NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation

• URL: http://arxiv.org/abs/2607.14643v1
• Date: Thu, 16 Jul 2026 07:10:46 GMT
• Title: NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation
• Abstract summary: We present NavCMPO, a two-stage adaptive navigation framework that combines few-step MeanFlow trajectory generation, critic-guided refinement, and reinforcement learning fine-tuning.<n>Under a matched training budget on the InternVLA-N1 benchmark, NavCMPO achieves an average success rate of 74.7%, exceeding the retrained NavDP baseline by 6.4 percentage points.
• Score: 8.749359019282508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end diffusion-based policies have demonstrated strong performance in mapless visual navigation, but their iterative denoising process introduces substantial inference latency, while behavior cloning limits performance to the quality of expert demonstrations. We present NavCMPO, a two-stage adaptive navigation framework that combines few-step MeanFlow trajectory generation, critic-guided refinement, and reinforcement learning fine-tuning. During pre-training, an obstacle proximity prediction task encourages the visual representation to capture obstacle-aware spatial information. To compensate for the degradation in obstacle avoidance caused by few-step generation, Critic-Guided Trajectory Refinement (CGTR) uses gradients from a critic trained with obstacle-point-cloud supervision to refine intermediate trajectories. During adaptation, the MeanFlow policy is fine-tuned using Proximal Policy Optimization with behavior-cloning regularization, while the critic is updated to accommodate embodiment-specific observation changes. Under a matched training budget on the InternVLA-N1 benchmark, NavCMPO achieves an average success rate of 74.7\%, exceeding the retrained NavDP baseline by 6.4 percentage points, while reducing inference latency from 85\,ms to 60\,ms. Experiments on a Unitree Go2 further demonstrate effective sim-to-real transfer.

Related papers

• An Adaptive Fixed-Time Line-of-Sight Guidance Scheme for 3D Path Following of Underwater Vehicles: Theory and Experiment [2.202253618096515]
  This paper proposes a robust fixed-time adaptive guidance framework for 3D path tracking for AUVs.<n>A time-varying look-ahead mechanism is also introduced to improve tracking performance on curved paths.
  arXiv  Detail & Related papers  (2026-09-13T19:42:16Z)
• RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation [15.931984448913264]
  RoamFlow is a generative navigation framework that leverages MeanFlow to predict the average velocity field for trajectory synthesis.<n>Experiments in both Habitat simulation and real-world robotic platforms demonstrate that RoamFlow achieves efficient inference while maintaining strong navigation performance under real-time constraints.
  arXiv  Detail & Related papers  (2026-06-29T08:10:43Z)
• LNN-Fly: Continuous-Time UAV Navigation for Robust Obstacle Avoidance under Timing Mismatch [17.86034589419106]
  LNN-Fly is a continuous-time navigation policy for LiDAR-based UAV obstacle avoidance.<n>It improves obstacle-avoidance performance in the tested settings and shows better tolerance to reduced control frequency, sparse observations, and control-period jitter.<n>In indoor cross-frequency real-world tests, the system achieves 100% success over 20 flights.
  arXiv  Detail & Related papers  (2026-06-27T09:26:22Z)
• A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination Conditions [14.576960188691215]
  Reinforcement learning (RL)-based quadrotor control policies have achieved impressive performance in tasks such as fast navigation in cluttered environments and drone racing.<n>We present a novel approach to achieve tunable performance in RL-based Quadrotor control through reward design and termination conditions.
  arXiv  Detail & Related papers  (2026-05-18T22:40:30Z)
• Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization [69.03519018775779]
  Group Relative Policy Optimization is essential for aligning video diffusion models with human preferences.<n>Existing efficiency methods compromise optimization, exhibiting severe instability and failing to reach full trajectory performance.<n>We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets.
  arXiv  Detail & Related papers  (2026-05-15T14:13:39Z)
• SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data [49.370849653460716]
  We propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation signal as an automated early-stopping mechanism.<n> evaluated on 25 continuous control tasks from the Minari benchmark suite.<n>SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x.
  arXiv  Detail & Related papers  (2026-05-07T08:32:09Z)
• Beyond Imitation: Reinforcement Learning Fine-Tuning for Adaptive Diffusion Navigation Policies [31.52910494173408]
  Diffusion-based robot navigation policies can generate multi-modal trajectories directly from the robot's visual observations.<n>We propose a reinforcement learning framework tailored for diffusion-based navigation.<n>Our approach improves the Success Rate from 52.0% to 58.7% and SPL from 0.49 to 0.54 on unseen scenes, while reducing collision frequency.
  arXiv  Detail & Related papers  (2026-03-13T10:14:32Z)
• Spatially-Aware Adaptive Trajectory Optimization with Controller-Guided Feedback for Autonomous Racing [74.83272587893508]
  We present a framework for autonomous raceline optimization that combines NURBS-based trajectory representation, CMA-ES global trajectory optimization, and controller-guided spatial feedback.<n>In simulation, our approach achieves a 17.38% lap time reduction compared to a controller parametrized with maximum static acceleration.<n>On real hardware, tested with different tire compounds ranging from high to low friction, we obtain a 7.60% lap time improvement without explicitly parametrizing friction.
  arXiv  Detail & Related papers  (2026-02-17T15:10:44Z)
• DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation [73.80968452950854]
  Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces.<n>Existing VLN-CE approaches typically use a two-stage waypoint planning framework.<n>We propose DAgger Diffusion Navigation (DifNav) as an end-to-end optimized VLN-CE policy.
  arXiv  Detail & Related papers  (2025-08-13T02:51:43Z)
• Gaussian Process Regression for Improved Underwater Navigation [13.221163846643607]
  Doppler velocity logs (DVLs) are typically used to mitigate this drift through velocity measurements.<n>This paper proposes a data-driven alternative based on multi-output Gaussian process regression (MOGPR) to improve DVL velocity estimation.<n>We evaluate our proposed approach using real-world AUV data and compare it against LS and a state-of-the-art deep learning model, BeamsNet.
  arXiv  Detail & Related papers  (2025-02-23T09:13:41Z)
• StreamYOLO: Real-time Object Detection for Streaming Perception [84.2559631820007]
  We endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. We consider multiple velocities driving scene and propose Velocity-awared streaming AP (VsAP) to jointly evaluate the accuracy. Our simple method achieves the state-of-the-art performance on Argoverse-HD dataset and improves the sAP and VsAP by 4.7% and 8.2% respectively.
  arXiv  Detail & Related papers  (2022-07-21T12:03:02Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.