CollisionSplatting: Collision-Aware Motion Planning in 3DGS Scenes with Image-Conditioned Objectives and Adjustable Conservatism

2026-09-28

AI Summary

This study addresses the limitations of geometric representations that discard visual information and vision models lacking geometric interpretability and computational efficiency in motion planning. We propose a joint visual-geometric planning framework integrating 3D Gaussian Splatting (3DGS) with probabilistic distance metrics. By designing a tunably conservative, GPU-accelerated distance metric, our approach unifies collision costs and image-space objectives within a single formulation, efficiently solved via MPPI and RRT algorithms to bridge the perception-planning gap. Experiments demonstrate that the proposed method achieves collision classification performance comparable to or exceeding baselines, while significantly improving detection throughput and substantially reducing GPU memory consumption. The framework is further validated on real-world navigation tasks.

Abstract

Incorporating dense visual information into motion planning remains challenging, as geometric planners rely on abstracted scene representations that discard visual richness, while learned visual models often lack geometric interpretability and computational efficiency. This paper introduces CollisionSplatting, a simple, modular, GPU-accelerated, probability-inspired distance metric with tunable conservatism that operates directly on standard 3D Gaussian Splatting (3DGS) scenes. When combined with learned image-conditioned reward functions, this metric enables joint geometric and visual planning by unifying collision-aware costs with image-space objectives. We integrate the metric into GPU-accelerated Model Predictive Path Integral (MPPI) and Rapidly-Exploring Random Tree (RRT) planners, and show on-par or better collision-classification performance compared to representative baselines while achieving substantially higher collision-checking throughput and significantly lower VRAM usage. Finally, we demonstrate the effectiveness of our metric in real-world vision-guided navigation and manipulation tasks, highlighting 3DGS as a practical bridge between rich perception and real-time motion planning.

Problem

• motion planning
• 3D Gaussian Splatting
• collision avoidance
• visual information
• GPU acceleration

Innovation

• 3D Gaussian Splatting
• Motion Planning
• Collision-Aware Distance Metric
• GPU Acceleration
• Image-Conditioned Objectives