# DiMuRe helps robots recover from task disruptions

> Researchers introduce a recovery framework and benchmark for disturbed robot tasks. In scheduled tests, its local recovery approach completed more tasks than the original program.

Oossa · 2026-11-04 · https://oossa.com/en/dimure-helps-robots-recover-from-task-disruptions

Researchers introduce DiMuRe, a system that helps robots recover when a disruption makes their next action unsuitable. It uses evidence from the robot’s current task phase to decide whether to reuse the existing program or try a predefined recovery skill; an AI model can also generate corrective code after the program exits.

On 801 scheduled disturbed cases in the Encore development setup, the paper reports 77.65% complete-task success for Local DiMuRe, versus 58.68% for the original program under the same physical-step allowance. Full DiMuRe reached 81.90%, but with extra steps and terminal replanning. The researchers also introduce LIBERO-Disturb, a benchmark for testing recovery.

## The facts

- The paper reports 77.65% success for Local DiMuRe and 58.68% for the original program on 801 scheduled disturbed cases.
- The arXiv record lists publication on Nov. 4, 2026.

## Why it matters

For robotics researchers testing task reliability, LIBERO-Disturb offers a benchmark focused on mid-task disruptions; whether the reported gains carry over to other robots or real-world settings is not established here.

## Sources & references

1. [DiMuRe: Diagnosis-Guided Multilevel Recovery for Robotic Task Execution](https://arxiv.org/abs/2611.04226) – arXiv cs.RO, 2026-11-04

Last updated: 2026-11-04