检索结果-内蒙古大学图书馆

Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Yu Zhang, Yuexin Li, Kunming Qiao, Yongliang Worrall, Stewart Li, You-Fu Kong, He Shenzhen518055 China Department of Mechanical Engineering City University of Hong Kong Hong Kong School of Automation Guangdong Polytechnic Normal University Guangzhou510665 China Australian Centre for Field Robotics The University of Sydney NSW2006 Australia Australian Institute for Machine Learning The University of Adelaide SA5005 Australia Shenzhen Key Laboratory of Control Theory and Intelligent Systems SUSTech Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities SUSTech Shenzhen518055 China

Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different environments. For training, recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians, among others. This can limit the prediction performance across various scenarios since the discrepancies between training datasets have not been properly incorporated. To overcome this limitation, this paper proposes a graph transformer structure to improve prediction performance, capturing the differences between the various sites and scenarios contained in the datasets. In particular, a self-attention mechanism and a domain adaption module have been designed to improve the generalization ability of the model. Moreover, an additional metric considering crossdataset sequences is introduced for training and performance evaluation purposes. The proposed framework is validated and compared against existing methods using popular public datasets, i.e., ETH and UCY. Experimental results demonstrate the improved performance of our proposed scheme. © 2024, CC BY.

关键词： Trajectories

Low-Tubal-Rank Tensor Recovery via Factorized Gradient Descent

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Zhiyu Han, Zhi Tang, Yandong Zhao, Xi-Le Wang, Yao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China University of Electronic Science and Technology of China Chengdu610051 China Center for Intelligent Decision-making and Machine Learning School of Management Xi’an Jiaotong University Xi’an710049 China

This paper considers the problem of recovering a tensor with an underlying low-tubal-rank structure from a small number of corrupted linear measurements. Traditional approaches tackling such a problem require the computation of tensor Singular Value Decomposition (t-SVD), which is a computationally intensive process, rendering them impractical for dealing with large-scale tensors. Aiming to address this challenge, we propose an efficient and effective low-tubal-rank tensor recovery method based on a factorization procedure akin to the Burer-Monteiro (BM) method. Precisely, our fundamental approach involves decomposing a large tensor into two smaller factor tensors, followed by solving the problem through factorized gradient descent (FGD). This strategy eliminates the need for t-SVD computation, thereby reducing computational costs and storage requirements. We provide rigorous theoretical analysis to ensure the convergence of FGD under both noise-free and noisy situations. Additionally, it is worth noting that our method does not require the precise estimation of the tensor tubal-rank. Even in cases where the tubal-rank is slightly overestimated, our approach continues to demonstrate robust performance. A series of experiments have been carried out to demonstrate that, as compared to other popular ones, our approach exhibits superior performance in multiple scenarios, in terms of the faster computational speed and the smaller convergence error. Copyright © 2024, The Authors. All rights reserved.

关键词： Singular value decomposition

Predicting Dense and Context-aware Cost Maps for Semantic Robot Navigation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Goel, Yash Vaskevicius, Narunas Palmieri, Luigi Chebrolu, Nived Stachniss, Cyrill The laboratory for Photogrammetry and Robotics University of Bonn Germany Robert Bosch GmbH Germany Robert Bosch GmbH Corporate Research Stuttgart Germany The Dynamic Robot Systems Group University of Oxford United Kingdom The University of Bonn Germany The Department of Engineering Science the University of Oxford United Kingdom The Lamarr Institute for Machine Learning and Artificial Intelligence Germany

We investigate the task of object goal navigation in unknown environments where the target is specified by a semantic label (e.g. find a couch). Such a navigation task is especially challenging as it requires understanding of semantic context in diverse settings. Most of the prior work tackles this problem under the assumption of a discrete action policy whereas we present an approach with continuous control which brings it closer to real world applications. We propose a deep neural network architecture and loss function to predict dense cost maps that implicitly contain semantic context and guide the robot towards the semantic goal. We also present a novel way of fusing mid-level visual representations in our architecture to provide additional semantic cues for cost map prediction. The estimated cost maps are then used by a sampling-based model predictive controller (MPC) for generating continuous robot actions. The preliminary experiments suggest that the cost maps generated by our network are suitable for the MPC and can guide the agent to the semantic goal more efficiently than a baseline approach. The results also indicate the importance of mid-level representations for navigation by improving the success rate by 7 percentage points. Copyright © 2022, The Authors. All rights reserved.

关键词： Navigation

Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction

学校读者我要写书评

暂无评论

Knowledge-aware Graph Transformer for Pedestrian Trajectory ...

International Conference on Intelligent Transportation

作者： Yu Liu Yuexin Zhang Kunming Li Yongliang Qiao Stewart Worrall You-Fu Li He Kong Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology (SUSTech) Shenzhen China Department of Mechanical Engineering City University of Hong Kong Hong Kong SAR China School of Automation Guangdong Polytechnic Normal University Guangzhou China Australian Centre for Field Robotics The University of Sydney NSW Australia Australian Institute for Machine Learning The University of Adelaide SA Australia Department of Mechanical Engineering City University of Hong Kong Hong Kong SAR China Shenzhen Key Laboratory of Control Theory and Intelligent Systems SUSTech Shenzhen China Guangdong Provincial Key Laboratory of Human-Augmentation Rehabilitation Robotics in Universities SUSTech Shenzhen China

Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different environments. For training, recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians, among others. This can limit the prediction performance across various scenarios since the discrepancies between training datasets have not been properly incorporated. To overcome this limitation, this paper proposes a graph transformer structure to improve prediction performance, capturing the differences between the various sites and scenarios contained in the datasets. In particular, a self-attention mechanism and a domain adaption module have been designed to improve the generalization ability of the model. Moreover, an additional metric considering cross-dataset sequences is introduced for training and performance evaluation purposes. The proposed framework is validated and compared against existing methods using popular public datasets, i.e., ETH and UCY. Experimental results demonstrate the improved performance of our proposed scheme.

关键词：

EXPOSURE-BASED MULTI-AGENT INSPECTION OF A TUMBLING TARGET USING DEEP REINFORCEMENT learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Aurand, Joshua Cutlip, Steven Lei, Henry Lang, Kendra Phillips, Sean Machine Learning Engineer - Robotics Verus Research 6100 Uptown Blvd NE AlbuquerqueNM87110 United States Research Engineer - Controls Verus Research United States Software Controls Engineer Verus Research United States Technical Director - Space and Autonomy Verus Research United States Research Mechanical Engineer Air Force Research Laboratory Space Vehicles Directorate Kirtland AFB NM United States

As space becomes more congested, on-orbit inspection is an increasingly relevant activity whether to observe a defunct satellite for planning repairs or to de-orbit it. However, the task of on-orbit inspection itself is challenging, typically requiring the careful coordination of multiple observer satellites. This is complicated by a highly nonlinear environment where the target may be unknown or moving unpredictably without time for continuous command and control from the ground. There is a need for autonomous, robust, decentralized solutions to the inspection task. To achieve this, we consider a hierarchical, learned approach for the decentralized planning of multi-agent inspection of a tumbling target. Our solution consists of two components: a viewpoint or high-level planner trained using deep reinforcement learning and a navigation planner handling point-to-point navigation between pre-specified viewpoints. We present a novel problem formulation and methodology that is suitable not only to reinforcement learning-derived robust policies, but extendable to unknown target geometries and higher fidelity information theoretic objectives received directly from sensor inputs. Operating under limited information, our trained multi-agent high-level policies successfully contextualize information within the global hierarchical environment and are correspondingly able to inspect over 90% of non-convex tumbling targets, even in the absence of additional agent attitude control. © 2023, CC BY-NC-ND.

关键词： Reinforcement learning

Neuromorphic system development based on adaptive neuronal network to modulate synaptic transmission in hippocampus 3

学校读者我要写书评

暂无评论

Neuromorphic system development based on adaptive neuronal n...

3rd International Conference "Neurotechnologies and Neurointerfaces", CNN 2021

作者： Lebedeva, Albina Gerasimova, Svetlana Fedulina, Anastasiya Mishchenko, Mikhail Beltyukova, Anna Matveeva, Mariya Mikhaylov, Alexey Pisarchik, Alexander Kazantsev, Victor Neurotechnologies Department N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Physics and Technology of Thin Films Department of Solid State Electronics and Optoelectronics Research Institute of Physics and Technology N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Department of Theory of Oscillations and Automatic Control Faculty of Radiophysics N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Center for Biomedical Technology Technical University of Madrid Pozuelo de Alarcón Madrid Spain Center for Technologies in Robotics and Mechatronics Component Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665424745

The project presents fundamental research on the development of concept and basic components of physical circuit based on optoelectronic elements (neuromorphic generators, memristors, optical fibers). This network can replace some functions of brain’s neural networks (such as memory) through adaptive stimulation of neural interfaces at the cellular and cellular networks level. Developing learning system will perform the electrical stimulation of brain areas based on the neural activity recorded and will include electronic devices for recording and processing signals. In addition, this system will include electronic devices for generating electrical stimuli based on hardware models of neurons and memristive devices. The basic idea is to integrate an artificial network with living microcircuits of the brain. The artificial network is capable of adaptively generating electrical output signals and can stimulate a given area of the brain according to the recorded pattern of input signals. We suppose that such a network will be able to reproduce the functions of brain systems, based on the use of learning algorithms. It can be used to expand the functionality of these brain systems and to replace lost functions in pathology or trauma. © 2021 IEEE.

关键词： Memristors

Flexible disaster response of tomorrow final presentation and evaluation of the CENTAURO system

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Klamt, Tobias Rodriguez, Diego Baccelliere, Lorenzo Chen, Xi Chiaradia, Domenico Cichon, Torben Gabardi, Maßimiliano Guria, Paolo Holmquist, Karl Kamedula, Malgorzata Karaoguz, Hakan Kashiri, Navvab Laurenzi, Arturo Lenz, Christian Leonardis, Daniele Hoffman, Enrico Mingo Muratore, Luca Pavlichenko, Dmytro Porcini, Francesco Ren, Zeyu Schilling, Fabian Schwarz, Max Solazzi, Maßimiliano Felsberg, Michael Frisoli, Antonio Gustmann, Michael Jensfelt, Patric Nordberg, Klas Roßmann, Jürgen Süß, Uwe Tsagarakis, Nikos G. Behnke, Sven Autonomous Intelligent Systems University of Bonn Germany Humanoids and Human-Centred Mechatronics Istituto Italiano di Tecnologia Genoa Italy Department of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden PERCRO Laboratory TeCIP Institute Sant'Anna School of Advanced Studies Pisa Italy Institute for Man-Machine Interaction RWTH Aachen University Germany Computer Vision Laboratory Linköping University Sweden Lausanne Switzerland Kerntechnische Hilfsdienst GmbH Karlsruhe Germany School of Electrical and Electronic Engineering University of Manchester United Kingdom

Spatial computing in structured spiking neural networks with a robotic embodiment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lobov, Sergey A. Mikhaylov, Alexey N. Berdnikova, Ekaterina S. Makarov, Valeri A. Kazantsev, Victor B. Lobachevsky State University of Nizhny Novgorod Gagarin Ave. 23 Nizhny Novgorod603950 Russia Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Universitetskaya Str. 1 Innopolis420500 Russia Center For Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia Instituto de Matemática Interdisciplinar F. de Ciencias Matemáticas Universidad Complutense de Madrid Madrid28040 Spain

One of the challenges of modern neurosciwence is creating a "living computer" based on neural networks grown in vitro. Such an artificial device is supposed to perform neurocomputational tasks and interact with the environment when embodied in a robot. Recent studies have identified the most critical challenge, the search for a neural network architecture to implement associative learning. This work proposes a model of modular architecture with spiking neural networks connected by unidirectional couplings. We show that the model enables training a neuro-robot according to Pavlovian conditioning. The robot's performance in obstacle avoidance depends on the ratio of the weights in inter-network couplings. We show that besides STDP, critical factors for successful learning are synaptic and neuronal competitions. We use the recently discovered shortest path rule to implement the synaptic competition. This method is ready for experimental testing. Strong inhibitory couplings implement the neuronal competition in the subnetwork responsible for the unconditional response. Empirical testing of this approach requires a technique for growing neural networks with a given ratio of excitatory and inhibitory neurons not available yet. An alternative is building a hybrid system with in vitro neural networks coupled through hardware memristive connections. © 2021, CC BY.

关键词： Neural networks

Novel 3D game-like applications driven by body interactions for learning specific forms of intangible cultural heritage 10

学校读者我要写书评

暂无评论

Novel 3D game-like applications driven by body interactions ...

10th International Conference on Computer Vision Theory and Applications, VISAPP 2015

作者： Yilmaz, E. Uʇurca, D. Şahin, C. Dagnino, F.M. Ott, M. Pozzi, F. Dimitropoulos, K. Tsalakanidou, F. Kitsikidis, A. Al Kork, S.K. Xu, K. Denby, B. Roussel, P. Chawah, P. Buchman, L. Adda-Decker, M. Dupont, S. Picart, B. Tilmanne, J. Alivizatou, M. Hadjileontiadis, L. Charisis, V. Glushkova, A. Volioti, C. Manitsaris, A. Hemery, E. Moutarde, F. Grammalidis, N. Argedor Information Technologies Ankara Turkey Palermo Italy Information Technologies Institute Centre for Research and Technology Hellas Thessaloniki Greece Universite Pierre et Marie Curie - Paris 6 Paris France University Paris 3 Sorbonne Nouvelle Paris France Centre National de la Recherche Scientifique Laboratoire de Phonétique et Phonologie UMR 7018 Paris France Phonetics and Phonology Laboratory LPP-CNRS Paris France Universite de Mons Mons Belgium University College London London United Kingdom Aristotle University of Thessaloniki Thessaloniki Greece MTCG Lab. Dep. of Ap. Informatics University of Macedonia Thessaloniki Greece Robotics Lab. Dep. of Mathématiques et Systèmes MINES ParisTech-ARMINES Paris France Signal Processing and Machine Learning Lab. ESPCI Paris France

ISBN: (纸本)9789897580901

The main objective of the EU FP7 ICT i-Treasures project is to build a public and expandable platform to enable learning and transmission of rare know-how of intangible cultural heritage. A core part of this platform consists of game-like applications able to support teaching and learning processes in the ICH field. We have designed and developed four game-like applications (for Human Beat Box singing, Tsamiko dancing, pottery making and contemporary music composition), each corresponding to one of the ICH use cases of i-Treasures project. A first preliminary version of these applications is currently available for further validation, evaluation and demonstration within the project. We have encountered a number of issues, most of which derive from the peculiarities of the ICH domains addressed by the project, and many have already been resolved / The evaluation results are expected to lead to further optimization of these games.

关键词： Human computer interaction