Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
Advanced Perception-Planning Fusion Technology in Robotics
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Advanced Perception-Planning Fusion Technology in Robotics

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".

Deadline for manuscript submissions: closed (5 January 2021) | Viewed by 19148

Special Issue Editors

Dr. Wei Pan

E-Mail Website
Guest Editor
Department of Cognitive Robotics, Delft University of Technology, 2628 CD Delft, The Netherlands
Dr. Chengchao Bai

E-Mail Website
Guest Editor
Department of Cognitive Robotics, Delft University of Technology, 2628 CD Delft, The Netherlands
Interests: Multi-Robot Systems; Autonomous Learning

Special Issue Information

With the rapid development of artificial intelligence technology, perception technology has advanced considerably. Both the recognition accuracy rate and the detection rate are far superior to traditional methods, and have been widely used in many industries, playing an important role in the field of robots. Perception technology provides various robots with efficient perception of the external environment and accurate estimation of their own state, thereby providing effective guarantees for planning and control systems.

However, with the variety and complexity of tasks, higher requirements have been placed on the intelligence of robot systems, not only achieving information acquisition, processing, and output of the environment, but also human-like decision-making ability. A single system no longer separates perception and planning into different system units. Conversely, different levels of intelligence can be achieved through fusion. For example, based on the planning and analysis of tasks, intelligent detection and selective output at the perception end can be realized. Simultaneously, the use of a hybrid mechanism of the two can provide resilience for single or multiple robot systems, producing optimal decision-making behaviors for unknown disturbances and active attacks.

Therefore, perception–planning fusion technology is essential for the intelligent development of robot systems, and is a future development trend.

This Special Issue focuses on recent advances in perception–planning fusion technology in robotics. We welcome original research contributions and reviews of state-of-the-art studies from academia and industry. The Special Issue topics include, but are not limited to:

  •  Perception–planning fusion
  •  Planning based active perception
  •  Distributed dynamic perception
  •  Distributed motion planning
  •  Hybrid decision optimization
  •  Fusion technology for resilience

Dr. Wei Pan
Dr. Chengchao Bai
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • aerial robotics
  • ground robotics
  • space robotics
  • underwater robotics
  • industry robotics
  • special robotics
  • swarm robotics
  • sensing–planning fusion
  • planning based active sensing
  • distributed dynamic perception
  • distributed motion planning
  • hybrid decision optimization
  • fusion technology for resilience

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 2021 KiB  
Article
An Integrated Mission Planning Framework for Sensor Allocation and Path Planning of Heterogeneous Multi-UAV Systems
by Hongxing Zheng and Jinpeng Yuan
Sensors 2021, 21(10), 3557; https://doi.org/10.3390/s21103557 - 20 May 2021
Cited by 5 | Viewed by 2416
Abstract
Mission planning is the guidance for a UAV team to perform missions, which plays the most critical role in military and civil applications. For complex tasks, it requires heterogeneous cooperative multi-UAVs to satisfy several mission requirements. Meanwhile, airborne sensor allocation and path planning [...] Read more.
Mission planning is the guidance for a UAV team to perform missions, which plays the most critical role in military and civil applications. For complex tasks, it requires heterogeneous cooperative multi-UAVs to satisfy several mission requirements. Meanwhile, airborne sensor allocation and path planning are the critical components of heterogeneous multi-UAVs system mission planning problems, which affect the mission profit to a large extent. This paper establishes the mathematical model for the integrated sensor allocation and path planning problem to maximize the total task profit and minimize travel costs, simultaneously. We present an integrated mission planning framework based on a two-level adaptive variable neighborhood search algorithm to address the coupled problem. The first-level is devoted to planning a reasonable airborne sensor allocation plan, and the second-level aims to optimize the path of the heterogeneous multi-UAVs system. To improve the mission planning framework’s efficiency, an adaptive mechanism is presented to guide the search direction intelligently during the iterative process. Simulation results show that the effectiveness of the proposed framework. Compared to the conventional methods, the better performance of planning results is achieved. Full article
(This article belongs to the Special Issue Advanced Perception-Planning Fusion Technology in Robotics)
►▼ Show Figures

Figure 1

18 pages, 7950 KiB  
Article
Searching and Tracking an Unknown Number of Targets: A Learning-Based Method Enhanced with Maps Merging
by Peng Yan, Tao Jia and Chengchao Bai
Sensors 2021, 21(4), 1076; https://doi.org/10.3390/s21041076 - 04 Feb 2021
Cited by 5 | Viewed by 2310
Abstract
Unmanned aerial vehicles (UAVs) have been widely used in search and rescue (SAR) missions due to their high flexibility. A key problem in SAR missions is to search and track moving targets in an area of interest. In this paper, we focus on [...] Read more.
Unmanned aerial vehicles (UAVs) have been widely used in search and rescue (SAR) missions due to their high flexibility. A key problem in SAR missions is to search and track moving targets in an area of interest. In this paper, we focus on the problem of Cooperative Multi-UAV Observation of Multiple Moving Targets (CMUOMMT). In contrast to the existing literature, we not only optimize the average observation rate of the discovered targets, but we also emphasize the fairness of the observation of the discovered targets and the continuous exploration of the undiscovered targets, under the assumption that the total number of targets is unknown. To achieve this objective, a deep reinforcement learning (DRL)-based method is proposed under the Partially Observable Markov Decision Process (POMDP) framework, where each UAV maintains four observation history maps, and maps from different UAVs within a communication range can be merged to enhance UAVs’ awareness of the environment. A deep convolutional neural network (CNN) is used to process the merged maps and generate the control commands to UAVs. The simulation results show that our policy can enable UAVs to balance between giving the discovered targets a fair observation and exploring the search region compared with other methods. Full article
(This article belongs to the Special Issue Advanced Perception-Planning Fusion Technology in Robotics)
►▼ Show Figures

Figure 1

16 pages, 9391 KiB  
Article
Learning-Based End-to-End Path Planning for Lunar Rovers with Safety Constraints
by Xiaoqiang Yu, Ping Wang and Zexu Zhang
Sensors 2021, 21(3), 796; https://doi.org/10.3390/s21030796 - 25 Jan 2021
Cited by 26 | Viewed by 4341
Abstract
Path planning is an essential technology for lunar rover to achieve safe and efficient autonomous exploration mission, this paper proposes a learning-based end-to-end path planning algorithm for lunar rovers with safety constraints. Firstly, a training environment integrating real lunar surface terrain data was [...] Read more.
Path planning is an essential technology for lunar rover to achieve safe and efficient autonomous exploration mission, this paper proposes a learning-based end-to-end path planning algorithm for lunar rovers with safety constraints. Firstly, a training environment integrating real lunar surface terrain data was built using the Gazebo simulation environment and a lunar rover simulator was created in it to simulate the real lunar surface environment and the lunar rover system. Then an end-to-end path planning algorithm based on deep reinforcement learning method is designed, including state space, action space, network structure, reward function considering slip behavior, and training method based on proximal policy optimization. In addition, to improve the generalization ability to different lunar surface topography and different scale environments, a variety of training scenarios were set up to train the network model using the idea of curriculum learning. The simulation results show that the proposed planning algorithm can successfully achieve the end-to-end path planning of the lunar rover, and the path generated by the proposed algorithm has a higher safety guarantee compared with the classical path planning algorithm. Full article
(This article belongs to the Special Issue Advanced Perception-Planning Fusion Technology in Robotics)
►▼ Show Figures

Figure 1

19 pages, 6100 KiB  
Article
A Trajectory Planning Method for Autonomous Valet Parking via Solving an Optimal Control Problem
by Chen Chen, Bing Wu, Liang Xuan, Jian Chen, Tianxiang Wang and Lijun Qian
Sensors 2020, 20(22), 6435; https://doi.org/10.3390/s20226435 - 11 Nov 2020
Cited by 11 | Viewed by 3962
Abstract
In the last decade, research studies on parking planning mainly focused on path planning rather than trajectory planning. The results of trajectory planning are more instructive for a practical parking process. Therefore, this paper proposes a trajectory planning method in which the optimal [...] Read more.
In the last decade, research studies on parking planning mainly focused on path planning rather than trajectory planning. The results of trajectory planning are more instructive for a practical parking process. Therefore, this paper proposes a trajectory planning method in which the optimal autonomous valet parking (AVP) trajectory is obtained by solving an optimal control problem. Additionally, a vehicle kinematics model is established with the consideration of dynamic obstacle avoidance and terminal constraints. Then the parking trajectory planning problem is modeled as an optimal control problem, while the parking time and driving distance are set as the cost function. The homotopic method is used for the expansion of obstacle boundaries, and the Gauss pseudospectral method (GPM) is utilized to discretize this optimal control problem into a nonlinear programming (NLP) problem. In order to solve this NLP problem, sequential quadratic programming is applied. Considering that the GPM is insensitive to the initial guess, an online calculation method of vertical parking trajectory is proposed. In this approach, the offline vertical parking trajectory, which is calculated and stored in advance, is taken as the initial guess of the online calculation. The selection of an appropriate initial guess is based on the actual starting position of parking. A small parking lot is selected as the verification scenario of the AVP. In the validation of the algorithm, the parking trajectory planning is divided into two phases, which are simulated and analyzed. Simulation results show that the proposed algorithm is efficient in solving a parking trajectory planning problem. The online calculation time of the vertical parking trajectory is less than 2 s, which meets the real-time requirement. Full article
(This article belongs to the Special Issue Advanced Perception-Planning Fusion Technology in Robotics)
►▼ Show Figures

Figure 1

19 pages, 1625 KiB  
Article
A Distributed Radio Beacon/IMU/Altimeter Integrated Localization Scheme with Uncertain Initial Beacon Locations for Lunar Pinpoint Landing
by Rongjun Mu, Yuntian Li, Rubin Luo, Bingzhi Su and Yongzhi Shan
Sensors 2020, 20(19), 5643; https://doi.org/10.3390/s20195643 - 02 Oct 2020
Cited by 2 | Viewed by 2588
Abstract
As a growing number of exploration missions have successfully landed on the Moon in recent decades, ground infrastructures, such as radio beacons, have attracted a great deal of attention in the design of navigation systems. None of the available studies regarding integrating beacon [...] Read more.
As a growing number of exploration missions have successfully landed on the Moon in recent decades, ground infrastructures, such as radio beacons, have attracted a great deal of attention in the design of navigation systems. None of the available studies regarding integrating beacon measurements for pinpoint landing have considered uncertain initial beacon locations, which are quite common in practice. In this paper, we propose a radio beacon/inertial measurement unit (IMU)/altimeter localization scheme that is sufficiently robust regarding uncertain initial beacon locations. This scheme was designed based on the sparse extended information filter (SEIF) to locate the lander and update the beacon configuration at the same time. Then, an adaptive iterated sparse extended hybrid filter (AISEHF) was devised by modifying the prediction and update stage of SEIF with a hybrid-form propagation and a damping iteration algorithm, respectively. The simulation results indicated that the proposed method effectively reduced the error in the position estimations caused by uncertain beacon locations and made an effective trade-off between the estimation accuracy and the computational efficiency. Thus, this method is a potential candidate for future lunar exploration activities. Full article
(This article belongs to the Special Issue Advanced Perception-Planning Fusion Technology in Robotics)
►▼ Show Figures

Figure 1

22 pages, 6757 KiB  
Article
Solving the Multi-Functional Heterogeneous UAV Cooperative Mission Planning Problem Using Multi-Swarm Fruit Fly Optimization Algorithm
by Rubin Luo, Hongxing Zheng and Jifeng Guo
Sensors 2020, 20(18), 5026; https://doi.org/10.3390/s20185026 - 04 Sep 2020
Cited by 17 | Viewed by 2746
Abstract
The complexity of unmanned aerial vehicle (UAV) missions is increasing with the rapid development of UAV technology. Multiple UAVs usually cooperate in the form of teams to improve the efficiency of mission execution. The UAVs are equipped with multiple sensors with complementary functions [...] Read more.
The complexity of unmanned aerial vehicle (UAV) missions is increasing with the rapid development of UAV technology. Multiple UAVs usually cooperate in the form of teams to improve the efficiency of mission execution. The UAVs are equipped with multiple sensors with complementary functions to adapt to the complex mission constraints. Reasonable task assignment, task scheduling, and UAV trajectory planning are the prerequisites for efficient cooperation of multi-functional heterogeneous UAVs. In this paper, a multi-swarm fruit fly optimization algorithm (MFOA) with dual strategy switching is proposed to solve the multi-functional heterogeneous UAV cooperative mission planning problem with the criterion of simultaneously minimizing the makespan and the total mission time. First, the multi-swarm mechanism is introduced to enhance the global search capability of the fruit fly optimization algorithm. Second, in the smell-based search phase, the local search strategies and large-scale search strategies are designed to drive multiple fruit fly swarms, and the dual strategy switching method is presented. Third, in the vision-based search stage, the greedy selection strategy is adopted. Finally, numerical simulation experiments are designed. The simulation results show that the MFOA algorithm is more effective and stable for solving the multi-functional heterogeneous UAV cooperative mission planning problem compared with other algorithms. Full article
(This article belongs to the Special Issue Advanced Perception-Planning Fusion Technology in Robotics)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop