通过动作组合训练释放VLA模型的更多动作
Unleashing More Actions via Action Compositional Training for VLA Models
AI总结：
针对VLA模型因过拟合特定行为模式而无法泛化到新动作组合的问题，提出ACT-VLA框架，利用模型潜在任务表示从现有任务中合成新演示数据，无需额外人工采集，有效缓解过拟合并提升泛化能力。
摘要：
视觉-语言-动作模型在机器人操作中表现出色，这得益于演示数据的规模和多样性。然而，标准训练范式常常导致VLA模型严重过拟合特定行为模式，使得即使场景仅需相同子技能的新颖组合，也无法泛化到分布外场景。虽然扩展数据集可以缓解这种过拟合，但获取高质量机器人数据仍然非常劳动密集且成本高昂。为了解决这一僵局，无需昂贵的人工遥操作，并真正释放更多动作，即让VLA模型将已知子技能组合成比原始演示更广泛的可执行行为，我们提出了ACT-VLA（VLA模型的动作组合训练），一种离线数据增强框架，利用模型的潜在任务表示直接从现有任务中合成新颖的、物理上有效的演示用于策略训练。通过消除额外的手动数据收集，我们的方法自动扩展训练分布并缓解过拟合。我们在模拟中具有挑战性的操作任务上评估了我们的方法。实验表明，基线VLA模型由于原始分布过拟合而泛化能力差，而使用我们合成数据训练的策略实现了显著更高的成功率，验证了利用现有任务进行自动演示合成为拓宽VLA泛化提供了一条有效、可扩展且数据高效的途径。
英文摘要：
Vision-Language-Action models excel at robotic manipulation, driven by the scale and diversity of demonstration data. However, standard training paradigms often cause VLA models to severely overfit to specific behavioral patterns, rendering them unable to generalize to out-of-distribution scenarios even when those scenarios merely require novel combinations of identical sub-skills. While expanding datasets can mitigate this overfitting, acquiring high-quality robot data remains notoriously labor-intensive and cost-prohibitive. To resolve this impasse without expensive human teleoperation and to truly unleash more actions,i.e., enable VLA models to compose known sub-skills into a much broader set of executable behaviors beyond the original demonstrations-we propose ACT-VLA (Action Compositional Training for VLA Models), an offline data augmentation framework that leverages the model's latent task representations to synthesize novel, physically valid demonstrations directly from existing tasks for policy training. By eliminating additional manual data collection, our method automatically expands the training distribution and mitigates overfitting. We evaluate our approach on challenging manipulation tasks in simulation. Experiments demonstrate that while baseline VLA models generalize poorly due to original distribution overfitting, policies trained with our synthesized data achieve substantially higher success rates, validating that leveraging existing tasks for automated demonstration synthesis provides an effective, scalable, and data-efficient route to broadening VLA generalization.
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。
