TY - GEN
T1 - Robot in a China Shop
T2 - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
AU - Xihan, Bian
AU - Mendez, Oscar
AU - Hadfield, Simon
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Robots need to be able to work in multiple different environments. Even when performing similar tasks, different behaviour should be deployed to best fit the current environment. In this paper, We propose a new approach to navigation, where it is treated as a multi-task learning problem. This enables the robot to learn to behave differently in visual navigation tasks for different environments while also learning shared expertise across environments. We evaluated our approach in both simulated environments as well as real-world data. Our method allows our system to converge with a 26% reduction in training time, while also increasing accuracy.
AB - Robots need to be able to work in multiple different environments. Even when performing similar tasks, different behaviour should be deployed to best fit the current environment. In this paper, We propose a new approach to navigation, where it is treated as a multi-task learning problem. This enables the robot to learn to behave differently in visual navigation tasks for different environments while also learning shared expertise across environments. We evaluated our approach in both simulated environments as well as real-world data. Our method allows our system to converge with a 26% reduction in training time, while also increasing accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85125474199&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9561545
DO - 10.1109/ICRA48506.2021.9561545
M3 - Conference Proceeding
AN - SCOPUS:85125474199
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 5959
EP - 5965
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 30 May 2021 through 5 June 2021
ER -