论文/arXiv 2609.17115·1 个月前

Intrinsic Robot Rewarding：复用 VLA 表征用于自主评估和策略改进

IRR面向机器人自主评估与策略改进，复用VLA视觉编码器和成功示范终点形成奖励，并以COMAU Racer 3实验室演示器为基础。

AI 整理

• 数据与采集
• 具身模型
• 评测与安全

原文链接：Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement（arXiv 2609.17115 · 发布日期：2026-09-15）

Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement

IRR面向机器人自主评估与策略改进，复用VLA视觉编码器和成功示范终点形成奖励，并以COMAU Racer 3实验室演示器为基础。

核心要点

• VLA已有视觉表征和成功示范，可用于结果评估与策略改进反馈。
• IRR以成功示范终点为任务参考，在冻结视觉编码器特征空间评分。
• 核心机制加入参考库和评分操作，无需单独评估器或额外感知骨干。
• 论文给出奖励公式、研究问题和评估方法，并提供TRL4实验室演示器。

验证范围与局限：验证范围为实验室COMAU Racer 3演示器（TRL4）基础；连接到物理策略改进仍是下一步。

英文摘要 (Abstract)

Vision-language-action (VLA) systems already bring together two valuable resources for robot learning: rich visual representations and demonstrations of successful task execution. Intrinsic Robot Rewarding (IRR) proposes to use these resources for a second, complementary purpose: evaluating the robot's own outcomes and providing feedback for policy improvement. Successful demonstration endpoints define task-specific references, and the policy's frozen visual encoder provides the feature space in which new outcomes are assessed. The core reward mechanism adds a reference bank and a scoring operation to the existing pipeline, without requiring a separate learned evaluator or an additional perception backbone. Our position is that this reuse offers a promising route to lower integration effort, efficient reward computation, and reduced recurring human outcome scoring. Building on established research in visual rewards and learning from experience, IRR brings these ideas into the robot's existing perception and demonstration pipeline. An operational COMAU Racer 3 demonstrator is available at technology readiness level 4 (TRL 4). This laboratory foundation supports the next research step: connecting internal outcome evaluation to physical policy improvement. We present the reward formulation, central research questions, and an evaluation methodology linking reward reliability to task success and supervision effort. The intended contribution is a reusable approach to learn and improve from the data and experience already available in industrial robot systems.

作者：Tobias Schaffer, Mohab Elkhayat, Daniela Nicklas, Mustafa Almohamad, Elham Al-Fuqara

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2609.17115：Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement访问 2026-10-21