Related Experiment Video
Updated: Aug 28, 2026

Corticospinal Excitability Modulation During Action Observation
Published on: December 31, 2013
Action- and Language-Conditioned Video Assessment for Embodied Control
Hwanhee Kim1, Jaehyun Jang2, Seungmin Cha2
1Robotics Program, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea.
Abstract:
Vision-based embodied agents executing multi-step natural language instructions require feedback mechanisms that assess task progress over complete trajectories. Conventional approaches based on final-frame matching or continuous embedding similarity may overlook intermediate transitions that are necessary for determining whether an instruction has been completed. We propose ALVA (Action- and Language-Conditioned Video Assessment), a trajectory evaluator that conditions its assessment on visual observations, the executed action sequence, and the natural language instruction. The method uses a pre-trained vision-language model (VLM) in two stages: it first summarizes frame-to-frame visual transitions conditioned on the executed actions and then assesses the generated summary with respect to the instruction to produce a discrete trajectory-level progress score. In simulated 3D household environments, ALVA exhibits a conservative assessment pattern with near-zero false-positive rates. When used as terminal feedback for closed-loop policy optimization, it provides more effective feedback than the evaluated static image and embedding-based visual baselines and reduces the performance gap to a ground-truth oracle. These results support action- and language-conditioned video assessment as an interpretable feedback mechanism for the evaluated simulated embodied-control tasks.
Related Concept Videos
Hierarchy of Motor Control
Muscle Coordination and Action
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement.

