Imitation Learning based on Generative Adversarial Networks for Robot Path Planning
Name:
Final Thesis - Xianyong Yi - 170511.pdf
Size:
8.089Mb
Format:
PDF
Embargo End Date:
2021-11-24
Type
ThesisAuthors
Yi, Xianyong
Advisors
Michels, Dominik L.Committee members
Wonka, Peter
Moshkov, Mikhail

Program
Chemical ScienceDate
2020-11-24Embargo End Date
2021-11-24Permanent link to this record
http://hdl.handle.net/10754/666096
Metadata
Show full item recordAccess Restrictions
At the time of archiving, the student author of this thesis opted to temporarily restrict access to it. The full text of this thesis will become available to the public after the expiration of the embargo on 2021-11-24.Abstract
Robot path planning and dynamic obstacle avoidance are defined as a problem that robots plan a feasible path from a given starting point to a destination point in a nonlinear dynamic environment, and safely bypass dynamic obstacles to the destination with minimal deviation from the trajectory. Path planning is a typical sequential decision-making problem. Dynamic local observable environment requires real-time and adaptive decision-making systems. It is an innovation for the robot to learn the policy directly from demonstration trajectories to adapt to similar state spaces that may appear in the future. We aim to develop a method for directly learning navigation behavior from demonstration trajectories without defining the environment and attention models, by using the concepts of Generative Adversarial Imitation Learning (GAIL) and Sequence Generative Adversarial Network (SeqGAN). The proposed SeqGAIL model in this thesis allows the robot to reproduce the desired behavior in different situations. In which, an adversarial net is established, and the Feature Counts Errors reduction is utilized as the forcing objective for the Generator. The refinement measure is taken to solve the instability problem. In addition, we proposed to use the Rapidly-exploring Random Tree* (RRT*) with pre-trained weights to generate adequate demonstration trajectories in dynamic environment as the training data, and this idea can effectively overcome the difficulty of acquiring huge training data.Citation
Yi, X. (2020). Imitation Learning based on Generative Adversarial Networks for Robot Path Planning. KAUST Research Repository. https://doi.org/10.25781/KAUST-2CT9Bae974a485f413a2113503eed53cd6c53
10.25781/KAUST-2CT9B