%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 05:07:12 PM

@INPROCEEDINGS{Brudermuller_IEEEICAR_2021,
         author = {Brudermuller, Lara and Lembono, Teguh Santoso and Shetty, Suhan and Calinon, Sylvain},
       projects = {Idiap},
          month = dec,
          title = {Trajectory Prediction with Compressed 3D Environment Representation using Tensor Train Decomposition},
      booktitle = {International Conference on Advanced Robotics},
           year = {2021},
       abstract = {Trajectory optimization for motion planning and
optimal control is a popular approach in robotics. Algorithms
typically require good initialization in order to find the optimal
trajectories. To provide such initialization, many approaches
rely on the concept of memory of motion, where a function
approximator is trained on a database of robot trajectories to
predict good initial trajectories for novel situations, and hence
speeding up the subsequent trajectory optimization process. To
be able to generalize well to a new environment, an expressive
environment descriptor is necessary. We propose to encode
the environment by discretized signed distance functions (SDF)
which are then compressed using a tensor train (TT) decomposition approach. In order to show the expressiveness of this
low-rank TT-SDF representation, three function approximators
are compared: k-nearest neighbors, a neural network, and a
mixture density network. We demonstrate the proposed method
with motion planning examples on two different systems (point
mass and quadcopter). Our experiments demonstrate that the
TT-SDF encoding can provide compact environment descriptors
in order to predict good initial trajectories for warm-starting
an optimal control solver.},
            pdf = {https://publications.idiap.ch/attachments/papers/2021/Brudermuller_IEEEICAR_2021.pdf}
}