Some Modifications to Our End-to-End UAV Planner

Published August 18, 2026 · Category: Robotics

Overview

arXiv:2608.15741v1 Announce Type: new Abstract: The one-stage planner YOPO maps a single depth image and the robot state directly to a set of candidate trajectories, trained by backpropagating through differentiable trajectory costs. This yields dense, geometrically informative supervision, but inherits the pathologies of soft-constrained optimization: the safety cost competes with the smoothness and goal-reaching terms, is non-convex across homotopy classes, and the single-piece polynomial is limited in expressiveness. In this report, we summarize several effective modifications. We adopt a two-piece MINCO parameterization, trading time for smoothness without altering the trajectory's spatial profile. We further lift YOPO's multi-modal prediction to span distinct homotopy classes, treating each motion primitive as a homotopy anchor that confines the trajectory to a feasible basin - without explicit safe-flight-corridor construction or front-end search. For dynamic feasibility, we impose barrier penalties on velocity and acceleration together with a curvature-dependent speed limit whose gradient acts only on the velocity, producing an adaptive-speed behavior that decelerates in cluttered regions or sharp turns. We replace score regression with a ranking loss, preventing small score errors from reordering the candidate set. These yield richer trajectory representations, safer obstacle avoidance, and more direct flight paths.

Source

Originally published at arxiv.org.

Related Articles

• From Continuous Design to Delay-Aware Discrete Synthesis: Guaranteed High-Bandwidth Joint Control for PMSM Drives
• StructRL: Structured Action-Space Exploration for Flow-Based VLAs
• Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models