Jetson-PI Enables Real-Time Robot Control on Low-Power Devices via Asynchronous Inference

Jul 15, 2026

Researchers introduce Jetson-PI, a method for deploying Vision-Language-Action (VLA) models on low-power devices such as the Jetson Orin. Jetson-PI uses foresight-aligned asynchronous inference, including a future correction module and confidence-based scheduling, to address latency and misalignment issues. Experiments show Jetson-PI achieves 8.66x and 5.41x improvements in control frequency over naive PyTorch and vla.cpp, respectively, and outperforms VLASH by 14.8% in success rate on the LIBERO benchmark.

Why it matters: This work makes advanced VLA models practical for real-time robot control on resource-constrained edge hardware.

Full story at: arXiv Robotics ↗