AFTER-WM：具备快慢自适应时间尺度的误差驱动世界模型
AFTER: A World Model with Adaptive Fast--Slow Timescales for Error-Driven Retention
AI 导读
研究者提出 AFTER-WM，一种受人类大脑预测编码启发的世界模型，通过快慢两种时间尺度的误差驱动校正，解决机器人动力学突变下的响应性、稳定性与持久性权衡。在五个模拟机器人数据集和真实无人机数据上，其多步平均误差比十个对比模型中最强者低 16%-34%，并在联合失效控制任务中取得最高平均回报。全部代码与数据集将开源发布。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2611.15215 [cs.AI] |
| (or arXiv:2611.15215v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15215 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoyi Zhang [view email]
[v1]
Wed, 11 Nov 2026 09:09:37 UTC (46,563 KB)
来源：arXiv cs.AI · arxiv.org