APG-Planner: Learning Vision-Based High-Speed Trajectory Planning via Analytic Policy Gradient
Abstract
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.
Figures & tables
| Parameter | Setting |
|---|---|
| Terminal bounds | : m; |
| : m/s; | |
| : m/s 2 (all axes) | |
| Depth input | pixels, clipped to m |
| Goal-vector threshold | m |
| Trajectory duration | s |
| Map Density | Method | Success Rate | Mean Speed (m/s) |
|---|---|---|---|
| Sparse | APG | 94% | 8.16 |
| APG w/o Temp. Grad. | 94% | 2.46 | |
| PPO | 60% | 5.14 | |
| Dense | APG | 92% | 7.47 |
| APG w/o Temp. Grad. | 88% | 2.05 | |
| PPO | 64% | 5.11 |
Motion Planning
Motion planning finds safe, feasible paths and trajectories for robots and vehicles amid geometric, dynamic, and task constraints.
See all 441 papers