Actionable Dynamics Modeling for Drifter Prediction | Robotics for Climate Change Workshop @ ICRA 2022

7 views
Download
  • Share

About the Video:
Learning-based methods combined with easily-specified physics knowledge form a powerful duo to enable robust robotic performance in the open world. This talk presents a series of improvements in robotic perception and behavior learning centered around building high-quality models of the robot’s environment, its sensors, and even the robot itself. It also highlights several innovations in structured dynamics modeling focused on trajectory prediction of floating sensors in marine environments, both in simulation and real-world environments.

About the Speaker:
Johanna Hansen is a final year PhD student at McGill University. Currently, she is working on dexterous manipulation with visuo-tactile sensors at the Samsung AI Center in Montreal. She also interned at JPL and worked on machine vision aspects of the Mars Sample Return Mission.

Recorded at the Robotics for Climate Change Workshop during the 2022 IEEE International Conference on Robotics and Automation (ICRA).

Produced in partnership with the IEEE Robotics and Automation Society (https://www.ieee-ras.org/).
Recording funded in part by a grant from the United Engineering Foundation (https://www.uefoundation.org/).

About the Video:
Learning-based methods combined with easily-specified physics knowledge form a powerful duo to enable robust robotic performance in the open world. This talk presents a series of improvements in robotic perception and...

Advertisment

Advertisment