Now 374 visitors
Today:0 Yesterday:0
Total: 123830 216S 51P 5R
2026-10-21, Week 43
Member Login
TACT Journal Homepage
Call for Paper
Committee
Find My Paper
Author Homepage
Statistics & History
Welcome Message
Paper Procedure
FAQ
Paper Archives
Outstanding Papers
Program & Proceedings
Presentation Platform
Hotel & Travel Info
Photo Gallery
Scheduler Login
Seminar
Archives Login
Sponsors


















Online Q&A Session
Paper Number Author:
Paper Title
Keyword
Q&A Number **Select your question number !!
Questioner eMail:
Question
Answer
by
Author
Save Q&A

* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)
ICACT20230128 Question.1
Questioner: haodp@dau.edu.vn    2023-02-27 오전 7:25:01 		ICACT20230128 Answer.1
Answer by Auhor p2109422@mpu.edu.mo   2023-02-27 오전 7:25:01
Chrome Click!!
How can heuristic algorithms and reinforcement learning be integrated to create effective path planning strategies for cellular connected UAVs, and what are the most important design considerations for these systems? This is indeed a good question. In our experiments, the A* algorithm was used to search for a path from point-to-point to generate the distance matrix, while the reinforcement learning was responsible for generating training and testing data. As a result, we consider the RL method to be more important because the A* algorithm can be replaced. In future research, we will also try to combine reinforcement learning and heuristic algorithms from other perspectives to achieve even better results.
ICACT20230128 Question.2
Questioner: haodp@dau.edu.vn    2023-02-12 오전 3:01:33 		ICACT20230128 Answer.2
Answer by Auhor p2109422@mpu.edu.mo   2023-02-12 오전 3:01:33
Chrome Click!!
What are the trade-offs between using heuristic algorithms and reinforcement learning for path planning for cellular connected UAVs, and how can these trade-offs be balanced in practice? According to our experiments, the heuristic algorithm performs better in terms of correctness and the advantage increases as the number of cities to be visited increases. At the same time, the reinforcement learning method is unable to handle the problem when the number of cities is large. We demonstrated the correctness of RL when the number of cities was equal to 50 and the result was unacceptable. Furthermore, RL cannot handle changes in the environment, so a new model has to be trained for each different environment. On the other hand, RL can search for a path without a distance matrix and its search time is faster than that of the heuristic algorithm, which saves computer resources and time during path planning. We suggest using RL only when the number of cities is less than 25.
ICACT20230128 Question.3
Questioner: haodp@dau.edu.vn    2023-02-27 오전 7:24:57 		ICACT20230128 Answer.3
Answer by Auhor p2109422@mpu.edu.mo   2023-02-27 오전 7:24:57
Chrome Click!!
What are the current challenges and limitations of path planning for cellular connected UAVs, and how can heuristic algorithms and reinforcement learning help to address these challenges? Different from traditional path planning, cellular-connected UAV path planning has a more complex and dynamic situation, which may make the operation time longer. Most recent studies only focus on using traditional methods, such as dynamic programming, to solve the TSP problem. Only a few studies have used machine learning methods to address TSP. Additionally, most traditional algorithms can only handle simple TSPs that calculate the tour length between two cities using Euclidean distance, or that require a distance matrix for a sequence of cities. However, for cellular-connected UAVs, distance calculation is not a straightforward problem and cannot be calculated using Euclidean distance, so traditional algorithms may not be effective in new scenarios. We consider a scenario where a UAV take off from a start state and fly over several places covered by cellular networks to finish some mission such as data collection or search and rescue. Once the missions are completed, UAV must fly back to where it takes off. In this paper, we use grid map to model the UAV flyable area and A* to calculate the distance between point and point. Then, we use three optimal algorithm, Genetic Algorithm (GA), Simulated Annealing Algorithm (SAA), Pointer Network (Reinforcement Learning) to calculate the best path between the star point and end point.
ICACT20230128 Question.4
Questioner: june@etri.re.kr    2023-02-22 오후 3:41:40 		ICACT20230128 Answer.4
Answer by Auhor p2109422@mpu.edu.mo   2023-02-22 오후 3:41:40
Chrome Click!!
I would like to know additional information about the distance from the starting point to the destination point, whether the test was conducted in the field, and the spatial characteristics of the field. The test environment is basically a 2D grip map with several signal coverage areas which allow UAV pass. We set the distance as the total amount of grip passed along the way planned by the A* algorithm.
ICACT20230128 Question.5
Questioner: bnbadhon17@gmail.com    2023-02-22 오후 3:41:52 		ICACT20230128 Answer.5
Answer by Auhor p2109422@mpu.edu.mo   2023-02-22 오후 3:41:52
Chrome Click!!
Do you have a plan to turn your idea into a Real project/ product? Thank you for your question. We are currently using computer tools to simulate our idea at this stage, but we still expect to be able to implement it in a real environment in the near future
ICACT20230128 Question.6
Questioner: tangfeixi@outlook.com    2023-02-27 오전 7:24:54 		ICACT20230128 Answer.6
Answer by Auhor p2109422@mpu.edu.mo   2023-02-27 오전 7:24:54
Chrome Click!!
Thanks for your interesting paper! Will you tell us your further research direction? Thank you for you comments. In the future we will focus on using Reinforcment Learning to solve TSP in the field of path planning. Also, we want to extend this work to 3-D maps.