When adopting a deep learning model for embodied agents, it is required that the model structure be optimized for specific tasks and operational conditions. Such optimization can be static such as model compression or dynamic such as adaptive inference. Yet, these techniques have not been fully investigated for embodied control systems subject to time constraints, which necessitate sequential decision-making for multiple tasks, each with distinct inference latency limitations. In this paper, we present MoDeC, a time constraint-aware embodied control framework using the modular model adaptation. We formulate model adaptation to varying operational conditions on resource and time restrictions as dynamic routing on a modular network, incorporating these conditions as part of multi-task objectives. Our evaluation across several vision-based embodied environments demonstrates the robustness of MoDeC, showing that it outperforms other model adaptation methods in both performance and adherence to time constraints in robotic manipulation and autonomous driving applications

翻译：在将深度学习模型应用于具身智能体时，需要针对具体任务与运行条件优化模型结构。此类优化可以是静态的（如模型压缩），也可以是动态的（如自适应推理）。然而，这些技术尚未在受时间约束的具身控制系统中得到充分研究——这类系统需为多个任务进行序列决策，且每个任务具有不同的推理延迟限制。本文提出MoDeC，一种基于模块化模型自适应、具备时间约束感知能力的具身控制框架。我们将资源与时间限制等变化运行条件下的模型自适应问题，形式化为模块化网络上的动态路由问题，并将这些约束条件纳入多任务目标函数。通过在多个基于视觉的具身环境中的评估，我们证明了MoDeC的鲁棒性：在机器人操控与自动驾驶应用中，其在性能表现与时间约束遵循度方面均优于其他模型自适应方法。