Vision language models enable robots to adapt tasks before failure
ProAct-VLM: Pre-Failure Vision-Language Task Replanning with Continuous Perception Feedback
Robotics
Summary
Robots often struggle with long tasks because unexpected changes around them can ruin their plans and cause mistakes. The authors created a new system called ProAct-VLM that uses advanced AI to watch the environment all the time and change the robot’s plan right away if something important changes. This means the robot can avoid problems before they happen, making it more successful and efficient at complex tasks. Their tests showed it works better than other methods in tricky situations.
What this means in practice
- •For industrial robot operators: Improve robotic arms’ ability to adjust work plans immediately as factory conditions change during assembly tasks.
- •For warehouse automation teams: Enhance warehouse robots’ real-time task updates when pathways or items move unexpectedly, reducing delivery delays.
Authors
Ahmed Nader Ahmed, Omar Moured, Mughni Irfan Mohammed Abdul, Muhayy Ud Din, Irfan Hussain
Abstract
Long-horizon robotic tasks are vulnerable to unexpected environmental changes that can render planned actions ineffective or unsafe. To address this, robots must detect such changes as they occur, interpret their impact, and adjust their actions accordingly. Traditional rule-based decision-making pipelines are brittle in open-world conditions, as they are hand-tuned for specific scenarios and lack generalization. Vision-Language Models (VLMs) offer a promising alternative as they combine broad world knowledge with unified visual--text reasoning, enabling them to generalize across diverse scenarios and generate accurate, grounded task plans. However, for effective deployment in dynamic real-world settings, VLMs must be embedded into frameworks capable of handling uncertainty and environmental changes. Existing frameworks broadly address this reactively, triggering replanning only after execution failures or post-task checks, risking failed actions. Some methods verify conditions before actions, but these discrete checks miss changes occurring during execution. To address this, we present ProAct-VLM, an adaptive, physically grounded task planning framework that integrates VLMs within a real-time perception--feedback loop. ProAct-VLM continuously monitors the environment and re-plans as soon as relevant changes are detected, enabling adaptation before failure occurs. Evaluations against multiple baselines and across different VLM backbones show that our framework improves both success rates and efficiency in dynamic, long-horizon manipulation tasks. Project page: https://github.com/moured/ProAct-VLM