PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation
2026-06-15 • Robotics
Robotics
AI summaryⓘ
The authors present PolyMerge, a method to simplify detailed 3D scene models into easier shapes called convex polytopes that cover obstacles safely. This simplification helps drones quickly plan paths to avoid collisions without needing heavy computing power. They show their approach working well on a small drone, maintaining safety while being faster than other methods. Their technique carefully balances between how safely it covers obstacles and how much computing it requires.
Obstacle avoidance3D Gaussian SplattingConvex polytopesPath planningControl barrier functionsOnboard perceptionCollision-free trajectoriesMotion planningReal-time computingDrone navigation
Authors
Jihoon Hong, Chih-Yuan Chiu, Sara Fridovich-Keil, Glen Chou
Abstract
Obstacle avoidance is essential for safe navigation and motion planning. Recent radiance field reconstruction methods enable object detection and modeling with high fidelity, but remain too memory- and compute-intensive for on-board perception-based path planning. To address these limitations, we propose PolyMerge to convert a large, photorealistic 3D Gaussian Splatting (3DGS) model of a scene into a lightweight representation of convex polytopes whose union provably over-approximates all obstacles in the original 3DGS model. PolyMerge tunes the polytope count to trade off conservativeness and compute cost, and integrates with control barrier functions (CBFs) to plan collision-free paths. We showcase PolyMerge in simulation and hardware experiments on a Crazyflie drone, which uses PolyMerge to compute and follow safe trajectories in real time under severe onboard compute constraints, outperforming baselines in speed while guaranteeing safety. For our code and videos, visit https://athlon76.github.io/PolyMerge-website/.