发表机构
Ulsan National Institute of Science and Technology; Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM)（蔚山国立科学技术院; 慕尼黑机器人与机器智能研究所（MIRMI），慕尼黑工业大学（TUM））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出一种基于生成式经验回放与不确定性感知的持续学习框架，使可通行性预测模型在适应新地形时保留旧经验并缓解灾难性遗忘，经滑移转向机器人实验验证有效。
AI 中文摘要
可通行性预测是自主导航在非结构化环境中的关键组成部分，其中复杂且不确定的机器人-地形交互带来了重大挑战，如牵引力损失和动态不稳定性。尽管基于学习的可通行性预测方法近期取得了进展，但这些方法往往无法适应新地形。即使实现了自适应，保留先前训练环境的经验仍然是一个挑战，这一问题被称为灾难性遗忘。为解决这一挑战，我们提出了一种用于可通行性预测的持续学习框架，该框架通过生成式经验回放模型逐步适应新地形。该框架的关键优点有两方面：i) 在不存储过去数据的情况下保留先前经验；ii) 融合回放模型生成样本的不确定性，实现不确定性感知的自适应。使用滑移转向机器人的真实世界实验验证了所提框架的有效性，展示了其在适应一系列多样化环境的同时缓解灾难性遗忘的能力。
英文摘要
Traversability prediction is a critical component of autonomous navigation in unstructured environments, where complex and uncertain robot-terrain interactions pose significant challenges such as traction loss and dynamic instability. Despite recent progress in learning-based traversability prediction, these methods often fail to adapt to novel terrains. Even when adaptation is achieved, retaining experience from previously trained environments remains a challenge, a problem known as catastrophic forgetting. To address this challenge, we propose a continual learning framework for traversability prediction that incrementally adapts to new terrains using a generative experience recall model. A key virtue of the proposed framework is two folds: i) retain prior experience without storing past data; and ii) incorporate the uncertainty of the generated samples from the recall model, enabling uncertainty-aware adaptation. Real-world experiments with a skid-steering robot validate the effectiveness of the proposed framework, demonstrating its ability to adapt across a series of diverse environments while mitigating catastrophic forgetting.
CommentsAccepted version of the article published in IEEE Robotics and Automation Letters. DOI: 10.1109/LRA.2025.3619687
Journal refIEEE Robotics and Automation Letters, vol. 10, no. 11, pp. 12109-12116, Nov. 2025
