跳到正文
返回论文列表
cs.AI提交于 已译

AFTER:具有自适应快慢时间尺度的误差驱动保持世界模型

AFTER: A World Model with Adaptive Fast--Slow Timescales for Error-Driven Retention

Haoyi Zhang · Qi Zhang · Yunfan Ren · Yi Bin · Lei Zhu · Heng Tao Shen

中文摘要

在机器人学与具身智能中,世界模型面临的核心挑战是适应交互过程中机器人动力学突然、持续且初始未知的变化。例如机械臂抓取未知负载物体时,动力学突然改变;若世界模型无法适应,预测误差会在开环推演中累积并误导动作。现有世界模型难以同时满足动力学适应的三项关键要求:响应性(对突变及时反应以抑制误差累积)、稳定性(区分持续变化与瞬态扰动以避免错误更新)、持久性(无新观测时保持已适应的动力学,使后续预测不退回旧动力学)。受人类大脑预测编码的多时间尺度适应启发,提出 AFTER-WM,其预测误差驱动一个会衰减的快速校正和一个持久的慢速校正,同时动态调整预训练专家的组合权重而不改动专家本身,以克服三者间的权衡。在五个仿真机器人数据集和真实 UAV 数据上,AFTER-WM 的多步平均误差低于全部十个对比模型,并在联合失效控制任务中取得最高平均回报。仿真中其多步平均误差比最强对比模型低 16%-34%,在变化后 1-4 步及仅含瞬态扰动时误差最低,第 40 步误差也最低,体现响应性、稳定性与持久性。全部代码(方法、基线、实验)与数据集将在线发布。

关键要点

  1. 01问题:世界模型难以同时兼顾动力学适应的响应性、稳定性与持久性。
  2. 02方法:预测误差驱动快校正衰减、慢校正持久,并动态调整预训练专家组合权重。
  3. 03结果:五个仿真机器人数据集与真实 UAV 数据上多步平均误差低于全部十个对比模型。
  4. 04结果:仿真多步平均误差比最强对比模型低 16%-34%,变化后 1-4 步与第 40 步误差最低。
  5. 05结果:联合失效控制任务中平均回报最高。

解读

尚无解读。

原始英文摘要

arXiv:2611.15215v1 Announce Type: new Abstract: In robotics and embodied AI, a core challenge for world models is adapting to sudden, persistent, yet initially unknown changes in robot dynamics during interaction. For instance, when a robotic arm grasps an object with an unknown payload, the robot dynamics change suddenly. If the world model fails to adapt, its prediction errors accumulate over the open-loop rollout and ultimately mislead the robot's actions. Existing world models, however, struggle to simultaneously satisfy three critical requirements for dynamics adaptation: responsiveness, reacting promptly to sudden changes to curb prediction error accumulation; stability, distinguishing persistent changes from transient disturbances to prevent incorrect updates; and persistence, retaining the adapted dynamics without new observations so that later predictions do not revert to the old dynamics. Inspired by predictive coding in the human brain with multi-timescale adaptation, we propose AFTER-WM, a world model with Adaptive Fast-slow Timescales for Error-driven Retention, whose prediction errors drive a fast correction that fades and a slow correction that persists, while dynamically adjusting the combination weights of pre-trained experts without altering them, to overcome the trade-offs among responsiveness, stability and persistence. On five simulated robot datasets and real UAV data, AFTER-WM has a lower multi-step mean error than all ten compared models and the highest mean return in a joint-failure control task. In simulation, its multistep mean error is 16%-34% below the strongest compared model's and is also the lowest 1-4 steps after a change and under transient disturbances alone, and its step-40 error is the lowest as well, reflecting responsiveness, stability and persistence. All code (method, baselines, experiments) and datasets will be released online.

同方向论文 · cs.AI

查看全部 →

反向发现 · 这篇论文相关的工具与提示词

去交叉发现 →

关联工具 · 2

Hacker News · 首页84

Dream Labs 发布 Dream-1 机器人基础模型并开放公共 API

Dream Labs 发布 Dream-1 World Action Model,并面向全球开放公共 API,可零样本控制未见过的双臂平行夹爪机器人,无需针对目标机器人微调或提供示范数据。Dream-1 运行时价格为 $3/hour,Dream-1-flash 为 $2/hour;官方也披露了不同机器人上的性能差异,并通过 FaaS 支持基于少量自有数据的适配。

推荐理由:文章同时给出跨机器人零样本控制、公开 API、成本与失败边界,便于评估通用机器人模型的落地条件。

NVIDIA Blog72

NVIDIA Cosmos 扩展世界模型训练、评测与部署工具

NVIDIA Cosmos 新增训练工具、仿真检查点与 Cosmos Data Factory 蓝图,用于构建训练数据、训练和适配世界模型,并完成仿真评测与部署。开发者可微调 GR00T、Alpamayo、QWEN、Pi0.5 等模型;Cosmos 3 NIM 在已验证配置中可实现最高 2 倍推理提速,Metropolis Blueprint 3.3 可在同一 GPU 上监控多 40% 的视频流。

推荐理由:新增工具覆盖训练数据构建、模型训练优化、策略测试与部署,并提供了具体应用效果。