Continual Learning for Traversability Prediction With Uncertainty-Aware Adaptation
This work proposes a continual learning framework for traversability prediction that incrementally adapts to new terrains using a generative experience recall model, and incorporates the uncertainty of the generated samples from the recall model, enabling uncertainty-aware adaptation.
Ho-Jin Lee, Yunho Lee, D. Duecker et al.
· IEEE Robotics and Automation... · 3 citations