SatBuilder

Autonomous visual manipulation for in-space assembly.

Period of Performance: 2018–2019

My role: PI

Additional Contributors: Shubham Sonawani, S. Kailas, Ryan Alimo, Heni Ben Amor.

Funded by NASA's Jet Propulsion Laboratory (JPL).

We developed means of localizing, tracking, and grasping known objects in visual conditions representative of Earth orbit and on compute solutions representative of space hardware. The project was validated on a JPL-designed 6U cubesat manipulator, demonstrating the assembly of a truss structure (Sonawani et al., 2020; Sonawani et al., 2020).

References

Robotic In-Space Assembly with Arm-Augmented Cubesats.

S. Sonawani, S. Kailas, R. Detry, R. Alimo, S. Backus, R. McCormick, R. Mukherjee, K. Wehage, and H. Ben Amor.

In Opportunities and Challenges in Space Robotics (Workshop at ICRA 2020), 2020 (Best Poster Award).

Bib

PDF

@inproceedings{sonawani2020b,
  author = {Sonawani, S. and Kailas, S. and Detry, R. and Alimo, R. and Backus, S. and McCormick, R. and Mukherjee, R. and Wehage, K. and Amor, H. Ben},
  title = {Robotic In-Space Assembly with Arm-Augmented Cubesats},
  year = {2020},
  booktitle = {Opportunities and Challenges in Space Robotics (Workshop at ICRA 2020)},
}

Assistive Relative Pose Estimation for On-orbit Assembly using Convolutional Neural Networks.

Shubham Sonawani, Ryan Alimo, Renuad Detry, Daniel Jeong, Andrew Hess, and Heni Ben Amor.

In AIAA SciTech Forum, 2020.

Bib

DOI

@inproceedings{sonawani2020a,
  author = {Sonawani, Shubham and Alimo, Ryan and Detry, Renuad and Jeong, Daniel and Hess, Andrew and Amor, Heni Ben},
  title = {Assistive Relative Pose Estimation for On-orbit Assembly using Convolutional Neural Networks},
  year = {2020},
  booktitle = {AIAA SciTech Forum},
  doi = {10.2514/6.2020-2096},
  url = {https://arc.aiaa.org/doi/pdf/10.2514/6.2020-2096}
}