Skip to main content
Search

# Vision-Language-Action Policy

8 related articles

Subscribe to updates
  1. arXiv

    A robot policy misread "in the bowl": closed-form weight edits, with no retraining or instruction change, lift held-out success from 27/128 to 106/128

    A zero-shot vision-language-action policy told to put the cube then the banana in the bowl releases the cube early because it binds "in the bowl" to the banana rather than the cube in its gripper. Closed-form instruction distillation writes the per-layer effect of a working rewording directly into the VLM's MLP weights, with no gradients, training data or change to the instruction; on 128 held-out seeds success rises from 27/128 to 106/128, while a random-direction update of the same size leaves success unchanged.

  2. arXiv

    Lunar rover docking now driven directly by a vision-language-action policy: it beats a modular pipeline under the strongest sensor disturbances while making half the inferences

    Autonomous lunar rover docking has relied on modular pipelines that split perception, mapping and planning, so perception errors propagate into planning. Researchers trained a vision-language-action policy with a Qwen3.5-4B backbone on safety-aware demonstrations from a privileged expert in the LuPNT lunar simulator, mapping a single monocular camera and a bird's-eye-view map directly to waypoints. Under dust and optical disturbances unseen in training, the policy achieved higher docking success in five of six disturbance conditions, with the largest advantage under the strongest perturbations; adaptive-horizon execution held 90% docking success while cutting policy inferences per successful scenario from 17.16 with a fixed 2 m horizon to 8.36.

  3. arXiv

    Robot disassembly learns from its own rollouts: PACER turns autonomous traces and human corrections into training weights, reaching 87/100 motherboard handoffs

    In electronic-waste disassembly, demonstrations for vision-language-action (VLA) policies are scarce, and supervised fine-tuning alone struggles to cover the state shifts a deployed policy meets. PACER compiles autonomous rollouts, operator corrections and supplementary clean demonstrations into typed action-chunk rows, then weights each row by progress toward the declared target and by the trace's source and role, while keeping the native supervised action loss. On held-out hardware for UR5e motherboard disassembly across five components, the selected policy completed 87/100 approach-and-handoff trials, against 54/100 for uniformly weighted post-SFT and 79/100 for fixed-geometry reweighting.

  4. arXiv

    Robot memory stops guessing from keyframes: per-tick text lines lift success from 44.5% to 66.0% under a fixed policy

    Gamma replaces pixel keyframe memory with auditable text lines, raising average success on RoboMME's sixteen memory tasks from 44.5% to 66.0% under a fixed execution policy and matching the privileged subgoal ceiling on three tasks.

  5. arXiv

    CAPABLE lifts a frozen VLA from 24.8% to 59.3% success on an actuator excluded from fault training

    CAPABLE is a capability-aware adaptation framework for frozen vision-language-action policies: a temporal encoder shared across joints infers from command-response history and live Jacobian grounding how much commanded motion each joint still realizes, a self-supervised physical-prediction objective ties that representation to behavior, and a bounded residual reinforcement-learning policy corrects the VLA arm action without fault labels or faulty-joint identifiers; across 28 LIBERO tasks it raises success on an actuator excluded from fault training from 24.8% to 59.3%, 17.4 points above a parameter-matched global-history baseline, while preserving healthy performance.

  6. arXiv

    PyRUA-Lean lifts GPT-6 Astra robot-agent success from 63.1% to 71.7% while cutting input tokens by 65%

    The authors introduce PyRUA-Lean, an interactive code-execution framework that couples feedback-driven primitive composition with selective observation, letting the agent compose classical robot primitives and learned vision-language-action (VLA) policies into Python cells that perform conditional checks and local retries and return only explicitly requested images and state feedback for replanning; across 700 simulated task instances from LIBERO-PRO, RoboTwin 2.0, and RoboCasa365, compared with a tool-calling baseline using the same GPT-6 Astra planner and the same underlying robot primitives, it raises overall success from 63.1% to 71.7% under equal LLM-call budgets and, on instances solved by both agents, uses 49% fewer LLM calls and 65% fewer input tokens.

  7. arXiv

    Vela replaces fixed-rate action chunks with continuous spline trajectories, reaching 45.3% average success on LIBERO-X, 49.7% overall on EBench, and 67.5% mean subtask success on a real dual-arm egg-cake task

    Vela is a vision-language-action foundation model pretrained in trajectory space that represents future motion with a fixed number of cubic B-spline control points plus a motion-dependent temporal span; pretrained on roughly 20,000 hours of public and roughly 20,000 hours of private robot data, it reaches 45.3% average success on LIBERO-X, 49.7% overall success and a 66 task-progress score on EBench, and 67.5% mean subtask success on a real wheeled dual-arm egg-cake cooking task.

  8. arXiv

    SWAP routes stepwise among VLA policies via offline RL, lifting real-world DROID task success from 63.3% to 96.7%

    SWAP casts robot policy routing as an offline reinforcement learning problem, training an IQL routing critic that picks, after each action chunk, the candidate pretrained VLA policy with the highest predicted long-horizon return given the current observation; on real-world DROID tabletop manipulation it raises success from 63.3% for the best single policy to 96.7% while cutting average action steps for successful trajectories from 269 to 193 (a 28.3% reduction), and it outperforms fixed-policy and random-routing baselines in LIBERO and LIBERO-Plus simulation.

You’re all caught up