@InProceedings{watt:icip:2020,
  author    = {Watt, Alassane, M. and Yoshiyasu, Yusuke},
  title     = {Pathnet: Learning To Generate Trajectories Avoiding Obstacles},
  booktitle = {IEEE International Conference on Image Processing},
  year      = {2020},
  address   = {Abu Dhabi, United Arab Emirates},
  month     = {October 25-October 28},
  url       = {https://cmsworkshops.com/ICIP2020/Papers/AcceptedPapers.asp},
  keywords  = {Trajectory, Planning, Two dimensional displays, Neural networks, Computational modeling, Shape, Task analysis},
  doi       = {10.1109/ICIP40778.2020.9191088},
  abstract  = {This paper presents a novel approach to solving 2D motion planning problems using deep neural networks, which we refer to as PathNet. PathNet first takes a 2D environment map composed of obstacle zone and free zone and compresses it to a latent vector. The latent vector is afterward concatenated with the start and goal positions to generate a trajectory connecting those positions. Our learning-based neural planner can solve motion planning problems in unseen environments and is computationally efficient as it only needs one single pass in our network to generate trajectories.}
}