General
RePlan-VLA: Progress-Aware Replanning for Long-Horizon Vision-Language-Action Models
arXiv cs.RO0 views
arXiv:2611.23843v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation, yet their performance often degrades on long-horizon tasks that require multiple interdependent manipulations. Instead of burdening the VLA policies with long-horizon reasoning, memory, action generation, progress tracking, and error recovery, we argue for leveraging their short-horizon manipulation capabilities within an execution-aware framework. To this end, we introduce \textnormal{\textbf{RePlan-VLA}}, a VLA-agnostic framework that translates a VLA's short-horizon capabilities into reliable long-horizon execution. RePlan-VLA explicitly monitors the robot's motion for progress evaluation, and adaptively revises the future plan based on observed outcomes. We preserve the underlying VLA policy entirely, requiring no additional fine-tuning. Experiments on RoboCasa365 and CALVIN benchmarks show an improvement of 21.9% and 10.4% in success rate over the next strongest baseline. We also validate our approach for real-world deployment on a Franka Research 3 robot.
Source:https://arxiv.org/abs/2611.23843PreviousEstimation-Aware ReachabilityNextLAGR: Language-Aware Grasp Re-Ranking for Task Oriented Grasping
Related posts
Fanatics Promo Code: 10% Off
0Wired
If nobody writes it down, it did not get decided
0dev.to Productivity
Micrograph B-factor estimation via Wilson statistics
0arXiv eess.IV
Greedy Vector Approximation Based on Rotation for Multiplierless Complex Products
0arXiv eess.SP
Toward Massive MIMO HAPS Networks: Antenna Architectures and Design
0arXiv eess.SP
Deep-Learning-Assisted Full Waveform Inversion for Attenuation Reconstruction in Ultrasound Computed Tomography
0arXiv eess.SP