{"version":1,"issue":{"week":"2026-W44","title":"Inspection planning, distributed lunar SLAM, and gaze-driven teleoperation","intro":"IAC season brings a cluster of on-orbit servicing planners built on reinforcement learning and POMDPs. On the surface side: a field-tested multi-robot SLAM stack for planetary missions, plus new tools for rover adaptation and lunar digital twins.","curator":"Space Robots","publishedAt":"2026-11-02","url":"https://space-robots.org/papers/top/2026-W44/","picks":[{"rank":1,"note":"A QR-DQN agent picks which target a low-thrust servicer should inspect next in LEO. Because it learns the full return distribution, operators can trade expected value against risk at each step.","paper":{"id":"2610.41647","title":"Risk-Sensitive Mission Planning for Multi-Target On-Orbit Inspection via Distributional Reinforcement Learning","authors":["Adam Abdin"],"abstract":"Multi-target on-orbit servicing missions require planning tools that can adapt to evolving operational conditions while accounting for the outcome variability inherent to safety-critical spaceflight. This paper presents an adaptive planning approach for multi-target servicing campaigns in low Earth orbit and applies it to inspection missions flown by a low-thrust servicer. The approach is based on Distributional Reinforcement Learning, which learns the full distribution of mission returns and thereby supports explicit risk-sensitive decision-making at each planning step. Specifically, a Quantile-Regression Deep Q-Network (QR-DQN) agent selects which target to inspect next by jointly considering the expectation and the variance of the predicted return through a mean-variance criterion. The mission environment models circular orbits with a spread in inclination and uses Edelbaum's combined-manoeuvre low-thrust transfer estimates. The observation comprises the orbital elements, the visit history, the observed risk state of each target and the remaining mission-time budget. The risk state of each target changes stochastically during the campaign, making the outcome of an inspection uncertain and creating operationally meaningful distinctions between risk-neutral and risk-averse planning strategies. Because the mission-time budget generally admits only a subset of the candidate targets, the planner must also select which targets to inspect. Numerical experiments on scenarios with five target satellites show that one risk-aversion weight moves the policy across a range of mean return and return variance, over an unchanged environment and reward. Risk-averse agents reduce the variance of the episodic return by approximately one half relative to risk-neutral agents and lower the probability of a mission loss, at a cost in mean return. To validate the learned policies, the efficient frontier, which gives the highest mean return attainable at each level of return variance, is computed exactly by enumerating the admissible visit orders. At equal variance, the learned policies lie close to this frontier in mean return, and the risk-averse policies have a lower probability of a mission loss than the frontier policies.","published":"2026-10-30","addedAt":"2026-10-30","year":2026,"venue":{"id":"iac","label":"IAC 2026","year":2026,"isWorkshop":false,"raw":"77th International Astronautical Congress (IAC), International Astronautical Federation (IAF), Oct 2026, Antalya (Turkey), Turkey"},"intersection":"ai","domains":[{"id":"orbital-robotics","label":"ORBITAL ROBOTICS"},{"id":"in-space-servicing","label":"IN-SPACE SERVICING"}],"techniques":[{"id":"autonomy-ops","code":"T10","label":"Autonomy, Task Planning & Operations","source":"text","via":["arxiv:cs.AI","title:mission planning"]},{"id":"gnc","code":"T7","label":"Guidance, Dynamics & Control","source":"official","via":["arxiv:math.OC"]},{"id":"learning","code":"T8","label":"Learning-based Methods","source":"text","via":["title:reinforcement learning"]}],"missions":[],"indexedAs":{"arxiv":["cs.AI","math.OC"],"openalexTopics":[],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // SPACE AI & AUTONOMY","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2610.41647","arxiv":"https://arxiv.org/abs/2610.41647","pdf":"https://arxiv.org/pdf/2610.41647","html":"https://arxiv.org/html/2610.41647","doi":null,"code":null,"project":null}}},{"rank":2,"note":"Viewpoint selection around a target spacecraft, framed as a constrained MDP and solved with Lagrangian PPO. Transfers are checked against Clohessy–Wiltshire relative-motion dynamics.","paper":{"id":"2610.41639","title":"Chance-Constrained Inspection Viewpoint Sequencing for On-Orbit Servicing via Safe Reinforcement Learning","authors":["Chloé Carer","Adam Abdin"],"abstract":"Autonomous inspection of a target spacecraft is typically the initial step in on-orbit servicing. Planning close-proximity observation viewpoints involves a complex combinatorial problem constrained by coverage, fuel, and safety considerations. This paper models the viewpoint selection as a Constrained Markov Decision Process (CMDP) and applies Proximal Policy Optimization with Lagrangian relaxation to solve it. The system combines a high-level planner, which sequences camera viewpoints on an observation sphere around the target, with a low-level model that assesses each transfer using the Clohessy--Wiltshire (CW) equations for relative motion. The deterministic constraints on single-impulse reachability and $\\Delta v$ cap are enforced directly on the action set. Safety margins are affected by navigation and manoeuvre errors, making the actual clearance stochastic. To address this, a chance constraint on the realised trajectory is implemented, with a Lagrangian multiplier governed by PID control to adapt the penalty during training. The approach is tested on a Galileo-class navigation satellite in medium Earth orbit, modelled as a point cloud where visibility from each viewpoint considers field-of-view and line-of-sight occlusion. Across various risk budgets, the trained policy maintains the keep-out violation rate within the specified limit, achieving coverage close to its maximum and staying within the mission $\\Delta v$ budget. Compared to the usual practice of applying a fixed margin to the keep-out radius and planning deterministically, the chance-constrained policy attains less than half the violation rate at comparable coverage. This makes the collision risk an explicit design parameter, eliminating the need for re-tuning per case. The learned policy selects a viewpoint without the repeated Monte Carlo risk estimates required by a greedy, chance-constrained planner at every decision point.","published":"2026-10-30","addedAt":"2026-10-30","year":2026,"venue":{"id":"iac","label":"IAC 2026","year":2026,"isWorkshop":false,"raw":"77th International Astronautical Congress (IAC), International Astronautical Federation (IAF), Oct 2026, Antalya (TR), Turkey"},"intersection":"both","domains":[{"id":"in-space-servicing","label":"IN-SPACE SERVICING"},{"id":"orbital-robotics","label":"ORBITAL ROBOTICS"}],"techniques":[{"id":"gnc","code":"T7","label":"Guidance, Dynamics & Control","source":"official","via":["arxiv:math.OC"]},{"id":"learning","code":"T8","label":"Learning-based Methods","source":"text","via":["title:reinforcement learning"]}],"missions":[],"indexedAs":{"arxiv":["cs.AI","math.OC"],"openalexTopics":[],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // IN-SPACE SERVICING","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2610.41639","arxiv":"https://arxiv.org/abs/2610.41639","pdf":"https://arxiv.org/pdf/2610.41639","html":"https://arxiv.org/html/2610.41639","doi":null,"code":null,"project":null}}},{"rank":3,"note":"Distributed multi-robot LiDAR SLAM sized to the communication and compute budgets of real planetary missions. Deployed at analog sites for both cave and surface exploration concepts.","paper":{"id":"2610.38141","title":"SKiD-SLAM: Resource-Aware Distributed Multi-Robot LiDAR SLAM for Planetary Missions with Field Deployments at Analog Sites","authors":["Hogyun Kim","Juwon Kim","Dongjin Cho","Jiwon Choi","Geonmo Yang","Seokhwan Jeong","Jiyun Lee","Miryeong Park","Hyungtae Lim","Younggun Cho"],"abstract":"Future planetary exploration missions require teams of robots to collaboratively map unknown environments under severe communication limits, constrained onboard computation, and no central infrastructure. In this field report, we present SKiD-SLAM, a distributed multi-robot LiDAR simultaneous localization and mapping (SLAM) system for such environments, and report its deployment across two mission concepts: cave exploration and scientific surface exploration. We survey the communication and computation budgets of actual planetary missions and select modules that fit these budgets for inter-robot place recognition, relative pose estimation, and distributed trajectory fusion. Before field deployment, we verify the assembled system on public datasets resembling planetary environments and in a simulator built on NASA JPL's Open Source Rover. We then validate SKiD-SLAM through field deployments in South Korea: a team of wheeled rovers explores the Majang lava-tube cave on Jeju Island, and quadruped robots carry out a crater-and-rock science scenario on a planetary analog terrain at the Korea Institute of Civil Engineering and Building Technology (KICT) in Yeoncheon. Across both deployments, SKiD-SLAM reliably performed distributed multi-robot LiDAR SLAM within a 250 kbps inter-robot communication budget, demonstrating its feasibility under challenging field conditions. Supplementary materials, including code and field data, are available at https://sparolab.github.io/research/skid_slam/.","published":"2026-10-28","addedAt":"2026-10-28","year":2026,"venue":{"id":"jfr","label":"JFR / Field Robotics 2026","year":2026,"isWorkshop":false,"raw":"IEEE transactions on field robotics."},"intersection":"robotics","domains":[{"id":"planetary-robotics","label":"PLANETARY ROBOTICS"}],"techniques":[{"id":"perception","code":"T5","label":"Perception & State Estimation","source":"official","via":["openalex-topic:Robotics and Sensor-Based Localization","openalex-keyword:multi-robot SLAM","openalex-keyword:LiDAR SLAM","openalex-keyword:distributed SLAM"]},{"id":"multi-robot","code":"T12","label":"Multi-Robot & Swarms","source":"official","via":["openalex-keyword:multi-robot SLAM","title:multi-robot","abstract:multi-robot"]},{"id":"simulation-testbeds","code":"T13","label":"Simulation, Digital Twins & Benchmarks","source":"text","via":["title:analog site","abstract:dataset","abstract:simulator"]}],"missions":[],"indexedAs":{"arxiv":["cs.RO"],"openalexTopics":[{"id":"T10191","name":"Robotics and Sensor-Based Localization","score":0.999},{"id":"T10586","name":"Robotic Path Planning Algorithms","score":0},{"id":"T10462","name":"Reinforcement Learning in Robotics","score":0}],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // PLANETARY ROBOTICS","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2610.38141","arxiv":"https://arxiv.org/abs/2610.38141","pdf":"https://arxiv.org/pdf/2610.38141","html":"https://arxiv.org/html/2610.38141","doi":"https://doi.org/10.1109/tfr.2026.3721725","code":null,"project":"https://sparolab.github.io/research/skid_slam/"}}},{"rank":4,"note":"Gaze nominates a rock or placement target, the operator confirms, and the rover arm executes a bounded grasp-and-place. Evaluated against joystick teleoperation in a 16-participant mission-analog VR study.","paper":{"id":"2610.39998","title":"Gaze-Assisted Supervisory Control for Lunar Robotic Arm Teleoperation Under Concurrent Monitoring","authors":["Jiayu He","Yifan Li","Oliver R. Runswick","Ernest N. Kamavuako","Yunjie Jia","Peter D. Hodkinson","Yang Gao"],"abstract":"Rover-mounted robotic arms can extend human reach during lunar sample handling, but continuous joystick teleoperation requires repeated visual-motor alignment while operators may also need to monitor system states. This paper presents a gaze-assisted supervisory control framework in which gaze nominates a rock or placement target, explicit confirmation authorizes the action, and the robot performs bounded autonomous grasp-and-place execution. The framework was evaluated against manual joystick teleoperation in a mission-analog virtual reality study with 16 participants. The study used a 2 x 2 x 3 within-subject design varying control mode, placement difficulty, and concurrent monitoring load. Mean recorded task completion time decreased from 47.65 to 18.43 s per rock, with 72.5% of this difference arising during grasping. Under the tested auditory monitoring conditions, gaze-assisted supervisory control showed less average proportional slowing, with no detected control-mode difference in monitoring-response accuracy or speed. The rate of gaze shifts between core areas of interest decreased from 49.98 to 27.73 shifts/min, while the raw NASA Task Load Index score decreased from 32.54 to 18.26. However, the benefit was task dependent. In precision placement, manual control yielded lower mean placement error and a higher placement success rate. These findings support a mixed-initiative allocation in which gaze enables rapid task-level intention specification and autonomous execution, while precision-critical stages retain manual refinement.","published":"2026-10-29","addedAt":"2026-10-29","year":2026,"venue":{"id":"preprint","label":"Preprint","year":null,"isWorkshop":false,"raw":null},"intersection":"robotics","domains":[],"techniques":[{"id":"hri-teleoperation","code":"T11","label":"HRI & Teleoperation","source":"official","via":["openalex-topic:Teleoperation and Haptic Systems","openalex-topic:Human-Automation Interaction and Safety","openalex-keyword:virtual reality simulation","title:teleoperat"]},{"id":"manipulation","code":"T1","label":"Manipulation & Grasping","source":"text","via":["title:robotic arm","abstract:robotic arm","abstract:sample handling"]}],"missions":[],"indexedAs":{"arxiv":["cs.RO"],"openalexTopics":[{"id":"T11687","name":"Teleoperation and Haptic Systems","score":0.906},{"id":"T10525","name":"Human-Automation Interaction and Safety","score":0.051},{"id":"T11707","name":"Gaze Tracking and Assistive Technology","score":0.007}],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // HUMAN-ROBOT TEAMING","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2610.39998","arxiv":"https://arxiv.org/abs/2610.39998","pdf":"https://arxiv.org/pdf/2610.39998","html":"https://arxiv.org/html/2610.39998","doi":null,"code":null,"project":null}}},{"rank":5,"note":"TERRA adapts a simulation-trained world model on deformable terrain by seeking out deployment data where task-relevant model errors are likely. Fewer trial-and-error drives for planetary rovers.","paper":{"id":"2610.38657","title":"Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation","authors":["Jacob Levy","Arthur Bouton","Tristan D. Hassler","Hari Nayar","David Fridovich-Keil"],"abstract":"Future planetary rovers will traverse steep, deformable terrain where slip, sinkage, and terrain deformation can threaten mobility. Although simulation can capture some wheel-soil effects, unmodeled deformable-terrain phenomena create sim-to-real gaps requiring deployment-time adaptation. Yet, rover operations leave little room for extensive trial-and-error. We introduce TERRA (Targeted Exploration for Reward-Relevant Adaptation), an online adaptation framework that efficiently seeks deployment data exposing task-relevant model errors and corrects them. TERRA adapts a simulation-trained world model with a reward-weighted prediction loss and trains a loss predictor to estimate where future performance-relevant errors are likely to occur, using this signal to guide exploration during MPC. In simulation, TERRA reaches approximately 90% slope-climbing success within five trials under severe out-of-distribution pretraining conditions, outperforming exploration baselines in reward, completion time, and energy to first success. On the ERNEST rover, TERRA recovers coordinated active-suspension locomotion on a deformable Mars-simulant slope within three to five real-world trials. Project website: https://terra-explore.github.io","published":"2026-10-28","addedAt":"2026-10-28","year":2026,"venue":{"id":"corl","label":"CoRL 2026","year":2026,"isWorkshop":false,"raw":null},"intersection":"both","domains":[{"id":"planetary-robotics","label":"PLANETARY ROBOTICS"}],"techniques":[{"id":"surface-mobility","code":"T2","label":"Surface Mobility & Terramechanics","source":"official","via":["openalex-topic:Soil Mechanics and Vehicle Dynamics","openalex-keyword:wheel-soil interaction","openalex-keyword:slope climbing","abstract:slip"]},{"id":"learning","code":"T8","label":"Learning-based Methods","source":"official","via":["arxiv:cs.LG","openalex-topic:Reinforcement Learning in Robotics","openalex-keyword:sim-to-real gap"]},{"id":"perception","code":"T5","label":"Perception & State Estimation","source":"official","via":["openalex-topic:Robotics and Sensor-Based Localization"]}],"missions":[],"indexedAs":{"arxiv":["cs.RO","cs.AI","cs.LG"],"openalexTopics":[{"id":"T10462","name":"Reinforcement Learning in Robotics","score":0.995},{"id":"T11978","name":"Soil Mechanics and Vehicle Dynamics","score":0.004},{"id":"T10191","name":"Robotics and Sensor-Based Localization","score":0.001}],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // PLANETARY ROBOTICS","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2610.38657","arxiv":"https://arxiv.org/abs/2610.38657","pdf":"https://arxiv.org/pdf/2610.38657","html":"https://arxiv.org/html/2610.38657","doi":null,"code":null,"project":null}}},{"rank":6,"note":"MAP state reconstruction for a hybrid manipulator whose distal link is a tendon-driven continuum robot. The aim is compliant, low-stowage servicing arms.","paper":{"id":"2610.37043","title":"State estimation for a hybrid rigid-continuum space manipulator system","authors":["Lorenzo Ticozzi","Patricio A. Vela","and Panagiotis Tsiotras"],"abstract":"Spacecraft-mounted robotic manipulators can support long-term operability of orbiting assets by conducting tasks such as on-orbit assembly, repair, upgrade, and refueling. In this context, the integration of continuum/soft robotic mechanisms into space manipulator designs promises to reduce stowage volume and mass, as well as to improve operational safety through the inherent mechanical compliance of soft structures. This work presents a novel state reconstruction pipeline for a hybrid soft-rigid space manipulator, in which the distal link is a tendon-driven continuum robot. The estimation problem is formulated as a maximum a posteriori (MAP) inference problem over the hybrid manipulator's configuration, conditioned on discrete, noisy measurements from joint encoders and a vision-based sensing pipeline. The resulting soft-constrained optimization problem is transcribed as a factor graph, providing a compact representation for fusing heterogeneous measurements with the rigid-soft kinematic model. Furthermore, the adoption of the Geometric Variable Strain (GVS) approach yields a minimum-order parameterization of the configuration, a property expected to facilitate model-based feedback control design in future work. The proposed implementation is validated in simulation on a closed-loop trajectory where, for better realism, position measurements for the continuum link are obtained by means of a simulated visual pipeline leveraging synthetic photorealistic images. The state reconstruction accuracy and computational performance confirm the potential of the proposed framework for hybrid soft-rigid robotic applications in orbit.","published":"2026-10-27","addedAt":"2026-10-27","year":2026,"venue":{"id":"preprint","label":"Preprint","year":null,"isWorkshop":false,"raw":null},"intersection":"robotics","domains":[{"id":"orbital-robotics","label":"ORBITAL ROBOTICS"},{"id":"in-space-servicing","label":"IN-SPACE SERVICING"}],"techniques":[{"id":"manipulation","code":"T1","label":"Manipulation & Grasping","source":"official","via":["openalex-keyword:space manipulators","title:space manipulator","abstract:manipulat","abstract:space manipulator"]},{"id":"perception","code":"T5","label":"Perception & State Estimation","source":"official","via":["openalex-keyword:state estimation","title:state estimation"]},{"id":"design-hardware","code":"T14","label":"Design, Mechanisms & Hardware","source":"official","via":["openalex-topic:Soft Robotics and Applications","abstract:soft robot","abstract:tendon"]}],"missions":[],"indexedAs":{"arxiv":["cs.RO"],"openalexTopics":[{"id":"T10868","name":"Soft Robotics and Applications","score":0.94},{"id":"T11701","name":"Space Satellite Systems and Control","score":0.027},{"id":"T10571","name":"Robotic Mechanisms and Dynamics","score":0.021}],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // ORBITAL ROBOTICS","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2610.37043","arxiv":"https://arxiv.org/abs/2610.37043","pdf":"https://arxiv.org/pdf/2610.37043","html":"https://arxiv.org/html/2610.37043","doi":null,"code":null,"project":null}}},{"rank":7,"note":"Sixteen visual place recognition datasets from Moon and Mars analog sites, with a benchmark showing where current loop-closure methods break down in feature-poor terrain.","paper":{"id":"2610.35642","title":"VPR-Space: A Benchmark for Visual Place Recognition in Space Analog Domains","authors":["Richard Fechner","Peer Neubert"],"abstract":"Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-of-the-art VPR and SLAM approaches excel in urban and feature-rich natural environments, the vast and feature-poor environments of extraterrestrial surfaces like on the Moon or Mars pose severe challenges for existing approaches. This paper presents a novel benchmark, VPR-Space, to evaluate VPR capabilities on extraterrestrial surfaces. There are three contributions: (1) We collected sixteen VPR database-query datasets based on existing data from Space Analog Domains (SAD), terrestrial environments that resemble properties of the Moon or Mars. The collection includes a range of challenges regarding environment, viewpoint change, and illumination conditions. (2) To address the ill-posed nature of VPR, we propose a novel approach to generate the ground-truth information in VPR benchmarks. Instead of defining that a query and datbase image show the same place if and only if their camera poses are within fixed position and viewing direction thresholds, we propose to make the decision dependent on whether the match would be valuable in the downstream SLAM task. To avoid the overhead and restrictions of evaluating VPR in-the-loop within SLAM systems, we provide VPR ground-truth (GT) matrices based on the performance of an ensemble of state-of-the-art Relative Pose Estimators (RPE). Under this GT we require a VPR method to identify exactly those image pairs for which a subsequently applied RPE is expected to provide a valuable pose estimate in a SLAM context. (3) We evaluated nine state-of-the-art VPR approaches. The results show considerable room for improvement and indicate directions for future research. We provide a pre-release version of the dataset on github: $\\texttt{https://github.com/rfechner/VPR-Space}$","published":"2026-10-26","addedAt":"2026-10-26","year":2026,"venue":{"id":"preprint","label":"Preprint","year":null,"isWorkshop":false,"raw":null},"intersection":"both","domains":[],"techniques":[{"id":"perception","code":"T5","label":"Perception & State Estimation","source":"official","via":["arxiv:cs.CV","openalex-topic:Robotics and Sensor-Based Localization","openalex-topic:Advanced Image and Video Retrieval Techniques","openalex-keyword:visual SLAM"]},{"id":"simulation-testbeds","code":"T13","label":"Simulation, Digital Twins & Benchmarks","source":"text","via":["title:benchmark","abstract:benchmark","abstract:dataset"]}],"missions":[],"indexedAs":{"arxiv":["cs.RO","cs.CV"],"openalexTopics":[{"id":"T10191","name":"Robotics and Sensor-Based Localization","score":1},{"id":"T10627","name":"Advanced Image and Video Retrieval Techniques","score":0},{"id":"T11211","name":"3D Surveying and Cultural Heritage","score":0}],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // SPACE AI & AUTONOMY","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2610.35642","arxiv":"https://arxiv.org/abs/2610.35642","pdf":"https://arxiv.org/pdf/2610.35642","html":"https://arxiv.org/html/2610.35642","doi":null,"code":"https://github.com/rfechner/VPR-Space","project":null}}},{"rank":8,"note":"Benchmarks six 3D Gaussian Splatting variants on lunar analog scenes. Traversal effects such as motion blur and lofted-regolith haze cause digital-twin accuracy to diverge from test-set novel-view metrics.","paper":{"id":"2611.00870","title":"A Reproducible Reconstruction and Evaluation Framework for Photorealistic Lunar Analog Scene Reconstruction Toward Digital Twins","authors":["Antar Mazumder","Ryan Hartzell","Luke Boyd","Alexander Robinson","Neha Sharma","Chance Carnival","Frances Zhu"],"abstract":"In this paper, we present a reconstruction pipeline that empirically quantifies the photorealistic scene reconstruction accuracy from both human-controlled and rover mast camera monocular feeds against physical ground truth as a function of Lunar traversal effects (e.g., motion blur, haze due to lofted regolith, trajectory bias, and sparse views). First, we benchmark six variants of 3D Gaussian Splatting (3DGS) across three Lunar analog scenes on held-out test sets using standard photometric metrics. We then establish how under traversal effects, this test-set-specific Novel View Synthesis (NVS) performance does not proportionally scale to the same photometric metrics in the reconstructed DTs. Our results quantify that splat training metrics alone are insufficient predictors of Cross-Reconstruction Photorealistic NVS Fidelity (CRPNVS), and that factors such as rover trajectory bias and geometric scene coverage play a critical role in determining the photorealistic quality of the reconstructed scenes targeting Lunar analog Digital Twins. Additionally, we pilot study Coverage Score ($S_c$), a geometry-based diagnostic derived from COLMAP poses and point cloud structure that provides a meaningful heuristic about the highest achievable CRPNVS structural fidelity, independently of splat training performance in the absence of a human-controlled reference. These findings establish a standardized, human control-referenced evaluation pipeline for photorealistic scene reconstruction for Lunar-analog Digital Twin development and future planetary exploration. Code and project page: https://rose-lab-admin.github.io/rose-lunar-dt-rec","published":"2026-10-31","addedAt":"2026-10-31","year":2026,"venue":{"id":"preprint","label":"Preprint","year":null,"isWorkshop":false,"raw":null},"intersection":"robotics","domains":[{"id":"planetary-robotics","label":"PLANETARY ROBOTICS"}],"techniques":[{"id":"simulation-testbeds","code":"T13","label":"Simulation, Digital Twins & Benchmarks","source":"text","via":["title:digital twin","abstract:benchmark","abstract:digital twin"]}],"missions":[],"indexedAs":{"arxiv":["cs.RO"],"openalexTopics":[],"ntrsSubjects":[],"ieeeTerms":[]},"cardTag":"RESEARCH // TESTBEDS & SIMULATION","citations":0,"links":{"page":"https://space-robots.org/papers/paper/2611.00870","arxiv":"https://arxiv.org/abs/2611.00870","pdf":"https://arxiv.org/pdf/2611.00870","html":"https://arxiv.org/html/2611.00870","doi":null,"code":null,"project":null}}}]},"weeks":["2026-W44","2026-W43"]}