SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing

• URL: http://arxiv.org/abs/2604.14399v1
• Date: Wed, 15 Apr 2026 20:27:57 GMT
• Title: SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing
• Abstract summary: SpaceMind is a self-evolving vision-language model that decomposes knowledge, tools, and reasoning into three dimensions.<n>We validate SpaceMind through 192 closed-loop runs across five satellites, three task types, and two environments.<n>A self-evolution study shows that the agent recovers from failure in four of six groups from a single failed episode.
• Score: 1.614712872796152
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous on-orbit servicing demands embodied agents that perceive through visual sensors, reason about 3D spatial situations, and execute multi-phase tasks over extended horizons. We present SpaceMind, a modular and self-evolving vision-language model (VLM) agent framework that decomposes knowledge, tools, and reasoning into three independently extensible dimensions: skill modules with dynamic routing, Model Context Protocol (MCP) tools with configurable profiles, and injectable reasoning-mode skills. An MCP-Redis interface layer enables the same codebase to operate across simulation and physical hardware without modification, and a Skill Self-Evolution mechanism distills operational experience into persistent skill files without model fine-tuning. We validate SpaceMind through 192 closed-loop runs across five satellites, three task types, and two environments, a UE5 simulation and a physical laboratory, deliberately including degraded conditions to stress-test robustness. Under nominal conditions all modes achieve 90--100% navigation success; under degradation, the Prospective mode uniquely succeeds in search-and-approach tasks where other modes fail. A self-evolution study shows that the agent recovers from failure in four of six groups from a single failed episode, including complete failure to 100% success and inspection scores improving from 12 to 59 out of 100. Real-world validation confirms zero-code-modification transfer to a physical robot with 100% rendezvous success. Code: https://github.com/wuaodi/SpaceMind

Related papers

• Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents [31.4676947294786]
  We introduce MissionBench, a benchmark for mission-level evaluation of MLLMs in aerial 3D environments.<n>Across 22 open- and closed-source MLLMs, the strongest model succeeds on fewer than 35% of missions compared to 84.4% human performance.<n>Our analysis shows that mission-level competence requires coordinating multiple capabilities beyond spatial perception.
  arXiv  Detail & Related papers  (2026-07-24T06:22:50Z)
• ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI [110.18670135256235]
  Embodied AI is moving from isolated perception or action modules toward physical agents that understand, plan under goals, monitor progress, and improve from experience.<n>We present ACE-Brain-0.5, a unified embodied foundation model that organizes robot intelligence into five coupled functions.<n>A single 8B backbone instantiates the first four functions: grounding objects and affordances, reasoning over 3D and egocentric spatial relations, decomposing instructions into subgoals, generating navigation and manipulation actions, and estimating progress for verification and recovery.
  arXiv  Detail & Related papers  (2026-07-05T17:43:06Z)
• Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy [79.09714980186278]
  Building persistent embodied agents in unstructured environments requires unified orchestration of heterogeneous tools.<n>We present OmniAct, a framework integrating a multimodal semantic planner for skill routing across unified action spaces.<n>It achieves consistent improvements in end-to-end success across all complexity levels.
  arXiv  Detail & Related papers  (2026-06-25T16:36:35Z)
• Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation [0.6927055673104934]
  The architecture bridges the gap between high-level reasoning and low-level kinematics by decomposing the vision-action pipeline into three stages: visual perception, semantic interpretation, and task execution.<n>The framework is evaluated across two zero-shot experimental setups: unconstrained open-world sequential manipulation and dense relational spatial reasoning.
  arXiv  Detail & Related papers  (2026-06-22T11:01:56Z)
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning [99.49739831030388]
  We study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning.<n>We propose SpatialClaw, a training-free framework for spatial reasoning that adopts code as the action interface.
  arXiv  Detail & Related papers  (2026-06-11T17:59:36Z)
• Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models [63.96252564303143]
  Embodied-R1.5 is a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities.<n>We build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe.<n>With only 8B parameters, Embodied-R1.5 SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4.
  arXiv  Detail & Related papers  (2026-06-09T18:07:50Z)
• EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents [75.01735520608075]
  Existing benchmarks mostly test literal Theory of Mind (ToM) by asking direct belief questions.<n>We introduce EnactToM, an evolving benchmark of 300 embodied multi-agent tasks set in a 3D household.<n>On the hard split, all seven evaluated frontier models score 0.0% Pass3 on functional task completion, while averaging 45.0% on literal belief probes.
  arXiv  Detail & Related papers  (2026-05-11T00:04:19Z)
• AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules [7.392721604463545]
  We argue that a robot should be modeled as a single persistent intelligent subject whose capabilities are extended through installable packages.<n>We formalize this view as AEROS (Agent Execution Execution Operating System), in which each robot corresponds to one persistent agent and capabilities are provided through ECMs.<n>We evaluate a reference implementation in PyBullet simulation with a Franka Panda 7-DOF manipulator across eight experiments covering re-planning, failure recovery, policy enforcement, baseline comparison, cross-task generality, ECM hot-swapping, ablation, and failure boundary analysis.
  arXiv  Detail & Related papers  (2026-04-08T12:54:32Z)
• AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation [0.0]
  AutoMOOSE is an agentic framework that orchestrates the full simulation lifecycle from a single natural-language prompt.<n>It generates MOOSE input files with 6 of 12 structural blocks matching a human expert reference exactly and 4 functionally equivalent.<n>It performs an end-to-end physical consistency check spanning intent, finite-element execution, and Arrhenius kinetics with no human verification.
  arXiv  Detail & Related papers  (2026-03-22T00:11:19Z)
• RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset [48.645870795753105]
  We introduce Robust Autonomous Data Acquisition for Robotics (RADAR)<n>RADAR is a fully autonomous, closed-loop data generation engine that completely removes human intervention from the collection cycle.<n>In simulation, our framework achieves up to 90% success rates on complex, long-horizon tasks.
  arXiv  Detail & Related papers  (2026-03-12T11:18:52Z)
• DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI [84.9072161615971]
  We present DM0, an Embodied-Native Vision-Language-Action framework designed for Physical AI.<n>Our methodology follows a comprehensive three-stage pipeline: Pretraining, Mid-Training, and Post-Training.<n>Experiments on the RoboChallenge benchmark demonstrate that DM0 achieves state-of-the-art performance in both Specialist and Generalist settings.
  arXiv  Detail & Related papers  (2026-02-16T17:59:16Z)
• ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning [31.000965640377128]
  ABot-M0 is a framework that builds a systematic data curation pipeline.<n>It enables end-to-end transformation of heterogeneous raw data into unified, efficient representations.<n>ABot-M0 supports modular perception via a dual-stream mechanism.
  arXiv  Detail & Related papers  (2026-02-11T16:47:01Z)
• VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents [130.70999337445468]
  Key challenge in training Vision-Language Model (VLM) agents, compared to Language Model (LLM) agents, is shift from textual states to complex visual observations.<n>We ask: Can VLM agents construct internal world models through explicit visual state reasoning?<n>We architecturally enforce and reward the agent's reasoning process via reinforcement learning (RL)<n>We find that the agent's reasoning into State Estimation and Transition Modeling is critical for success.
  arXiv  Detail & Related papers  (2025-10-19T16:05:07Z)
• EmbRACE-3K: Embodied Reasoning and Action in Complex Environments [48.32142591866083]
  EmRACE-3K is a dataset of over 3,000 language-guided tasks constructed using Unreal Engine and the UnrealCV-Zoo framework.<n>We establish a benchmark to evaluate the embodied reasoning capabilities of VLMs across three key dimensions: Exploration, Dynamic Spatial-Semantic Reasoning, and Multi-stage Goal Execution.<n>In zero-shot settings, all models achieve success rates below 20%, underscoring the challenge posed by our benchmark and the current limitations of VLMs in interactive environments.
  arXiv  Detail & Related papers  (2025-07-14T17:59:46Z)
• MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning [54.47710436807661]
  MORSE-500 is a video benchmark composed of 500 fully scripted clips embedded questions spanning six complementary reasoning categories.<n>Each instance is generated using deterministic Python scripts (Manim, Matplotlib, MoviePy), generative video models, and real footage.<n>Unlike static benchmarks that become obsolete once saturated, MORSE-500 is built to evolve.
  arXiv  Detail & Related papers  (2025-06-05T19:12:45Z)
• Precise Mobile Manipulation of Small Everyday Objects [11.45585588241935]
  We develop Servoing with Vision Models (SVM), a closed-loop framework that enables a mobile manipulator to tackle precise tasks involving the manipulation of small objects.<n>SVM uses state-of-the-art vision foundation models to generate 3D targets for visual servoing to enable diverse tasks in novel environments.<n>We conduct a large-scale evaluation spanning experiments in 10 novel environments across 6 buildings including 72 different object instances.
  arXiv  Detail & Related papers  (2025-02-19T18:59:17Z)
• Toward a Plug-and-Play Vision-Based Grasping Module for Robotics [0.0]
  This paper introduces a vision-based grasping framework that can easily be transferred across multiple manipulators. The framework generates diverse repertoires of open-loop grasping trajectories, enhancing adaptability while maintaining a diversity of grasps.
  arXiv  Detail & Related papers  (2023-10-06T16:16:00Z)
• Reactive Long Horizon Task Execution via Visual Skill and Precondition Models [59.76233967614774]
  We describe an approach for sim-to-real training that can accomplish unseen robotic tasks using models learned in simulation to ground components of a simple task planner. We show an increase in success rate from 91.6% to 98% in simulation and from 10% to 80% success rate in the real-world as compared with naive baselines.
  arXiv  Detail & Related papers  (2020-11-17T15:24:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.