rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference
rMuscle, a caching-based inference framework for vision-language-action models, achieves 1.29-1.42x speedups on RTX 4090 and Jetson Thor while preserving success rates.
rMuscle is a real-time inference framework for Vision-Language-Action (VLA) models that exploits cross-execution similarity in repetitive robot tasks via a dual-phase muscle-memory cache. The Context Cache reuses visual-token outputs to reduce computation, while the Action Cache reuses neuron activation patterns to reduce weight accesses, with online recomputation and sliding-window retrieval keeping overhead low. It achieves 1.29-1.42x speedups on RTX 4090 and Jetson Thor across LIBERO, RoboTwin, and real-world manipulation tasks while maintaining original success rates.
- Dual-phase cache reuses visual-token outputs and neuron activation patterns across robot executions.
- 1.29-1.42x speedup on RTX 4090 and Jetson Thor with unchanged success rates.
- Evaluated on LIBERO, RoboTwin, and real-world physical manipulation tasks.
- Targets factory embodied-AI workloads where inference latency affects motion smoothness.
From the original article
1 min read at arxiv.orgFactory work is a promising early scenario for embodied AI: assigning repetitive manual jobs to robots has clear economic payoff, and a structured station keeps the jobs tractable for current policies. Vision-Language-Action (VLA) models now dominate as the policy paradigm for these robots. The inference latency of VLA models directly affects robot responsiveness and motion smoothness.
By Kaijun Zhou · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.