MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control

• URL: http://arxiv.org/abs/2609.06251v1
• Date: Sat, 05 Sep 2026 20:31:14 GMT
• Title: MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control
• Abstract summary: MobileVLA-R1 2.0 is an RL-enhanced vision-language-action framework for mobile robots.<n>It learns multi-granularity reasoning over embodied trajectories through supervised Chain-of-Thought (CoT) alignment and reinforcement learning.<n>We conduct evaluations on language-guided navigation, quadruped control, and humanoid mobile manipulation, covering VLN-CE, QUARD, and real-world deployments on Unitree Go2 and G1 robots.
• Score: 63.85634404397772
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for vision-language-action (VLA) systems on mobile robots, due to the persistent gap between high-level semantic reasoning and low-level locomotion and manipulation control. Existing approaches often rely on implicit reasoning or monolithic action prediction, making it difficult to maintain coherent long-horizon decision making while producing precise and adaptable robot actions. To address this challenge, we propose MobileVLA-R1 2.0, an RL-enhanced VLA framework that explicitly couples structured embodied reasoning with executable mobile robot control. The framework learns multi-granularity reasoning over embodied trajectories through supervised Chain-of-Thought (CoT) alignment and reinforcement learning, improving reasoning-to-action consistency beyond purely behavioral supervision. To support both locomotion and manipulation, we further introduce a reasoning-conditioned action decoder that maps multimodal reasoning representations to task-level action targets, which are subsequently translated into embodiment-specific commands by robot controllers. This design provides a unified perception-reasoning-action interface while decoupling high-level action generation from robot-specific actuation. We conduct extensive evaluations on language-guided navigation, quadruped control, and humanoid mobile manipulation, covering VLN-CE, QUARD, and real-world deployments on Unitree Go2 and G1 robots. MobileVLA-R1 2.0 consistently outperforms strong VLA baselines, achieving an average 1.6 point improvement in SR on VLN-CE and a 10.0 point improvement in full-task success on real-world G1 mobile manipulation tasks over MobileVLA-R1, while demonstrating robust long-horizon instruction following and closed-loop execution across different robotic platforms.

Related papers

• NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation [16.57017306622846]
  We present NebulaVLA, an asynchronous dual-frequency architecture that decouples high-level semantic reasoning from low-level action control.<n>To bridge semantic gaps across heterogeneous robots, we introduce GESTURE-7, a unified language-grounded action representation.
  arXiv  Detail & Related papers  (2026-08-17T12:40:23Z)
• ABot-M0.5: Unified Mobility-and-Manipulation World Action Model [27.262271208923995]
  ABot-M0.5 is built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency.<n> Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy.
  arXiv  Detail & Related papers  (2026-07-01T09:21:20Z)
• Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data [93.7685703383343]
  Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies is surprisingly difficult.<n>We argue that this gap can be bridged gradually with the right intermediate data.<n>We show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions.
  arXiv  Detail & Related papers  (2026-06-07T08:57:51Z)
• DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA [72.9197085473598]
  DIAL is a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck.<n>A VLM-based System-2 performs latent world modeling by latent visual foresight within the VLM's native feature space.<n>A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions.
  arXiv  Detail & Related papers  (2026-03-31T15:02:27Z)
• Vision-based Goal-Reaching Control for Mobile Robots Using a Hierarchical Learning Framework [4.014524824655106]
  This paper decomposes the whole system into a set of tightly coupled functional modules.<n>The proposed framework guarantees uniform exponential stability of the actuation system and safety of the whole operation.
  arXiv  Detail & Related papers  (2026-01-02T08:41:47Z)
• MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots [15.919707197385462]
  MobileVLA-R1, a vision-language-action framework, enables explicit reasoning and continuous control for quadruped robots.<n>We introduce a two-stage training paradigm that combines supervised CoT alignment with GRPO reinforcement learning to enhance reasoning consistency, control stability, and long-horizon execution.
  arXiv  Detail & Related papers  (2025-11-22T02:34:10Z)
• dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought [66.78110237549087]
  Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics.<n>We introduce dVLA, a diffusion-based VLA that unifies visual perception, language reasoning, and robotic control in a single system.
  arXiv  Detail & Related papers  (2025-09-30T02:36:11Z)
• Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics [55.05920313034645]
  We introduce Robot-R1, a novel framework that leverages reinforcement learning to enhance embodied reasoning specifically for robot control.<n>Inspired by the DeepSeek-R1 learning approach, Robot-R1 samples reasoning-based responses and reinforces those that lead to more accurate predictions.<n>Our experiments show that models trained with Robot-R1 outperform SFT methods on embodied reasoning tasks.
  arXiv  Detail & Related papers  (2025-05-29T16:41:12Z)
• Robotic Control via Embodied Chain-of-Thought Reasoning [86.6680905262442]
  Key limitation of learned robot control policies is their inability to generalize outside their training data.<n>Recent works on vision-language-action models (VLAs) have shown that the use of large, internet pre-trained vision-language models can substantially improve their robustness and generalization ability.<n>We introduce Embodied Chain-of-Thought Reasoning (ECoT) for VLAs, in which we train VLAs to perform multiple steps of reasoning about plans, sub-tasks, motions, and visually grounded features before predicting the robot action.
  arXiv  Detail & Related papers  (2024-07-11T17:31:01Z)

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.