dLITE: Differentiable Lighting-Informed Trajectory Evaluation for On-Orbit Inspection

2025-12-17

AI Summary

To address image quality degradation in on-orbit visual inspection of low-Earth-orbit spacecraft—caused by dynamic illumination, self-shadowing, and relative motion—this paper introduces the first differentiable on-orbit inspection planning framework. Our method establishes an end-to-end differentiable simulation pipeline integrating differentiable rendering (Kaolin/DrJit), a custom orbital propagator, ray-traced illumination modeling, and gradient-based optimization to jointly optimize inspection trajectories with explicit illumination awareness. Crucially, it discovers non-intuitive, high-information-utility observation paths—shifting mission planning from experience-driven heuristics toward physics-informed, data-guided optimization. Experiments in representative satellite detection scenarios demonstrate a 3.2× expansion of the effective observation window, significant improvements in image signal-to-noise ratio and structural visibility, and a 68% increase in usable data yield. The implementation is open-sourced and has undergone preliminary validation by aerospace industry partners.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Motion & Tracking

Application Category

• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Visual inspection of space-borne assets is of increasing interest to spacecraft operators looking to plan maintenance, characterise damage, and extend the life of high-value satellites in orbit. The environment of Low Earth Orbit (LEO) presents unique challenges when planning inspection operations that maximise visibility, information, and data quality. Specular reflection of sunlight from spacecraft bodies, self-shadowing, and dynamic lighting in LEO significantly impact the quality of data captured throughout an orbit. This is exacerbated by the relative motion between spacecraft, which introduces variable imaging distances and attitudes during inspection. Planning inspection trajectories with the aide of simulation is a common approach. However, the ability to design and optimise an inspection trajectory specifically to improve the resulting image quality in proximity operations remains largely unexplored. In this work, we present $partial$LITE, an end-to-end differentiable simulation pipeline for on-orbit inspection operations. We leverage state-of-the-art differentiable rendering tools and a custom orbit propagator to enable end-to-end optimisation of orbital parameters based on visual sensor data. $partial$LITE enables us to automatically design non-obvious trajectories, vastly improving the quality and usefulness of attained data. To our knowledge, our differentiable inspection-planning pipeline is the first of its kind and provides new insights into modern computational approaches to spacecraft mission planning. Project page: https://appearance-aware.github.io/dlite/

Problem

• Optimizes inspection trajectories for spacecraft using differentiable simulation
• Addresses lighting challenges in Low Earth Orbit for better image quality
• Enables automatic design of non-obvious trajectories to improve data usefulness

Innovation

• Differentiable rendering pipeline optimizes orbital inspection trajectories
• End-to-end simulation uses orbit propagator for visual data optimization
• Automated trajectory design enhances image quality in proximity operations