Weakly Supervised Correspondence Learning
This work addresses the difficulty of collecting paired data for robots with different dynamics, offering a more practical solution for real-world applications, though it is incremental as it builds on existing correspondence learning methods.
The paper tackles the problem of correspondence learning in robotics, which is challenging due to the need for strictly paired data or issues with unsupervised methods, by introducing a weakly supervised approach that uses temporal ordering and paired abstractions to improve alignment and reduce annotation costs.
Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments. However, current correspondence learning methods either leverage strictly paired data -- which are often difficult to collect -- or learn in an unsupervised fashion from unpaired data using regularization techniques such as cycle-consistency -- which suffer from severe misalignment issues. We propose a weakly supervised correspondence learning approach that trades off between strong supervision over strictly paired data and unsupervised learning with a regularizer over unpaired data. Our idea is to leverage two types of weak supervision: i) temporal ordering of states and actions to reduce the compounding error, and ii) paired abstractions, instead of paired data, to alleviate the misalignment problem and learn a more accurate correspondence. The two types of weak supervision are easy to access in real-world applications, which simultaneously reduces the high cost of annotating strictly paired data and improves the quality of the learned correspondence.