← 研踪 PaperTrailarXiv:2611.15296 · v1
APG-Planner: Learning Vision-Based High-Speed Trajectory Planning via Analytic Policy Gradient
首次提交 2026-11-11 18:28
版本更新 2026-11-11 18:28
雷达观测 2026-11-13 11:11
摘要
Vision-based high-speed navigation requires a trajectory planner that can reactively generate smooth, collision-free trajectories from onboard visual observations. Deep reinforcement learning offers a promising approach to vision-based trajectory planning, as it enables the optimization of sequential decision-making policies in complex environments. However, model-free policy gradient methods rely on sample-based policy gradient estimation, which yields noisy gradient estimates and inefficient training. To this end, we propose a framework for learning trajectory planning policies using the analytic policy gradient (APG) method and use it to train APG-Planner, a vision-based high-speed trajectory planner. The proposed framework leverages differential flatness to analytically reconstruct vehicle states from planned trajectories, thereby enabling differentiable trajectory-level state transitions without requiring an explicit low-level dynamics model. By iteratively performing trajectory planning and differentiable state transitions, we construct a differentiable episode rollout and analytically compute policy gradients from episode-level losses, improving both training efficiency and policy performance. After approximately 30 minutes of training on a single GPU, APG-Planner demonstrates comparable or superior performance to existing baseline methods in simulation and achieves speeds of up to 11\,m/s in real-world flight experiments. We further validate the proposed framework on a skid-steer ground robot, demonstrating its applicability to differentially flat robotic systems beyond quadrotors.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-11 18:28 · 最新观测版本
APG-Planner: Learning Vision-Based High-Speed Trajectory Planning via Analytic Policy Gradient
Vision-based high-speed navigation requires a trajectory planner that can reactively generate smooth, collision-free trajectories from onboard visual observations. Deep reinforcement learning offers a promising approach to vision-based trajectory planning, as it enables the optimization of sequential decision-making policies in complex environments. However, model-free policy gradient methods rely on sample-based policy gradient estimation, which yields noisy gradient estimates and inefficient training. To this end, we propose a framework for learning trajectory planning policies using the analytic policy gradient (APG) method and use it to train APG-Planner, a vision-based high-speed trajectory planner. The proposed framework leverages differential flatness to analytically reconstruct vehicle states from planned trajectories, thereby enabling differentiable trajectory-level state transitions without requiring an explicit low-level dynamics model. By iteratively performing trajectory planning and differentiable state transitions, we construct a differentiable episode rollout and analytically compute policy gradients from episode-level losses, improving both training efficiency and policy performance. After approximately 30 minutes of training on a single GPU, APG-Planner demonstrates comparable or superior performance to existing baseline methods in simulation and achieves speeds of up to 11\,m/s in real-world flight experiments. We further validate the proposed framework on a skid-steer ground robot, demonstrating its applicability to differentially flat robotic systems beyond quadrotors.
查看此版本解读 →查看此版本原文 ↗