IMOST:用于持续可通行性学习的在线自监督增量记忆机制
IMOST: Incremental Memory Mechanism with Online Self-Supervision for Continual Traversability Learning
AI总结:
提出持续可通行性学习框架IMOST,通过增量动态记忆和自监督标注模块解决复杂环境下的稀疏标注和遗忘问题,在四足机器人上实现在线学习并优于现有方法。
摘要:
可通行性估计是一般导航系统路径规划的基础。然而,复杂和动态的环境对使用自监督学习(SSL)技术的最新方法提出了挑战。首先,现有的基于SSL的方法生成的稀疏标注缺乏详细的边界信息。其次,它们的策略侧重于硬样本以实现快速适应,从而导致遗忘和预测偏差。在这项工作中,我们提出了IMOST,这是一个由两个关键模块组成的持续可通行性学习框架:增量动态记忆(IDM)和自监督标注(SSA)。通过模拟人类记忆机制,IDM根据信息扩展准则将新数据样本分配到新聚类中。它还基于多样性规则更新聚类,确保对新场景的代表性表征。该机制增强了场景感知知识多样性,同时保持了紧凑的记忆容量。集成了FastSAM的SSA模块利用点提示实时生成完整标注,从而降低了训练复杂度。此外,IMOST已成功部署在四足机器人上,并在在线学习过程中评估了其性能。在公开和自收集数据集上的实验结果表明,我们的IMOST优于当前最先进的方法,在各种场景中保持稳健的识别能力和适应性。代码可在 https://github.com/SJTU-MKH/OCLTrav 获取。
英文摘要:
Traversability estimation is the foundation of path planning for a general navigation system. However, complex and dynamic environments pose challenges for the latest methods using self-supervised learning (SSL) technique. Firstly, existing SSL-based methods generate sparse annotations lacking detailed boundary information. Secondly, their strategies focus on hard samples for rapid adaptation, leading to forgetting and biased predictions. In this work, we propose IMOST, a continual traversability learning framework composed of two key modules: incremental dynamic memory (IDM) and self-supervised annotation (SSA). By mimicking human memory mechanisms, IDM allocates novel data samples to new clusters according to information expansion criterion. It also updates clusters based on diversity rule, ensuring a representative characterization of new scene. This mechanism enhances scene-aware knowledge diversity while maintaining a compact memory capacity. The SSA module, integrating FastSAM, utilizes point prompts to generate complete annotations in real time which reduces training complexity. Furthermore, IMOST has been successfully deployed on the quadruped robot, with performance evaluated during the online learning process. Experimental results on both public and self-collected datasets demonstrate that our IMOST outperforms current state-of-the-art method, maintains robust recognition capabilities and adaptability across various scenarios. The code is available at https://github.com/SJTU-MKH/OCLTrav.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。