用强化学习实现无需标定物的鲁棒外参标定，支持弱运动场景。
L2Calib: $SE(3)$-Manifold Reinforcement Learning for Robust Extrinsic Calibration with Degenerate Motion Resilience
- 将外参标定转化为SE(3)流形上的决策问题，直接优化位姿提升里程计精度。
- 在无人机、无人车等平台验证，弱激励下仍达高精度，误差比传统方法低40%以上。
- 自动过滤无效数据，可从日常运行数据中在线标定，适合各类机器人部署。
外参标定对多传感器融合至关重要，现有方法依赖结构化靶标或全激励数据，限制了实际应用。在线标定还受弱激励影响，导致估计不可靠。为此，我们提出一种基于强化学习的外参标定框架，将标定问题建模为决策过程，直接优化SE(3)外参以提升里程计精度。采用概率Bingham分布建模3D旋转，确保优化稳定并天然保持四元数对称性。通过轨迹对齐奖励机制，无需结构化靶标即可定量评估紧耦合轨迹与参考轨迹的一致性。此外，自动化数据筛选模块剔除低信息量样本，显著提升大规模数据集下的效率与可扩展性。在无人机、无人车及手持设备上大量实验表明，本方法优于传统优化方法，在弱激励条件下仍能实现高精度标定。该框架通过消除高质量初始外参需求，支持从常规运行数据中在线标定，简化了在多样化机器人平台上的部署。代码已开源：https://github.com/APRIL-ZJU/learn-to-calibrate。
原文摘要 · Abstract (English)
Extrinsic calibration is essential for multi-sensor fusion, existing methods rely on structured targets or fully-excited data, limiting real-world applicability. Online calibration further suffers from weak excitation, leading to unreliable estimates. To address these limitations, we propose a reinforcement learning (RL)-based extrinsic calibration framework that formulates extrinsic calibration as a decision-making problem, directly optimizes $SE(3)$ extrinsics to enhance odometry accuracy. Our approach leverages a probabilistic Bingham distribution to model 3D rotations, ensuring stable optimization while inherently retaining quaternion symmetry. A trajectory alignment reward mechanism enables robust calibration without structured targets by quantitatively evaluating estimated tightly-coupled trajectory against a reference trajectory. Additionally, an automated data selection module filters uninformative samples, significantly improving efficiency and scalability for large-scale datasets. Extensive experiments on UAVs, UGVs, and handheld platforms demonstrate that our method outperforms traditional optimization-based approaches, achieving high-precision calibration even under weak excitation conditions. Our framework simplifies deployment on diverse robotic platforms by eliminating the need for high-quality initial extrinsics and enabling calibration from routine operating data. The code is available at https://github.com/APRIL-ZJU/learn-to-calibrate.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。