AI & ML
RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models
arXiv cs.RO0 views
arXiv:2609.34170v2 Announce Type: replace Abstract: Flow-based vision-language-action (VLA) models are highly effective for generalist robot manipulation, yet their reliance on computationally expensive VLM encoding and multi-step iterative action generation imposes a significant latency bottleneck. The resulting inference latency makes it difficult for robots to respond quickly, especially in dynamic environments. We address this limitation with RAVEL (Rolling Asynchronous VLA Enabling Low-Latency Control), an asynchronous inference framework that addresses the computational bottlenecks of both the VLM backbone and the action expert. To reduce the delay from multi-step action denoising, RAVEL allows near-term actions to be executed after a single additional denoising step by carrying partially denoised future actions forward in a rolling buffer. To avoid blocking on slow VLM encoding, RAVEL decouples VLM encoding from rolling action generation, allowing the action expert to operate continuously using the latest available VLM context, while a lightweight Fast Observation Pathway (FOP) directly conditions the action expert on current observations. Across simulated and real-world manipulation tasks, RAVEL consistently achieves substantially lower response latency while maintaining the task capability of the underlying VLA, enabling high-frequency and responsive closed-loop control.
Source:https://arxiv.org/abs/2609.34170PreviousGLoTouch: Global-to-Local Haptic Perception Using a Parallel Gripper for Object Search, Recognition, and Grasping Without External VisionNextVideo2SwimFish: An Automated Pipeline for Reconstructing Controllable Fish Models and Biological Locomotion from Real Fish Videos
Related posts
One Leaked Prefix Can Take Down Three Clouds: Route Filtering for Multi-Cloud Estates
0dev.to
Global stock markets slump as Anthropic's record IPO fails to stem AI sell-off
0Hacker News

The Download: inside the quest to make our minds immortal
0MIT Technology Review
The Birdfy Gifts I’d Buy for Backyard Birders
0Wired

Rocket Report: A weekend of ups and downs; Stoke celebrates engine milestone
0Ars Technica
California AG subpoenas Nvidia over worries about Huang’s ties with China
0TechCrunch