Evo-World:一种通过光流监督实现未来运动预测的轻量级视觉-语言-动作模型
Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision
AI总结:
Evo-World是一种轻量级VLA模型,通过光流监督实现未来运动预测,在Meta-World MT50模拟基准及AgileX真实机器人操作任务中均优于基线,参数仅0.87B且效率更高。
摘要:
视觉-语言-动作(VLA)模型为视觉理解、语言接地和机器人控制提供了统一框架,但预测当前观测之外的场景演化可为控制提供额外信息。仅动作监督无法明确鼓励此类预测,而未来图像预测会将任务相关运动与大量静态外观纠缠。为解决这些局限,我们引入Evo-World,一种轻量级VLA模型,其通过光流监督增强策略学习,实现未来运动预测,从而提供聚焦于运动而非外观的任务相关预测信号。我们进一步设计训练流程,在策略学习过程中保留这些预测表征,调节表征多样性,同时将表征学习与动作优化解耦。在模拟基准测试中,Evo-World表现出强劲性能,在Meta-World MT50上达到层级平均成功率91.1%,较无预测基线实现13.0%的相对提升。在真实世界AgileX机器人上,Evo-World在单臂和双臂操作任务中均优于所评估基线,且仅使用0.87B参数,同时具备更低GPU内存占用和更高推理效率。这些结果表明,通过光流监督的未来运动预测是增强VLA模型预测能力的有效且轻量方法。
英文摘要:
Vision-language-action (VLA) models provide a unified framework for visual understanding, language grounding, and robot control, yet anticipating how the scene will evolve beyond the current observation can provide additional information for control. Action supervision alone does not explicitly encourage such anticipation, while future-image prediction entangles task-relevant motion with largely static appearance. To address these limitations, we introduce Evo-World, a lightweight VLA model that augments policy learning with future motion prediction through optical-flow supervision, thereby providing a task-relevant predictive signal focused on motion rather than appearance. We further design the training procedure to preserve these predictive representations during policy learning, regulating representation diversity while decoupling representation learning from action optimization. Across simulation benchmarks, Evo-World demonstrates strong performance, achieving a tier-averaged success rate of 91.1% on Meta-World MT50 , with a 13.0% relative improvement over the non-predictive baseline. On real-world AgileX robots, Evo-World outperforms the evaluated baselines across single-arm and bimanual manipulation tasks while using only 0.87B parameters and delivering lower GPU memory usage and higher inference efficiency. These results demonstrate that future motion prediction through optical-flow supervision provides an effective and lightweight approach to enhancing the predictive capabilities of VLA models.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。