外观
论文arXiv 2610.1611916 天前
用于安全四旋翼导航的约束可微策略学习
原文链接：Constrained Differentiable Policy Learning for Safe Quadrotor Navigation（arXiv 2610.16119 · 发布日期：2026-10-12）
Constrained Differentiable Policy Learning for Safe Quadrotor Navigation
针对四旋翼安全导航中惩罚权重需调参的问题，提出显式约束的可微策略学习，并在仿真、Gazebo/PX4和实体四旋翼验证。
核心要点
- 将避障作为显式约束，避免安全仅作加权惩罚时需手动权衡性能与约束。
- 通过可微仿真器进行原始-对偶梯度下降-上升，训练四旋翼策略。
- 提出有界净空约束与LME聚合，用单个对偶变量强调轨迹和批次中的关键违规。
- 实验证明较固定惩罚和现有基线有更好安全-性能权衡，并泛化到更密集分布外环境。
验证范围与局限：验证包括仿真实验、更密集分布外环境，以及零样本迁移到Gazebo/PX4和实体四旋翼。
英文摘要 (Abstract)
Differentiable simulation enables efficient policy optimization through analytic gradients, yet safety is commonly incorporated as a weighted penalty, requiring manual tuning of the trade-off between task performance and constraint satisfaction. We instead formulate obstacle avoidance as an explicit constraint and train quadrotor policies using primal--dual gradient descent--ascent through a differentiable simulator. We introduce two key components to enable effective constrained training. First, we propose a bounded clearance-based constraint function that provides informative gradients around the safety boundary while preventing large violations from destabilizing primal--dual optimization. Second, we introduce log-mean-exp (LME) aggregation to smoothly emphasize critical per-step safety violations across a trajectory and training batch within a single constraint governed by one dual variable. Together, these components enable the desired safety level to be specified directly while balancing constraint satisfaction and task completion. We theoretically prove that the proposed optimization with differentiable simulation converges to feasible policy under mild assumptions. Experiments demonstrate improved safety--performance trade-offs over fixed-penalty and existing policy-learning baselines, as well as generalization to denser out-of-distribution environments. Finally, the learned policy transfers zero-shot to Gazebo/PX4 and a physical quadrotor without additional fine-tuning.
作者：Yan Shuo Tan, Praveen Krishnapur, Zeyu Feng, Han Bao, Yew Soon Ong, Fan Shi
来源
本页事实对应的公开页面，以原文为准。