aiqbench analysis
The paper proposes a two-stage learning framework for drone (AAV) trajectory planning that builds safety gradient fields from camera-based polar occupancy maps, treating static and dynamic obstacles alike. Its claims of superiority and real-time onboard performance rest on comparisons and real-world tests, so readers should check the benchmarks and compute requirements against their own constraints. For AI readers, the notable element is the ESDF-guided offline learning and self-supervised policy training, which trade heavy obstacle tracking for learned, geometry-informed guidance.
From Field to Planning: Learning Temporal Polar Gradient Fields for Vision-based AAV Trajectory Planning in Dynamic Environments
arXiv:2610.14482v1 Announce Type: new Abstract: Autonomous Aerial Vehicle (AAV) trajectory planning requires real-time and accurate safety gradient guidance, especially in dynamic environments. Existing methods typically rely on static maps and dynamic obstacle tracking to construct gradient fields, imposing heavy computational burdens and yielding conservative trajectories. To address these limitations, we propose a two-stage Field-to-Planning (F2P) learning framework to provide accurate and efficient safety gradients for trajectory planning in dynamic environments. In the first stage, we introduce an Ego-centric Polar Occupancy (EPO) representation that naturally matches the geometry of the onboard camera frustum, while supporting unstructured scene modeling. Subsequently, we formulate a Temporal Polar Gradient Field (TPGF) via multi-kernel separable Gaussian convolution to provide unified safety gradients, without explicitly distinguishing between static and dynamic obstacles. To mitigate the inherent spatial ambiguity introduced by applying convolutions within the polar grid, we propose an ESDF-guided offline learning strategy that incorporates geometric priors into TPGF. In the second stage, we employ the calibrated TPGF to guide the trajectory planning policy in a self-supervised learning manner. Comparative results with other approaches demonstrate the superiority of our method. Extensive real-world experiments within various cluttered dynamic environments validate the real-time performance and robustness on resource-constrained onboard systems.
Abstract:Autonomous Aerial Vehicle (AAV) trajectory planning requires real-time and accurate safety gradient guidance, especially in dynamic environments. Existing methods typically rely on static maps and dynamic obstacle tracking to construct gradient fields, imposing heavy computational burdens and yielding conservative trajectories. To address these limitations, we propose a two-stage Field-to-Planning (F2P) learning framework to provide accurate and efficient safety gradients for trajectory planning in dynamic environments. In the first stage, we introduce an Ego-centric Polar Occupancy (EPO) representation that naturally matches the geometry of the onboard camera frustum, while supporting unstructured scene modeling. Subsequently, we formulate a Temporal Polar Gradient Field (TPGF) via multi-kernel separable Gaussian convolution to provide unified safety gradients, without explicitly distinguishing between static and dynamic obstacles. To mitigate the inherent spatial ambiguity introduced by applying convolutions within the polar grid, we propose an ESDF-guided offline learning strategy that incorporates geometric priors into TPGF. In the second stage, we employ the calibrated TPGF to guide the trajectory planning policy in a self-supervised learning manner. Comparative results with other approaches demonstrate the superiority of our method. Extensive real-world experiments within various cluttered dynamic environments validate the real-time performance and robustness on resource-constrained onboard systems.
Robotics (cs.RO)
arXiv:2610.14482 [cs.RO]
(or arXiv:2610.14482v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.14482 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 288 words
Related coverage
Game Design Creativity evals
LessWrong · Oct 12, 2026
RiskFly: Frustum-Aligned Spatio-Temporal Risk Fields for One-Stage Agile Flight in Dynamic Clutter
arXiv · Oct 6, 2026
Links #5: 2026/07
LessWrong · Jul 31, 2026
RL & search is a terrifying way to build AGI (an FAQ)
AI Alignment Forum · Jul 27, 2026