Filters








29,975 Hits in 7.9 sec

Simultaneous Optimization and Sampling of Agent Trajectories over a Network [chapter]

Hala Mostafa, Akshat Kumar, Hoong Chuin Lau
2016 Lecture Notes in Computer Science  
We study the problem of optimizing the trajectories of agents moving over a network given their preferences over which nodes to visit subject to operational constraints on the network.  ...  Our main contribution is a mathematical program that simultaneously optimizes decision variables and implements inverse transform sampling from the distribution they induce.  ...  Conclusion In this paper we addressed decision making in settings where movement of agents in a network is affected by both the agents inherent preferences and the actions of the network manager.  ... 
doi:10.1007/978-3-319-46840-2_4 fatcat:mrq6t4cf3zbspj6cbe5wrghrwm

Adaptive Information Collection by Robotic Sensor Networks for Spatial Estimation

Rishi Graham, Jorge Cortes
2012 IEEE Transactions on Automatic Control  
We examine the optimal sampling problem of minimizing the maximum predictive variance of the estimator over the space of network trajectories.  ...  This work deals with trajectory optimization for a robotic sensor network sampling a spatio-temporal random field.  ...  Finally, we combine individual agent trajectories into a network trajectory to find the constrained optimizers of H W . A.  ... 
doi:10.1109/tac.2011.2178332 fatcat:6imlgnjvzjhslhhhpborj4h2jy

Sampled-Data Consensus for High-Order Multiagent Systems under Fixed and Randomly Switching Topology

Niu Jie, Li Zhong
2014 Discrete Dynamics in Nature and Society  
by solving theH∞optimal control problem of certain system with uncertainty.  ...  For systems under fixed topology, a necessary and sufficient sampling period bound is obtained for single-input multiagent systems, and a sufficient allowable bound is proposed for multi-input systems  ...  Conflict of Interests The authors declare that there is no conflict of interests regarding the publication of this paper.  ... 
doi:10.1155/2014/598965 fatcat:vw7u34dslbeqzm7idwidzud4km

Proximal Policy Optimization with Mixed Distributed Training [article]

Zhenyu Zhang, Xiangfeng Luo, Tong Liu, Shaorong Xie, Jianshu Wang, Wei Wang, Yang Li, Yan Peng
2019 arXiv   pre-print
Actions are sampled by each policy separately as usual, but the trajectories for the training process are collected from all agents, instead of only one policy.  ...  In our algorithm, multiple different policies train simultaneously and each of them controls several identical agents that interact with environments.  ...  U1813217), and the project of the Intelligent Ship Situation Awareness System.  ... 
arXiv:1907.06479v3 fatcat:6gm3ibfvpbftxine3rhpde3raa

Global Pose Estimation with an Attention-Based Recurrent Network

Emilio Parisotto, Devendra Singh Chaplot, Jian Zhang, Ruslan Salakhutdinov
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
For unknown environments, Simultaneous Localization and Mapping (SLAM) enables incremental and concurrent building of and localizing within a map.  ...  We present a new, differentiable architecture, Neural Graph Optimizer, progressing towards a complete neural network solution for SLAM by designing a system composed of a local pose estimation model, a  ...  Acknowledgments We thank Tim Barfoot and Russ Webb for helpful comments and discussions. We would also like to thank Barry Theobald and Megan Maher for helpful feedback on the manuscript.  ... 
doi:10.1109/cvprw.2018.00061 dblp:conf/cvpr/ParisottoCZS18 fatcat:h6n4ob3ygvaknmfkajwwdwfixm

Global Pose Estimation with an Attention-based Recurrent Network [article]

Emilio Parisotto, Devendra Singh Chaplot, Jian Zhang, Ruslan Salakhutdinov
2018 arXiv   pre-print
For unknown environments, Simultaneous Localization and Mapping (SLAM) enables incremental and concurrent building of and localizing within a map.  ...  We present a new, differentiable architecture, Neural Graph Optimizer, progressing towards a complete neural network solution for SLAM by designing a system composed of a local pose estimation model, a  ...  Acknowledgments We thank Tim Barfoot and Russ Webb for helpful comments and discussions. We would also like to thank Barry Theobald and Megan Maher for helpful feedback on the manuscript.  ... 
arXiv:1802.06857v1 fatcat:qhcxgjgxgbe73a73xqsyloqqji

Multi-Agent Tensor Fusion for Contextual Trajectory Prediction

Tianyang Zhao, Yifei Xu, Mathew Monfort, Wongun Choi, Chris Baker, Yibiao Zhao, Yizhou Wang, Ying Nian Wu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This work was mainly conducted at ISEE, Inc. with the support of the ISEE team and ISEE data platform. This work was supported in part by NSFC-61625201, 61527804.  ...  We use conditional generative adversarial training [12, 23] to capture this uncertainty over predicted trajectories, representing the distribution over trajectories with a finite set of samples.  ...  These networks are simultaneously trained in a two player minmax game framework.  ... 
doi:10.1109/cvpr.2019.01240 dblp:conf/cvpr/ZhaoXMCBZ0W19 fatcat:faif52n3rnelpgr2d4lhcopw2e

Trajectory Based Prioritized Double Experience Buffer for Sample-Efficient Policy Optimization

Shengxiang Li, Ou Li, Guangyi Liu, Siyuan Ding, Yijie Bai
2021 IEEE Access  
This paper introduces a novel policy gradient method to improve the sample efficiency via a pair of trajectory based prioritized replay buffers and reduce the variance in training with a target network  ...  Reinforcement learning has recently made great progress in various challenging domains such as board game of Go and MOBA game of StarCraft II.  ...  The agent samples actions from its policy to interact with the environment, generating a trajectory that consists of states, actions, and rewards.  ... 
doi:10.1109/access.2021.3097357 fatcat:evq3kgrsxnfm3cjnvwpbutw7mu

Inferring mobile trajectories using a network of binary proximity sensors

Eunjoon Cho, Kevin Wong, Omprakash Gnawali, Martin Wicke, Leonidas Guibas
2011 2011 8th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks  
In our work, we show that we can use a network of binary proximity sensors to detect paths between nodes and also extract highly popular trajectories users take.  ...  We have tested our algorithm on a simulator and two sensor network deployments.  ...  ACKNOWLEDGMENTS We gratefully acknowledge the support from the Stanford Army High Performance Computing Research Center grant W911NF-07-2-0027, ARO grant W911NF-10-1-0037, ONR grant N0001470710747, and  ... 
doi:10.1109/sahcn.2011.5984896 dblp:conf/secon/ChoWGWG11 fatcat:rq2w4bcwxjhs5ldruyoue3nwby

Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior [article]

Davis Rempe, Jonah Philion, Leonidas J. Guibas, Sanja Fidler, Or Litany
2022 arXiv   pre-print
We additionally "close the loop" and use these scenarios to optimize hyperparameters of a rule-based planner.  ...  Scenario generation is formulated as an optimization in the latent space of this traffic model, perturbing an initial real-world scene to produce trajectories that collide with a given planner.  ...  Author Guibas was supported by a Vannevar Bush faculty fellowship. The authors thank Amlan Kar for the fruitful discussion and feedback throughout the project.  ... 
arXiv:2112.05077v2 fatcat:ngubklppybgnxgzopxdx4jboim

Multi-Agent Imitation Learning for Driving Simulation [article]

Raunak P. Bhattacharyya, Derek J. Phillips, Blake Wulfe, Jeremy Morton, Alex Kuefler, Mykel J. Kochenderfer
2018 arXiv   pre-print
Compared with single-agent GAIL policies, policies generated by our PS-GAIL method prove superior at interacting stably in a multi-agent setting and capturing the emergent behavior of human drivers.  ...  This difference makes such models unsuitable for the simulation of driving scenes, where multiple agents must interact realistically over long time horizons.  ...  ACKNOWLEDGMENTS Toyota Research Institute (TRI) provided funds to assist the authors with their research, but this article solely reflects the opinions and conclusions of its authors and not TRI or any  ... 
arXiv:1803.01044v1 fatcat:c7x7bbxcejh7ddtxdfockkojcq

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning [article]

Kei Ota, Devesh K. Jha, Tomoaki Oiki, Mamoru Miura, Takashi Nammoto, Daniel Nikovski, Toshisada Mariyama
2020 arXiv   pre-print
Our experiments show that our RL agent trained with a reference path outperformed a model-free PID controller of the type commonly used on many robotic platforms for trajectory tracking.  ...  In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems.  ...  We assume that the target state g is sampled from the set G. We train a single network to maximize the expected discounted reward over multiple goal states.  ... 
arXiv:1903.05751v2 fatcat:lnysxjuavnbrzbtmohi43xvakq

Energy-Based Continuous Inverse Optimal Control [article]

Yifei Xu, Jianwen Xie, Tianyang Zhao, Chris Baker, Yibiao Zhao, Ying Nian Wu
2022 arXiv   pre-print
Moreover, to make the sampling or optimization more efficient, we propose to train the energy-based model simultaneously with a top-down trajectory generator via cooperative learning, where the trajectory  ...  The problem of continuous inverse optimal control (over finite time horizon) is to learn the unknown cost function over the sequence of continuous control variables from expert demonstrations.  ...  The controls of other vehicles are used to predict the trajectories of other vehicles. Suppose there are K agents, and every agent in the scene can be regarded as a general agent.  ... 
arXiv:1904.05453v6 fatcat:ai62xvl7fng6xip2ptjj63cruu

A Sensor-Network-Supported Mobile-Agent-Search Strategy for Wilderness Rescue

Shin, Kashino, Nejat, Benhabib
2019 Robotics  
This paper proposes a hybrid approach for target search utilizing a team of mobile agents supported by a network of static sensors.  ...  Namely, deployment locations and times are optimized while being constrained by the already planned mobile-agent trajectories.  ...  Figure 11 illustrates the complete initial plan of optimal agent trajectories and the static-sensor network.  ... 
doi:10.3390/robotics8030061 fatcat:5rdahboeczfd5mtqium6rsj7hu

Learning from Observations Using a Single Video Demonstration and Human Feedback [article]

Sunil Gandhi, Tim Oates, Tinoosh Mohsenin, Nicholas Waytowich
2019 arXiv   pre-print
In this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of  ...  network.  ...  ., training of the similarity network, optimization using reinforcement learning and collecting human feedback run simultaneously and asynchronously.  ... 
arXiv:1909.13392v1 fatcat:ij2liqtpt5b7hjosbdcic5npni
« Previous Showing results 1 — 15 out of 29,975 results