.php/s/RzMQWqsFarQ6Kw4},
year = {2022},
date = {2022-09-26},
urldate = {2022-09-26},
publisher = {International Conference on Humanoid Robots (Humanoids 2022)},
abstract = {We solve a visual navigation problem in an urban setting via deep reinforcement learning in an end-to-end manner. A major challenge of a first-person visual navigation problem lies in severe partial observability and sparse positive experiences of reaching the goal. To address partial observability, we propose a novel 3D-temporal convolutional network to encode sequential historical visual observations, its effectiveness is verified by comparing to a commonly-used frame-stacking
approach. For sparse positive samples, we propose an improved automatic curriculum learning algorithm NavACL+, which
proposes meaningful curricula starting from easy tasks and gradually generalizes to challenging ones. NavACL+ is shown to
facilitate the learning process, greatly improve the task success rate on difficult tasks by at least 40% and offer enhanced
generalization to different initial poses compared to training from a fixed initial pose and the original NavACL algorithm.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We solve a visual navigation problem in an urban setting via deep reinforcement learning in an end-to-end manner. A major challenge of a first-person visual navigation problem lies in severe partial observability and sparse positive experiences of reaching the goal. To address partial observability, we propose a novel 3D-temporal convolutional network to encode sequential historical visual observations, its effectiveness is verified by comparing to a commonly-used frame-stacking
approach. For sparse positive samples, we propose an improved automatic curriculum learning algorithm NavACL+, which
proposes meaningful curricula starting from easy tasks and gradually generalizes to challenging ones. NavACL+ is shown to
facilitate the learning process, greatly improve the task success rate on difficult tasks by at least 40% and offer enhanced
generalization to different initial poses compared to training from a fixed initial pose and the original NavACL algorithm. |  |
Herzog, Rebecca; Berger, Till M; Pauly, Martje Gesine; Xue, Honghu; Rueckert, Elmar; Munchau, Alexander; B"aumer, Tobias; Weissbach, Anne Cerebellar transcranial current stimulation-an intraindividual comparison of different techniques Journal Article In: Frontiers in Neuroscience, 2022. @article{Herzog2022,
title = {Cerebellar transcranial current stimulation-an intraindividual comparison of different techniques},
author = {Rebecca Herzog and Till M Berger and Martje Gesine Pauly and Honghu Xue and Elmar Rueckert and Alexander Munchau and Tobias B{"a}umer and Anne Weissbach},
url = {https://cloud.cps.unileoben.ac.at/index.php/s/4qoooTyjFfBwYEZ},
doi = {10.3389/fnins.2022.987472},
year = {2022},
date = {2022-09-19},
urldate = {2022-09-19},
journal = {Frontiers in Neuroscience},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|  |
Xue, Honghu; Hein, Benedikt; Bakr, Mohamed; Schildbach, Georg; Abel, Bengt; Rueckert, Elmar Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics Journal Article In: Applied Sciences (MDPI), Special Issue on Intelligent Robotics, 2022, (Supplement: https://cloud.cps.unileoben.ac.at/index.php/s/Sj68rQewnkf4ppZ). @article{Xue2022,
title = {Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics},
author = {Honghu Xue and Benedikt Hein and Mohamed Bakr and Georg Schildbach and Bengt Abel and Elmar Rueckert},
editor = {/},
url = {https://cloud.cps.unileoben.ac.at/index.php/s/yddDZ7z9oqxenCi
},
year = {2022},
date = {2022-01-31},
urldate = {2022-01-31},
journal = {Applied Sciences (MDPI), Special Issue on Intelligent Robotics},
abstract = {We propose a deep reinforcement learning approach for solving a mapless navigation problem in warehouse scenarios. The automatic guided vehicle is equipped with LiDAR and frontal RGB sensors and learns to reach underneath the target dolly. The challenges reside in the sparseness of positive samples for learning, multi-modal sensor perception with partial observability, the demand for accurate steering maneuvers together with long training cycles. To address these points, we proposed NavACL-Q as an automatic curriculum learning together with distributed soft actor-critic. The performance of the learning algorithm is evaluated exhaustively in a different warehouse environment to check both robustness and generalizability of the learned policy. Results in NVIDIA Isaac Sim demonstrates that our trained agent significantly outperforms the map-based navigation pipeline provided by NVIDIA Isaac Sim in terms of higher agent-goal distances and relative orientations. The ablation studies also confirmed that NavACL-Q greatly facilitates the whole learning process and a pre-trained feature extractor manifestly boosts the training speed.},
note = {Supplement: https://cloud.cps.unileoben.ac.at/index.php/s/Sj68rQewnkf4ppZ},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We propose a deep reinforcement learning approach for solving a mapless navigation problem in warehouse scenarios. The automatic guided vehicle is equipped with LiDAR and frontal RGB sensors and learns to reach underneath the target dolly. The challenges reside in the sparseness of positive samples for learning, multi-modal sensor perception with partial observability, the demand for accurate steering maneuvers together with long training cycles. To address these points, we proposed NavACL-Q as an automatic curriculum learning together with distributed soft actor-critic. The performance of the learning algorithm is evaluated exhaustively in a different warehouse environment to check both robustness and generalizability of the learned policy. Results in NVIDIA Isaac Sim demonstrates that our trained agent significantly outperforms the map-based navigation pipeline provided by NVIDIA Isaac Sim in terms of higher agent-goal distances and relative orientations. The ablation studies also confirmed that NavACL-Q greatly facilitates the whole learning process and a pre-trained feature extractor manifestly boosts the training speed. |  |
2021
|
Xue, Honghu; Herzog, Rebecca; Berger, Till M.; Bäumer, Tobias; Weissbach, Anne; Rueckert, Elmar Using Probabilistic Movement Primitives in analyzing human motion differences under Transcranial Current Stimulation Journal Article In: Frontiers in Robotics and AI , vol. 8, 2021, ISSN: 2296-9144. @article{Rueckert2021,
title = {Using Probabilistic Movement Primitives in analyzing human motion differences under Transcranial Current Stimulation},
author = {Honghu Xue and Rebecca Herzog and Till M. Berger and Tobias Bäumer and Anne Weissbach and Elmar Rueckert},
editor = {Kensuke Harada},
url = {https://cps.unileoben.ac.at/wp/Frontiers2021Xue.pdf},
issn = {2296-9144},
year = {2021},
date = {2021-08-14},
urldate = {2021-08-14},
journal = {Frontiers in Robotics and AI },
volume = {8},
abstract = {In medical tasks such as human motion analysis, computer-aided auxiliary systems have become preferred choice for human experts for its high efficiency. However, conventional approaches are typically based on user-defined features such as movement onset times, peak velocities, motion vectors or frequency domain analyses. Such approaches entail careful data post-processing or specific domain knowledge to achieve a meaningful feature extraction. Besides, they are prone to noise and the manual-defined features could hardly be re-used for other analyses. In this paper, we proposed probabilistic movement primitives(ProMPs), a widely-used approach in robot skill learning, to model human motions. The benefit of ProMPs is that the features are directly learned from the data and ProMPs can capture important features describing the trajectory shape, which can easily be extended to other tasks. Distinct from previous research, where classification tasks are mostly investigated, we applied ProMPs together with a variant of Kullback-Leibler (KL) divergence to quantify the effect of different transcranial current stimulation methods on human motions. We presented an initial result with10participants. The results validate ProMPs as a robust and effective feature extractor for human motions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In medical tasks such as human motion analysis, computer-aided auxiliary systems have become preferred choice for human experts for its high efficiency. However, conventional approaches are typically based on user-defined features such as movement onset times, peak velocities, motion vectors or frequency domain analyses. Such approaches entail careful data post-processing or specific domain knowledge to achieve a meaningful feature extraction. Besides, they are prone to noise and the manual-defined features could hardly be re-used for other analyses. In this paper, we proposed probabilistic movement primitives(ProMPs), a widely-used approach in robot skill learning, to model human motions. The benefit of ProMPs is that the features are directly learned from the data and ProMPs can capture important features describing the trajectory shape, which can easily be extended to other tasks. Distinct from previous research, where classification tasks are mostly investigated, we applied ProMPs together with a variant of Kullback-Leibler (KL) divergence to quantify the effect of different transcranial current stimulation methods on human motions. We presented an initial result with10participants. The results validate ProMPs as a robust and effective feature extractor for human motions. |  |
Cansev, Mehmet Ege; Xue, Honghu; Rottmann, Nils; Bliek, Adna; Miller, Luke E.; Rueckert, Elmar; Beckerle, Philipp Interactive Human-Robot Skill Transfer: A Review of Learning Methods and User Experience Journal Article In: Advanced Intelligent Systems, pp. 1–28, 2021. @article{Cansev2021,
title = {Interactive Human-Robot Skill Transfer: A Review of Learning Methods and User Experience},
author = {Mehmet Ege Cansev and Honghu Xue and Nils Rottmann and Adna Bliek and Luke E. Miller and Elmar Rueckert and Philipp Beckerle},
url = {https://cps.unileoben.ac.at/wp/AIS2021Cansev.pdf, Article File},
doi = {10.1002/aisy.202000247},
year = {2021},
date = {2021-03-10},
journal = {Advanced Intelligent Systems},
pages = {1--28},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|  |
2020
|
Akbulut, M Tuluhan; Oztop, Erhan; Seker, M Yunus; Xue, Honghu; Tekden, Ahmet E; Ugur, Emre ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing Proceedings Article In: 2020. @inproceedings{nokey,
title = {ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing},
author = {M Tuluhan Akbulut and Erhan Oztop and M Yunus Seker and Honghu Xue and Ahmet E Tekden and Emre Ugur},
url = {https://cps.unileoben.ac.at/wp/CoRL2020Akbulut.pdf},
year = {2020},
date = {2020-11-20},
urldate = {2020-11-20},
abstract = {To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL). In this paper, we propose a novel LfD+RL framework, namely Adaptive Conditional Neural Movement Primitives (ACNMP), that allows efficient policy improvement in novel environments and effective skill transfer between different agents. This is achieved through exploiting the latent representation learned by the underlying Conditional Neural Process (CNP) model, and simultaneous training of the model with supervised learning (SL) for acquiring the demonstrated trajectories and via RL for new trajectory discovery. Through simulation experiments, we show that (i) ACNMP enables the system to extrapolate to situations where pure LfD fails; (ii) Simultaneous training of the system through SL and RL preserves the shape of demonstrations while adapting to novel situations due to the shared representations used by both learners; (iii) ACNMP enables order-of-magnitude sample-efficient RL in extrapolation of reaching tasks compared to the existing approaches; (iv) ACNMPs can be used to implement skill transfer between robots having different morphology, with competitive learning speeds and importantly with less number of assumptions compared to the state-of-the-art approaches. Finally, we show the real-world suitability of ACNMPs through real robot experiments that involve obstacle avoidance, pick and place and pouring actions.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL). In this paper, we propose a novel LfD+RL framework, namely Adaptive Conditional Neural Movement Primitives (ACNMP), that allows efficient policy improvement in novel environments and effective skill transfer between different agents. This is achieved through exploiting the latent representation learned by the underlying Conditional Neural Process (CNP) model, and simultaneous training of the model with supervised learning (SL) for acquiring the demonstrated trajectories and via RL for new trajectory discovery. Through simulation experiments, we show that (i) ACNMP enables the system to extrapolate to situations where pure LfD fails; (ii) Simultaneous training of the system through SL and RL preserves the shape of demonstrations while adapting to novel situations due to the shared representations used by both learners; (iii) ACNMP enables order-of-magnitude sample-efficient RL in extrapolation of reaching tasks compared to the existing approaches; (iv) ACNMPs can be used to implement skill transfer between robots having different morphology, with competitive learning speeds and importantly with less number of assumptions compared to the state-of-the-art approaches. Finally, we show the real-world suitability of ACNMPs through real robot experiments that involve obstacle avoidance, pick and place and pouring actions. |  |
Rottmann, N.; Bruder, R.; Xue, H.; Schweikard, A.; Rueckert, E. Parameter Optimization for Loop Closure Detection in Closed Environments Proceedings Article In: Workshop Paper at the International Conference on Intelligent Robots and Systems (IROS), pp. 1–8, 2020. @inproceedings{Rottmann2020c,
title = {Parameter Optimization for Loop Closure Detection in Closed Environments},
author = {N. Rottmann and R. Bruder and H. Xue and A. Schweikard and E. Rueckert},
url = {https://cps.unileoben.ac.at/wp/IROSWS2020Rottmann.pdf, Article File},
year = {2020},
date = {2020-10-25},
booktitle = {Workshop Paper at the International Conference on Intelligent Robots and Systems (IROS)},
pages = {1--8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|  |
Xue, H.; Boettger, S.; Rottmann, N.; Pandya, H.; Bruder, R.; Neumann, G.; Schweikard, A.; Rueckert, E. Sample-Efficient Covariance Matrix Adaptation Evolutional Strategy via Simulated Rollouts in Neural Networks Proceedings Article In: International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI’ 2020), 2020. @inproceedings{Xue2020,
title = {Sample-Efficient Covariance Matrix Adaptation Evolutional Strategy via Simulated Rollouts in Neural Networks},
author = {H. Xue and S. Boettger and N. Rottmann and H. Pandya and R. Bruder and G. Neumann and A. Schweikard and E. Rueckert},
url = {https://cps.unileoben.ac.at/wp/ASPAI2020Xue.pdf, Article File},
year = {2020},
date = {2020-06-30},
booktitle = {International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI’ 2020)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|  |
