Vision-Guided Optic Flow Navigation for Small Lunar Missions

2025-11-21

AI Summary

To address the challenge of achieving robust autonomous navigation for small lunar landers under stringent constraints on mass, power, and onboard computational resources, this paper proposes a lightweight visual optical flow-based motion estimation framework. The method innovatively integrates the classical pyramid Lucas-Kanade sparse optical flow algorithm with terrain-aware depth models—specifically planar and spherical geometries tailored to lunar landing scenarios—and incorporates parametric constraints from laser altimeter measurements to regularize motion field inversion. Implemented entirely on a CPU without requiring GPU or specialized hardware, the framework achieves real-time performance. Evaluated on synthetic imagery simulating complex lunar south-polar terrain, it attains velocity estimation errors below 10% in challenging topographies and under 1% in representative terrains—substantially outperforming existing lightweight approaches. This work establishes a new paradigm for high-accuracy, low-overhead, and robust autonomous navigation for resource-constrained lunar landers.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Private lunar missions are faced with the challenge of robust autonomous navigation while operating under stringent constraints on mass, power, and computational resources. This work proposes a motion-field inversion framework that uses optical flow and rangefinder-based depth estimation as a lightweight CPU-based solution for egomotion estimation during lunar descent. We extend classical optical flow formulations by integrating them with depth modeling strategies tailored to the geometry for lunar/planetary approach, descent, and landing, specifically, planar and spherical terrain approximations parameterized by a laser rangefinder. Motion field inversion is performed through a least-squares framework, using sparse optical flow features extracted via the pyramidal Lucas-Kanade algorithm. We verify our approach using synthetically generated lunar images over the challenging terrain of the lunar south pole, using CPU budgets compatible with small lunar landers. The results demonstrate accurate velocity estimation from approach to landing, with sub-10% error for complex terrain and on the order of 1% for more typical terrain, as well as performances suitable for real-time applications. This framework shows promise for enabling robust, lightweight on-board navigation for small lunar missions.

Problem

• Autonomous navigation under mass and power constraints
• Egomotion estimation using optical flow and depth modeling
• Real-time velocity estimation for lunar landing missions

Innovation

• Motion-field inversion framework for lunar descent navigation
• Integrates optical flow with rangefinder-based depth modeling
• CPU-based solution using sparse optical flow features