SWAP: Stepwise Action Policy Routing for Vision-Language-Action Models
SWAP: Stepwise Action Policy Routing for Vision-Language-Action Models
This research proposes SWAP, a framework that dynamically composes multiple Vision-Language-Action (VLA) policies during robot task execution. By formulating policy routing as an offline reinforcement learning problem, SWAP enables robots to select new policies online, improving real-world task success by up to 33% and reducing successful trajectory action steps by 28.3%.
Source: arXiv Robotics — research abstracts · Read original article ↗
Article text · Original source · English
arXiv:2610.06926v1 Announce Type: new Abstract: Robot manipulation systems using Vision-Language-Action (VLA) model backbones typically use just one VLA for task execution. However, individual VLAs do not perform well across different task states and environments. We introduce a framework for dynamically composing multiple VLA policies during execution: StepWise Action Policy Routing (SWAP). SWAP formulates policy routing as an offline reinforcement learning problem, learning a routing critic that selects the most appropriate policy at each decision step given the current observation. SWAP enables robots to select new policies to execute online rather than committing to a single policy for the duration of an episode. We evaluate SWAP on both real-world DROID manipulation tasks and LIBERO simulation experiments. SWAP improves over fixed-policy execution and routing baselines, giving absolute improvements in real-world task success up to 33% while reducing successful trajectory robot action step length by 28.3%.
Source：arXiv Robotics — research abstracts · arxiv.org