Filters








41,401 Hits in 4.9 sec

Introduction to the Special Issue on AI for Long-Term Autonomy

L. Kunze, N. Hawes, T. Duckett, M. Hanheide
2018 IEEE Robotics and Automation Letters  
Perception Pre-trained detectors and classifiers are usually used to allow a robot to perceive the objects in its environment.  ...  [2] , who employ Gaussian Processes in order to interactively learn local navigation recovery behaviours for mobile robots.  ... 
doi:10.1109/lra.2018.2870466 fatcat:x3clfqrgdfde3agslkoqahyzi4

Autonomous Car

Aniket Naik
2019 International Journal for Research in Applied Science and Engineering Technology  
Car following and decision making are critical to complete driving mission for autonomous vehicles under complex and dynamic urban environment.  ...  Autonomous car is a rapidly evolving technology, and today many auto makers and other technical companies are experimenting with autonomous cars.  ...  For an autonomous car to move from point A to point B, it needs to perform a series of steps: the car needs to perceive and make itself aware of the surrounding environment, plan the trip, navigate, and  ... 
doi:10.22214/ijraset.2019.4392 fatcat:jzpqtbufnrdq7iutyu67syj2sy

An Overview of Perception and Decision-Making in Autonomous Systems in the Era of Learning [article]

Yang Tang, Chaoqiang Zhao, Jianrui Wang, Chongzhen Zhang, Qiyu Sun, Weixing Zheng, Wenli Du, Feng Qian, Juergen Kurths
2020 arXiv   pre-print
have surfaced with respect to autonomous perception and decision-making.  ...  learning-based monocular depth estimation, ego-motion prediction, image enhancement, object detection, semantic segmentation, and their combinations with traditional SLAM frameworks.  ...  Meanwhile, navigation based on reinforcement learning also provides a new idea for decision-making in autonomous systems.  ... 
arXiv:2001.02319v3 fatcat:z3zhp2cyonfqtlttl2y57572uy

Vision Aided Navigation of a Quad-Rotor for Autonomous Wind-Farm Inspection

Petar Durdevic, Daniel Ortiz-Arroyo, Shaobao Li, Zhenyu Yang
2019 IFAC-PapersOnLine  
This work presents a vision based navigation system for an autonomous drone that is capable of recognizing and locating wind mills.  ...  Abstract: This work presents a vision based navigation system for an autonomous drone that is capable of recognizing and locating wind mills.  ...  This will allow us to navigate autonomously to a wind mill, independent of the initial position of the drone.  ... 
doi:10.1016/j.ifacol.2019.08.049 fatcat:geekel7xirg4dftt6cjtgnwocu

A MULTI-AGENT REINFORCEMENT LEARNING FRAMEWORK FOR INTELLIGENT MANUFACTURING WITH AUTONOMOUS MOBILE ROBOTS

Akash Agrawal, Sung Jun Won, Tushar Sharma, Mayuri Deshpande, Christopher McComb
2021 Proceedings of the Design Society  
This work offers a standardizing framework for integrated job scheduling and navigation control in an autonomous mobile robot driven shop floor, an increasingly common IM paradigm.  ...  Moreover, we observe nuanced behavior, including the ability to autonomously compensate for processing delays, and machine and robot failures in real time.  ...  In addition, incorporating visual sensors with convolutional neural network-based approaches for object detection and long short-term memory networks for mapless navigation could lead to more robust navigation  ... 
doi:10.1017/pds.2021.17 fatcat:bjoy4jmoaffwvdundqzi3b4e5e

A Survey of Deep Learning Techniques for Mobile Robot Applications [article]

Jahanzaib Shabbir, Tarique Anwer
2018 arXiv   pre-print
This research survey will present a summarization of the current research with a specific focus on the gains and obstacles for deep learning to be applied to mobile robotics.  ...  Advancements in deep learning over the years have attracted research into how deep artificial neural networks can be used in robotic systems.  ...  SEMI-SUPERVISED AND SELF-SUPERVISED LEARNING FOR ROBOTICS Imitation based learning is a promising approach to tackling the difficult robotic assignments, for instance, autonomous navigation.  ... 
arXiv:1803.07608v1 fatcat:edwca3yd5fhcri3zkfdfg2o2ju

COMPASS: Contrastive Multimodal Pretraining for Autonomous Systems [article]

Shuang Ma, Sai Vemprala, Wenshan Wang, Jayesh K. Gupta, Yale Song, Daniel McDuff, Ashish Kapoor
2022 arXiv   pre-print
Learning representations that generalize across tasks and domains is challenging yet necessary for autonomous systems.  ...  spaces arising from different tasks in different environments.We introduce the first general-purpose pretraining pipeline, COntrastive Multimodal Pretraining for AutonomouS Systems (COMPASS), to overcome  ...  We would also like to thank Weijian Xu for helping generate data for the drone navigation task.  ... 
arXiv:2203.15788v1 fatcat:h63bun4lxbhh3pomk5ex6cvypq

Incorporating Reactive Learning Behaviour into a Mini-robot Platform [chapter]

Mark Elshaw, Debra Lewis, Stefan Wermter
2004 Research and Development in Intelligent Systems XX  
By developing a fly-catcher robot scenario using a mini-robot platform it was possible to consider the incorporation of learned intelligent behaviour for navigation and the use of object recognition.  ...  This work offers an insight for robot uses into issues associated with intelligent learning on mini-robots that are also applicable to those using more sophisticated robots.  ...  Acknowledgements We would like to thank the following members of the Centre for Hybrid Intelligent Systems for their help with this paper Sheila Garfield, John Murray and Cornelius Weber.  ... 
doi:10.1007/978-0-85729-412-8_19 dblp:conf/sgai/ElshawLW03 fatcat:jmddwz2gkvegvjqrofdic4l224

Collision Avoidance in Unstructured Environments for Autonomous Robots: A Behavioural Modelling Approach

Chika O. Yinka-Banjo, Isaac O. Osunmakinde, Antoine Bagula
2011 Advanced Materials Research  
This reasoning ability enables autonomous robots to navigate in any unstructured environment with a higher degree of belief that there will be no collision with obstacles.  ...  Collision avoidance is one of the important safety key operations that needs attention in the navigation system of an autonomous robot.  ...  This provides the experimental results for an obstacle avoidance model when an autonomous robot navigates in a new environment while perceiving new obstacles' distances.  ... 
doi:10.4028/www.scientific.net/amr.403-408.3559 fatcat:eyrrxhycy5fjti35cjtqenkaga

Why did the Robot Cross the Road? - Learning from Multi-Modal Sensor Data for Autonomous Road Crossing [article]

Noha Radwan, Wera Winterhalter, Christian Dornhege, Wolfram Burgard
2017 arXiv   pre-print
In this work, we propose a novel multi-modal learning approach for the problem of autonomous street crossing.  ...  We consider the problem of developing robots that navigate like pedestrians on sidewalks through city centers for performing various tasks including delivery and surveillance.  ...  One of the key requirements for such robots is to properly perceive their environment.  ... 
arXiv:1709.06039v1 fatcat:5cpxarxpnbguxolqny6hjmljry

Artificial Life Simulation of Humans and Lower Animals: From Biomechanics to Intelligence [chapter]

Demetri Terzopoulos
2010 Lecture Notes in Computer Science  
More broadly, these biomimetic autonomous agents in their realistic virtual worlds also foster deeper computationally-oriented insights into natural living systems.  ...  Artificial animals are complex synthetic organisms that have functional, biomechanical bodies, perceptual sensors, and brains with locomotion, perception, behavior, learning, and cognition centers.  ...  interpretations of perceived situations (such as those obtained from specialized objects) that are at least as important and useful to a pedestrian.  ... 
doi:10.1007/978-3-642-12842-4_4 fatcat:o2dx56zt25chrnk3workfzs2ke

Autonomous Vehicle Control: End-to-end Learning in Simulated Urban Environments [article]

Hege Haavaldsen, Max Aasboe, Frank Lindseth
2019 arXiv   pre-print
This paper examines end-to-end learning for autonomous vehicles in simulated urban environments containing other vehicles, traffic lights, and speed limits.  ...  An end-to-end approach attempts to achieve autonomous driving using a single, comprehensive software component.  ...  These authors contributed equally to this work. Corresponding author.  ... 
arXiv:1905.06712v1 fatcat:x5bwas5x4neyxdap7dhmdqguae

An Efficient Object Navigation Strategy for Mobile Robots Based on Semantic Information

Yu Guo, Yuanyan Xie, Yue Chen, Xiaojuan Ban, Balqies Sadoun, Mohammad S. Obaidat
2022 Electronics  
Among the related technologies, the visual SLAM system allows the mobile robot to locate itself, build the map, and provide a navigation strategy to execute follow-up tasks, such as searching for objects  ...  To solve the above problems, an efficient object navigation strategy is proposed in this paper.  ...  For example, the "decision" node can obtain the object detection results ("Messages") from In the autonomous object navigation system introduced here, the robot will perceive the surrounding environment  ... 
doi:10.3390/electronics11071136 fatcat:aa5cxw2v2vbipbbykijfsadvre

Autonomous Social Distancing in Urban Environments using a Quadruped Robot [article]

Tingxiang Fan, Zhiming Chen, Xuan Zhao, Jing Liang, Cong Shen, Dinesh Manocha, Jia Pan, Wei Zhang
2020 arXiv   pre-print
Next, the robot uses a crowd-aware navigation algorithm to move freely in highly dynamic scenarios.  ...  We demonstrate and validate that our robot can be operated autonomously by conducting several experiments in various urban scenarios.  ...  With the blossom of deep learning, CNN is well developed to extract the trajectory of a single object [18] - [20] . Chu et al. developed STAM to detect more objects [21] .  ... 
arXiv:2008.08889v1 fatcat:6ptbrz3rprgp7d4p74rjb3pj64

Awareness in Software-Intensive Systems

Emil Vassev, Mike Hinchey
2012 Computer  
Closely related to artificial Intelligence, awareness depends on the knowledge transferred to software-intensive systems so they can use it to exhibit intelligence.  ...  A successful artificial awareness mechanism is critical in the construction of autonomous robotic systems able to perceive their environment and react to changes autonomously.  ...  concepts; 3) objects as realization of concepts; 4) relations to show how concepts and objects are related to each other; 5) self-adapting scenarios for the system in question, e.g., eventual problematic  ... 
doi:10.1109/mc.2012.401 fatcat:qf6mi6fonvgptovo3tjmouorie
« Previous Showing results 1 — 15 out of 41,401 results