Deep Reinforcement Learning for Model Predictive Controller Based on Disturbed Single Rigid Body Model of Biped Robots
Round 1
Reviewer 1 Report
Please see PDF attached. Thank you.
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Hou et al. present a DSRB-PMC method that take the mass of legs into consideration for bipedal robots. The method and results are clearly presented. The reviewer has two questions as listed below.
1. If the portion of leg mass exceeds 30%, what would be the possible solution to predict the disturbances?
2. How to potentially eliminate the static velocity error of this DSRB-PMC method?
3. Is the current method suitable for quadruped robots?
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper has a good scientific soundness and clearly explains the research.
Adding a little more detail on touchdown policies 1, 2 and 3 may help to understand in detail what they consist of and why it is necessary to switch from one to the other.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf