29,567 Hits in 4.9 sec

Socially Aware Motion Planning with Deep Reinforcement Learning [article]

Yu Fan Chen, Michael Everett, Miao Liu, Jonathan P. How
2018 arXiv   pre-print
Specifically, using deep reinforcement learning, this work develops a time-efficient navigation policy that respects common social norms.  ...  The proposed method is shown to enable fully autonomous navigation of a robotic vehicle moving at human walking speed in an environment with many pedestrians.  ...  APPROACH The following presents the socially aware multiagent collision avoidance with deep reinforcement learning algorithm (SA-CADRL).  ... 
arXiv:1703.08862v2 fatcat:7wus4z4h7zdghalta3z2x67ujy

Socially aware motion planning with deep reinforcement learning

Yu Fan Chen, Michael Everett, Miao Liu, Jonathan P. How
2017 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Specifically, using deep reinforcement learning, this work develops a time-efficient navigation policy that respects common social norms.  ...  The proposed method is shown to enable fully autonomous navigation of a robotic vehicle moving at human walking speed in an environment with many pedestrians.  ...  APPROACH The following presents the socially aware multiagent collision avoidance with deep reinforcement learning algorithm (SA-CADRL).  ... 
doi:10.1109/iros.2017.8202312 dblp:conf/iros/ChenELH17 fatcat:qzrgcqn5qzhefe4jzxto4c5uc4

Analysis of Social Robotic Navigation approaches: CNN Encoder and Incremental Learning as an alternative to Deep Reinforcement Learning [article]

Janderson Ferreira
2020 arXiv   pre-print
Dealing with social tasks in robotic scenarios is difficult, as having humans in the learning loop is incompatible with most of the state-of-the-art machine learning algorithms.  ...  This is the case when exploring Incremental learning models, in particular the ones involving reinforcement learning.  ...  Socially Aware Motion Collision Avoidance with Deep Reinforcement Learning Chen et al. developed a socially aware collision avoidance with deep reinforcement learning (SA-CADRL) model that aims to reproduce  ... 
arXiv:2008.07965v2 fatcat:6hwynr5prfa5lkvxagseqzdviq

Learning World Transition Model for Socially Aware Robot Navigation [article]

Yuxiang Cui, Haodong Zhang, Yue Wang, Rong Xiong
2020 arXiv   pre-print
We present a model-based reinforcement learning approach for robots to navigate through crowded environments.  ...  The navigation policy is trained with both real interaction data from multi-agent simulation and virtual data from a deep transition model that predicts the evolution of surrounding dynamics of mobile  ...  In this paper, we develop a framework of socially aware navigation policy training with model-based reinforcement learning using only 2D laser scans.  ... 
arXiv:2011.03922v1 fatcat:ki6buukqdfa6hjwtuot42d3i4i

Guest Editorial: Introduction to the Special Issue on Long-Term Human Motion Prediction

Luigi Palmieri, Rudenko Andrey, Jim Mainprice, Marc Hanheide, Alexandre Alahi, Achim Lilienthal, Kai O. Arras
2021 IEEE Robotics and Automation Letters  
He has worked on the theoretical challenges and practical applications of socially-aware Artificial intelligence, i.e., systems equipped with perception and social intelligence.  ...  The STRANDS, ILIAD, RASberry, and NCNR projects are among the bigger projects he is involved with.  ...  Kragic, "Human-centered collaborative robots with deep reinforcement learning," IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 566-571, 2021 . 8) P. Kratzer, S. Bihlmaier, N. B.  ... 
doi:10.1109/lra.2021.3077964 fatcat:2gzbhc3x7rgsloieovogcbo6gm

ICARSC 2020 Conference Program

2020 2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)  
, Luís Paulo Reis and Armando Sousa 9:39 Improving Local Motion Planning with a Reinforcement Learning Approach Luís Garrote, Diogo Temporão, Samuel Temporão, Ricardo Pereira, Tiago Barros and Urbano J  ...  Humanoid Robot Kick in Motion Ability for Playing Robotic Soccer Henrique Teixeira, Luís Paulo Reis, Tiago Silva and Miguel Abreu 10:57 Competitive Deep Reinforcement Learning over a Pokémon Battling Simulator  ... 
doi:10.1109/icarsc49921.2020.9096077 fatcat:mdwmiy25v5f5xc7nuagjyorf3u

Socially-Aware Multi-Agent Following with 2D Laser Scans via Deep Reinforcement Learning and Potential Field [article]

Yuxiang Cui, Xiaolong Huang, Yue Wang, Rong Xiong
2021 arXiv   pre-print
in advance, namely socially aware.  ...  The multi-agent following problem is tackled by utilizing the complementary strengths of both reinforcement learning and potential field, in which the reinforcement learning part handles local interactions  ...  Local Planning with Reinforcement Learning To evaluate the performance of the local planner, we test the learned policy in multiple social scenarios, results are shown in Tab. II.  ... 
arXiv:2109.01874v1 fatcat:4nbqyrdqkzbtzid46bfy5aob5i

Learning a Group-Aware Policy for Robot Navigation [article]

Kapil Katyal, Yuxiang Gao, Jared Markowitz, Sara Pohland, Corban Rivera, I-Jeng Wang, Chien-Ming Huang
2021 arXiv   pre-print
This paper explores learning group-aware navigation policies based on dynamic group formation using deep reinforcement learning.  ...  violation of social norms and discomfort, and reduce the robot's movement impact on pedestrians.  ...  Our approach utilizes deep reinforcement learning and considers group formation during training.  ... 
arXiv:2012.12291v2 fatcat:lzx6fwedjrfyrl5txlgxwnt6c4

Reinforcement Learning based Negotiation-aware Motion Planning of Autonomous Vehicles [article]

Zhitao Wang, Yuzheng Zhuang, Qiang Gu, Dong Chen, Hongbo Zhang, Wulong Liu
2021 arXiv   pre-print
This paper proposes a reinforcement learning based negotiation-aware motion planning framework, which adopts RL to adjust the driving style of the planner by dynamically modifying the prediction horizon  ...  length of the motion planner in real time adaptively w.r.t the event of a change in environment, typically triggered by traffic participants' switch of intents with different driving styles.  ...  In order to overcome the challenge, in this paper we propose a negotiation-aware planning framework that integrates reinforcement learning (RL) as a negotiation skill selector into motion planning.  ... 
arXiv:2107.03600v1 fatcat:tebaof5anzcd7dv6jp7eugznqu

Socially Aware Crowd Navigation with Multimodal Pedestrian Trajectory Prediction for Autonomous Vehicles [article]

Kunming Li, Mao Shan, Karan Narula, Stewart Worrall, Eduardo Nebot
2020 arXiv   pre-print
To overcome this problem, we propose a new method, SARL-SGAN-KCE, that combines a deep socially aware attentive value network with a human multimodal trajectory prediction model to help identify the optimal  ...  Recent work has demonstrated that reinforcement learning-based methods have the ability to learn to drive in crowds.  ...  Lei et al. present a learning-based, mapless motion planner using deep reinforcement learning [29] .  ... 
arXiv:2011.11191v1 fatcat:ztbum6eylbablhirlod4i3wd5e

Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans [article]

Jun Jin, Nhat M. Nguyen, Nazmus Sakib, Daniel Graves, Hengshuai Yao, Martin Jagersand
2020 arXiv   pre-print
We train the policy using reinforcement learning on a simple simulator and directly evaluate the learned policy in Gazebo and real robot tests.  ...  We observe that our method demonstrates time-efficient path planning behavior with high success rate in mapless navigation tasks.  ...  Recent works on deep reinforcement learning have proven the capability of using 2D laser scans in mapless navigation [2, 11] and multi-agent / dense crowd [12, 13] collision avoidance tasks.  ... 
arXiv:1911.03074v2 fatcat:trrsfsssorfbrhqhm5hvpzmujq

Learning Human-Aware Path Planning with Fully Convolutional Networks [article]

Noé Pérez-Higueras, Fernando Caballero, Luis Merino
2018 arXiv   pre-print
This work presents an approach to learn path planning for robot social navigation by demonstration.  ...  The approach is evaluated in experiments with real trajectories and compared with Inverse Reinforcement Learning algorithms that use RRT* as underlying planner.  ...  In [17] , a Reinforcement Learning approach is applied to develop a socially-aware collision avoidance system where a deep network is employed to learn multi-agent crossing trajectories.  ... 
arXiv:1803.00429v2 fatcat:e6pb5zdxzngpbhvcwqwx7nztge

Papers by title

2020 2020 7th NAFOSTED Conference on Information and Computer Science (NICS)  
Deep Reinforcement Learning Based Socially Aware Mobile Robot Navigation Framework Development of Warning and Predicting System for Quality of Air in Smart Cities Using RNNE A B C D E F G H I J L M O  ...  Low-Cost Cameras Using Deep Reinforcement Learning Multi-Branch Network with Dynamically Matching Algorithm in Pre-Identification O A B C D E F G H I J L M O P R S T U V On an Improvement of Graph  ... 
doi:10.1109/nics51282.2020.9335873 fatcat:jccrnlis2rdijbwayzrht4lskq

Editorial Special Issue on AI Innovations in Intelligent Transportation Systems

Tai-Hoon Kim
2022 IEEE transactions on intelligent transportation systems (Print)  
A deep reinforcement learning-based scheme is proposed for the scenario that the vehicles do not want to share personal information with other vehicles.  ...  In [A3] , Li et al. leverage a novel neural network-integrated with a heterogeneous attention mechanism to empower the policy in deep reinforcement learning to automatically select the nodes to address  ... 
doi:10.1109/tits.2022.3152067 fatcat:w5qyxfyp7zfzjckdkhsmddvzwm

DeepMoTIon: Learning to Navigate Like Humans [article]

Mahmoud Hamandi, Mike D'Arcy, Pooyan Fazli
2019 arXiv   pre-print
We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds.  ...  In addition, while many other approaches often failed to reach the target, our method reached the target in 100% of the test cases while complying with social norms and ensuring human safety.  ...  With the absence of a true model, learning the reward governing human motion is not feasible with current Inverse Reinforcement Learning algorithms such as the one presented in [20] .  ... 
arXiv:1803.03719v3 fatcat:kdemg64jl5ezngoyzfd55lhgzy
« Previous Showing results 1 — 15 out of 29,567 results