KERV：基于运动学的具身VLA模型的推测解码
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
AI总结：
本文提出KERV框架，结合token域和运动学域预测，通过运动学卡尔曼滤波和动态调整策略提升VLA模型的推理速度，实验显示在多种任务中加速27%-37%且成功率损失极小。
摘要：
本文提出KERV框架，结合token域和运动学域预测，通过运动学卡尔曼滤波和动态调整策略提升VLA模型的推理速度，实验显示在多种任务中加速27%-37%且成功率损失极小。
英文摘要：
Vision-Language-Action (VLA) models build a token-domain robot control paradigm, yet suffer from low speed. Speculative Decoding (SD) is an optimization strategy that can boost inference speed. Two key issues emerge when integrating VLA and SD: first, SD relies on re-inference to address token errors, which is computationally expensive; second, to mitigate token errors, the acceptance threshold in SD requires careful adjustment. Existing works fail to address the above two issues effectively. Meanwhile, as the bridge between AI and the physical world, existing embodied intelligence has overlooked the application of robotic kinematics. To address these issues, we innovatively combine token-domain VLA models with kinematic-domain prediction for SD, proposing a kinematic-rectified SD framework named KERV. We employ a kinematics-based Kalman Filter to predict actions and compensate for SD errors, avoiding costly re-inference. Moreover, we design a kinematics-based adjustment strategy to dynamically rectify the acceptance threshold, addressing the difficulty of threshold determination. Experimental results across diverse tasks and environments demonstrate that KERV achieves 27%~37% acceleration with nearly no Success Rate loss.
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。
