# 学习机器人元推理：面向实时控制的自适应计算预算

> 原文链接：https://robotics.hellobike.com/papers/2026-10-16-2610-23662
> 频道：papers | 更新日期：2026-10-16 | 标签：arxiv, cs.RO
> 核心摘要：该论文将实时控制中的计算预算选择建模为SMDP，并用强化学习策略在多类机器人任务上自适应分配规划时间。

# 学习机器人元推理：面向实时控制的自适应计算预算

::: v-pre
> 原文链接：[Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time Control](https://arxiv.org/abs/2610.23662)（arXiv 2610.23662 · 发布日期：2026-10-16）

**Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time Control**

该论文将实时控制中的计算预算选择建模为SMDP，并用强化学习策略在多类机器人任务上自适应分配规划时间。

## 核心要点

- 动中规划需在深度思考与快速反馈间权衡，固定动作承诺可能不适合状态变化。
- 方法将最优计算预算识别表述为SMDP，一次决策同时确定动作承诺和求解器时间。
- 训练的强化学习策略利用当前状态、执行中计划和低成本规划器统计量进行预算选择。
- 在地面机器人导航、敏捷四旋翼飞行和富接触操作中，策略优于固定预算基线。

**验证范围与局限**：验证范围为地面机器人导航、敏捷四旋翼飞行和富接触操作，摘要未说明仿真或真机。

## 英文摘要 (Abstract)

Planning while moving faces an historical trade-off between deliberation and reactivity. A planner running concurrently with execution needs time to compute, so the robot must commit to an open-loop action chunk for that duration: a longer commitment buys a better plan at the cost of feedback frequency. Existing controllers fix this action commitment, and consequently the computation budget, before deployment. However, the optimal computation time is highly state-dependent (due to factors such as unmodeled dynamics, safety constraints, and marginal optimisation gains), i.e. dynamic, therefore offline static tuning risks leaving systems blind during critical maneuvers or unable to find global effective solutions. We cast the identification of the optimal computation budget as a semi-Markov decision process (SMDP) in which a single decision defines both the robot action commitments and the time allocated to the solver. To solve this, we train a reinforcement-learning policy conditioned on the current state, the executing plan, and inexpensive planner statistics. Across ground-robot navigation, agile quadrotor flight, and contact-rich manipulation, the learned policy changes its budget with the demands of the scenario, discovering efficient reasoning patterns that outperform fixed-budget baselines. https://lorenzomagnino.github.io/learning-robot-metareasoning-review/

作者：Lorenzo Magnino, Antonio Marino, Michael Amir, Daigo Shishika, Amanda Prorok
:::

## 原始参考来源 (Sources)

- [arXiv 2610.23662：Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time Control](https://arxiv.org/abs/2610.23662)