Online Local Path Planning on the Campus Environment for Autonomous Driving Considering Road Constraints and Multiple Obstacles
Round 1
Reviewer 1 Report
Dear Authors, thank you very much for submitting your paper "Online Local Path Planning on the Campus Environment for Autonomous Driving considered Road Constraints and Multi- 3 ple Obstacles"
After reviewing heavily reviewing your paper i came to the following conclusions: The paper need to be revised and needs some revisions. In the following i will state which parts of the paper need to be changed or enhanced.
In summary, the paper is overall of good merit but lacks some information, state of the art literature, structural refinements and some additional explanations. In addition some of the results need to be redone and more discussed. In the following i will display what needs to be added to the paper:
1. General Objective and Abstract: In your paper you state that you are developing " a novel urban-based online path plan-ning algorithm robust to a curved-path with multiple obstacles is proposed." From my knowledge as well as the state of the art this is not true because you are enhancing just the A* algorithm. Therfore it is necessary to clarfiy the overall objective an point out that you are adopting the A* algorithm with an potential field. More or less its the combination of ideas and that needs to be adresse more clearly here.
2. Introduction/ Path planning problem analysis of the campus: You are stating the problem here and providing insights for autonomous driving at the campus road environments. A university campus is a "closed environment" which defines a well known area that enables objects that need to be evaded or overtaken. Those kind of approaches can be seen here by Stahl et. al. ( “Multilayer Graph-Based Trajectory Planning for Race Vehicles in Dynamic Scenarios,” presented at the 2019 IEEE Intelligent Transportation Systems Conference - ITSC, Oct. 2019, doi: 10.1109/itsc.2019.8917032.) Where they drive on a closed area with a racing car. Please state out here the difference to the campus scenario and why such an approach is not valid here. ? This kind of approach is taking high velocities into account and is able to overtake more sophisticaded. In addition this approach gives the possibility to create an offline graph beforehand which is suitable for your campus too. This kind of discussion needs to be the baseline for your algorithm enhancemend.
3. State of the Art: The current state of the art is very poor and just picks up the most well known algorithm like A-Star. Unfortunately this paper wants to state a new path planning algorithm so a good clarification for other approaches needs to be done here. I will list additional paper that need to be part of the state of the art as well as an additional discussion:
M. Werling J. Ziegler S. Kammel and S. Thrun "Optimal trajectory generation for dynamic street scenarios in a frenét frame" IEEE International Conference on Robotics and Automation pp. 987-993 2010.
C. Katrakazas M. Quddus W.-H. Chen and L. Deka "Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions" Transportation Research: Emerging Technologies vol. 60 pp. 416-442 2015.
S. Karaman and E. Frazzoli "Optimal kinodynamic motion planning using incremental sampling-based methods" IEEE Conference on Decision and Control pp. 7681-7687 2010.
X. Hu L. Chen B. Tang D. Cao and H. He "Dynamic path planning for autonomous driving on various roads with avoidance of static and moving obstacles" Mechanical Systems and Signal Processing vol. 100 pp. 482-500 2018.
Y. Zhang, H. Chen, S. L. Waslander, J. Gong, G. Xiong, T. Yang, and K. Liu, “Hybrid Trajectory Planning for Autonomous Driving in Highly Constrained Environments,” IEEE Access, vol. 6, pp. 32 800–32 819, 2018.
F. Borrelli P. Falcone T. Keviczky J. Asgari and D. Hrovat "MPC-based approach to active steering for autonomous vehicle systems" Int. J. Vehicle Auto. Syst. vol. 3 no. 2 pp. 265-291 2005.
3. Methods: The current chapter 4 is not sufficient enough. The current Path planning algorithm is just a high level explanation of what is done
- All formulas stated are missing the explanation of the variables. There is no statement about the units nor the meaning of the parameters. I highly recommend an additional table at the end of the paper
- What kind of constraints are stated for the creation of the polynomial for the path?
- What kind of approach is used to created the velocity profile?
- What is the final output of the algorithm: X and z Position? Curvature? ....
I highly recommend to create a step by step diagram that depicts in detail that individual steps that need to be done in this path planning algorithm
4. Simulator and Pipeline:
- Simulator: Where is the Autnomous Driving Pipeline depicted in Figure 7 coming from? Is this part of another paper or was this done as part of the paper? -- The quality of your path planner heavily changes with the quality of the input and output as well as the final control of your vehicle.
5. The current presentation of the results is poor, only figure 12 gives an overview of the results which is not sufficient.
- Please state about the computation time of your algorithm on the given hardware. What kind of hardware are you using in this case?
- The output of figure 12 is unclear: is this the path created by the algorithm or the final controlled path driven by the vehicle? It seems like that especially in case 3 the smoothness is not good enough.
- The quality of all the results images are poor, i highly recommend to integrate vectorized graphics.
5. Discussion: Currently the discussion about the advantages and disadvantages of this proposed of algorithm are missing. Please enter a new chapter that integrates and exhausive discussion about your research as well as a reflection an comparison to existend approachs (e.g. real time comparison)
In addition i think to make the paper more complete it would be helpful for everyone if you open-source your code on Github or similar.
Author Response
Dear reviewer
Thank you for your letter and the opportunity to revision our paper on ["Online Local Path Planning on the Campus Environment for Autonomous Driving considering Road Constraints and Multiple Obstacles"]. The suggestions offered by the reviewers have been immensely helpful, and we also appreciate your insightful comments on revising all aspects of the paper.
I have included the reviewer comments immediately after this letter and responded to them individually, indicating exactly how we addressed each concern or problem and describing the changes we have made.
We hope the revised manuscript will better suit the Journal of Applied Sciences but are happy to consider further revisions, and we thank you for your continued interest in our research.
Sincerely,
Seok-Cheol Kee
Author Response File: 
Author Response.docx
Reviewer 2 Report
The topic is relevant and new
Title: suggest to replace “considered” with “considering”: “Online Local Path Planning on the Campus Environment for Autonomous Driving Considering Road Constraints and Multiple Obstacles”
Abstract: appropriate
Overall, this paper proposed MGPF-Hybrid A* as the path planning algorithm applied to the complex campus environment to ensure collision free by considering road constraints as well as multiple obstacles, and contributed to make an initial step toward urban-based path planning research. The writing and organization are easy to follow. My main points for improvement are as followed.
Conclusions section: In additions to the summary of key results, a paragraph related to room for improvement and future work (e. g. the concept of local path planning in this study is static object avoidance, other hazardous scenarios yet to be identified, the study is an online local path planning rather than real road field-tested study…., if any) might provide insight.
Comments for author File: 
Comments.pdf
Author Response
Dear reviewer
Thank you for your letter and the opportunity to revision our paper on ["Online Local Path Planning on the Campus Environment for Autonomous Driving considering Road Constraints and Multiple Obstacles"]. The suggestions offered by the reviewers have been immensely helpful, and we also appreciate your insightful comments on revising all aspects of the paper.
I have included the reviewer comments immediately after this letter and responded to them individually, indicating exactly how we addressed each concern or problem and describing the changes we have made.
We hope the revised manuscript will better suit the Journal of Applied Sciences but are happy to consider further revisions, and we thank you for your continued interest in our research.
Sincerely,
Seok-Cheol Kee
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Dear Authors,
Thank you very much for considering all my additional request and enhancing the paper regarding my inputs. I am happy with all the additional inputs so nothing to add from my side.
