A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf
.
Filters
Hierarchical Vision Navigation System for Quadruped Robots with Foothold Adaptation Learning
2023
Sensors
We present a novel hierarchical vision navigation system combining foothold adaptation policy with locomotion control of the quadruped robots. ...
However, it remains a challenging task to efficiently utilize the dynamics of robots in cluttered environments and to achieve efficient navigation. ...
Chuan Yu for proofreading and support of the experiment.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/s23115194
fatcat:xpc2vnnyozhyrijsikl7vh4tju
Joint Communication and Control System Design for Connected and Autonomous Vehicle Navigation
2019
ICC 2019 - 2019 IEEE International Conference on Communications (ICC)
Simulation results validate the theoretical results and show that the proposed joint design can improve the number of reliable V2X pairs by as much as 70% compared to a baseline scheme that optimizes the ...
The first sub-problem is the control mechanism design in which a dual update method is used to determine the headway distance parameter for the control system. ...
The main contribution of this paper is a novel joint control system and V2X communication design framework that enables CAVs to leverage V2X connectivity for autonomous navigation (i.e., path tracking) ...
doi:10.1109/icc.2019.8761966
dblp:conf/icc/ZengSSB19
fatcat:4bnoggiuvzbplejenfvoiippem
Special Issue on Deep Reinforcement Learning for Emerging IoT Systems
2020
IEEE Internet of Things Journal
The article titled "A deep-reinforcement-learning-based recommender system for occupant-driven energy optimization in commercial buildings" presents recEnergy, a DRL-based recommender system to reduce ...
The article titled "Multiagent deep reinforcement learning for joint multichannel access and task offloading of mobile-edge computing in Industry 4.0" proposes a novel multiagent reinforcement learning ...
doi:10.1109/jiot.2020.2998256
fatcat:rct75tsesbh7lkjmhuyogfi4ym
Unifying Map and Landmark Based Representations for Visual Navigation
[article]
2017
arXiv
pre-print
This allows it to efficiently navigate in novel environments given only a sparse set of registered images as input for building representations for space. ...
This works presents a formulation for visual navigation that unifies map based spatial reasoning and path planning, with landmark based robust plan execution in noisy environments. ...
This shows the benefit of
Table 2 : 2 Full System Results: We report performance of our full system for navigation with noisy actuation. ...
arXiv:1712.08125v1
fatcat:234pn4ro3vbyrda7ub5sqpl2qe
An Overview of Perception and Decision-Making in Autonomous Systems in the Era of Learning
[article]
2020
arXiv
pre-print
Second, we briefly summarize the existing motion planning techniques, such as path planning and trajectory planning methods, and discuss the navigation methods based on reinforcement learning. ...
In this review, we focus on the applications of learning-based approaches in perception and decision-making in autonomous systems, which is different from previous reviews that discussed traditional methods ...
[36] introduced a reinforcement learning method to map-building based navigation. ...
arXiv:2001.02319v3
fatcat:z3zhp2cyonfqtlttl2y57572uy
Novel Framework for Navigation using Enhanced Fuzzy Approach with Sliding Mode Controller
2018
International Journal of Electrical and Computer Engineering (IJECE)
Therefore, this paper presents a novel optimized design of a sliding mode controller that can be effectively deployed on advanced navigational system. ...
Although, there has been good number of studies in sliding mode controller, it is less attempted to optimize the navigational performance of a vehicle. ...
RESEARCH METHODOLOGY The main intention of this work is to design a framework of a novel vehicle navigational system using fuzzy logic and sliding mode controller. ...
doi:10.11591/ijece.v8i6.pp4310-4320
fatcat:qqsynfpcrjbepj5wliavhwihna
Guest Editorial Special Section on Surgical Vision, Navigation, and Robotics
2022
IEEE Transactions on Medical Robotics and Bionics
The topic of this Special Section on "Surgical Vision, Navigation, and Robotics" is comprised under one of the six Journal Areas addressed in T-MRB, which is Surgical Robotics. ...
whose scope also encompasses the topics expressed in the Call for Papers, which sought articles relating to state-of-the-art research in Surgical Vision, Navigation, and Robotics. ...
XIONGBIAO LUO, Guest Editor Department of Computer Science and Technology Xiamen University Xiamen 361005, China E-mail: xbluo@xmu.edu.cn ...
doi:10.1109/tmrb.2022.3147605
fatcat:x6et3jtm4jdohodd3zi7winn5u
A novel and stable approach to anatomical structure morphing for enhanced intraoperative 3D visualization
2005
Medical Imaging 2005: Visualization, Image-Guided Procedures, and Display
In this paper we propose a novel and stable method to construct a patient-specific model that provides an appropriate intra-operative 3D visualization without the need for a pre or intra-operative imaging ...
Our morphing scheme efficiently and accurately computes a Mahalanobis distance weighted least square fit of the deformable model to the 3D data model by solving a linear equation system. ...
Davies and Chris Taylor from University of Manchester, UK. ...
doi:10.1117/12.595175
dblp:conf/miigp/RajamaniBNS05
fatcat:a27pqxuztvawbcb5mno6doky6i
Visual-UWB Navigation System for Unknown Environments
[article]
2019
arXiv
pre-print
In this paper, we present a novel accurate, robust and low-cost GNSS-independent navigation system, which is composed of a monocular camera and Ultra-wideband (UWB) transceivers. ...
We propose a visual-UWB Simultaneous Localization and Mapping (SLAM) algorithm which tightly combines visual and UWB measurements to form a joint non-linear optimization problem on Lie-Manifold. ...
However, as a navigation system, the UWB-only method can rarely enable the vehicle to avoid collisions, due to the fact that a comprehensive map of the environment cannot be obtained. ...
arXiv:1912.01178v1
fatcat:vo3qhghfp5hvbgaxl4inqsiceu
Connecting Deep-Reinforcement-Learning-based Obstacle Avoidance with Conventional Global Planners using Waypoint Generators
[article]
2021
arXiv
pre-print
Therefore, we integrate different waypoint generators into existing navigation systems and compare the joint system against traditional ones. ...
However, the integration of Deep Reinforcement Learning into existing navigation systems is still an open frontier due to the myopic nature of Deep-Reinforcement-Learning-based navigation, which hinders ...
Results showed that our joint navigation systems outperform conventional systems in terms of safety and efficiency. ...
arXiv:2104.03663v1
fatcat:qk2th2sih5hh5hx7in75wbstse
Curiosity-Driven Multi-Agent Exploration with Mixed Objectives
[article]
2022
arXiv
pre-print
In this work, we propose a curiosity-driven multi-agent exploration method that has the mixed objective of motivating the agents to explore the environment in ways that are individually and collectively ...
novel. ...
We provide an illustration of our proposed method in Figure 3 .
Curiosity-Driven Exploration We build upon the curiosity-driven approach of Pathak et al. ...
arXiv:2210.16468v1
fatcat:cazdbkngyngpzmw27dzlsinqw4
A Quadratic Programming Approach to Manipulation in Real-Time Using Modular Robots
[article]
2021
arXiv
pre-print
Different from robots with fixed geometry or configurations, the kinematics model of a modular robotic system can alter as the robot reconfigures itself, and developing a generic control and motion planning ...
Some constraints can be incorporated into this QP, including a novel way to approximate environment obstacles. ...
However, it is usually computationally expensive to build such a navigation function in general. ...
arXiv:2104.02755v1
fatcat:nsbgn36cgnf43l633e5bp5p3la
JOINT TRACKING GPS AND LEO SIGNALS WITH ADAPTIVE VECTOR TRACKING LOOP IN CHALLENGING ENVIRONMENTS
2022
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
In this study, we proposed a joint GPS and LEO navigation signal tracking strategy that employs a vector tracking loop (VTL) with fully considering the high dynamic characteristics of the LEO signals. ...
LEO navigation is joint positioning with the existing GNSS signals which has not been seriously studied. ...
ACKNOWLEDGEMENTS This work was sponsored by the National Natural Science Foundation of China (NSFC 42074036) and the Fundamental Research Funds for the Central Universities. ...
doi:10.5194/isprs-archives-xlvi-3-w1-2022-119-2022
fatcat:vtbkwhcjezeu3icadds2hzedyq
Learning Mobile Manipulation
[article]
2022
arXiv
pre-print
The challenge is in building systems that scale beyond specific situational instances and gracefully operate in novel conditions. ...
The work in this thesis will demonstrate how to build a system for robotic mobile manipulation that is robust to changes in these variables. ...
The agent then uses a novel panoramic prediction method to predict the view of the environment from that next-best-view to use the learned visual navigation system to navigate there without needing to ...
arXiv:2206.03448v1
fatcat:lbzovowk4zb53eqzavncchsi5q
Learning Generalizable Feature Fields for Mobile Manipulation
[article]
2024
arXiv
pre-print
We demonstrate the effectiveness of this approach by deploying GeFF on a quadrupedal robot equipped with a manipulator. ...
To do so, we treat generative novel view synthesis as a pre-training task, and then align the resulting rich scene priors with natural language via CLIP feature distillation. ...
To avoid costly per-scene optimization, generalizable NeRFs [11, 12] propose to condition the novel view on input frames instead of optimizing the underlying parameters. ...
arXiv:2403.07563v1
fatcat:c26p7lqlmncqtir4ydptmiu754
« Previous
Showing results 1 — 15 out of 32,341 results