Robots improve task planning with adaptive mentor guidance
FISRF: Flexible Instructional Scaffolding Reflection Framework for Robotics Task Planning with Large Language Model
Robotics
Summary
Robots often make mistakes when trying to complete new tasks because they learn on their own and can repeat errors. The authors designed a system where a robot can get help from a mentor that adjusts its level of guidance based on how well the robot is doing. This way, the robot learns more effectively and makes fewer repeated mistakes. Tests both in virtual environments and on real robots showed that this method helps robots complete tasks more successfully and with less wasted effort.
What this means in practice
- •For robotics engineers: Improve robot task planning accuracy by integrating adaptive mentor guidance systems for error correction during planning stages.
- •For industrial automation teams: Deploy robots with reflective planning frameworks to reduce task execution failures and increase operational efficiency in manufacturing settings.
Authors
Qingmiao Liang, Jiatao Zhang, Runxin Zou, Yufan Song, Wei Song, Yuhua Zheng
Abstract
Large Language Models (LLMs) are widely adopted for reflective error correction in task planning; however, existing approaches primarily rely on autonomous exploration, rendering them prone to accumulating erroneous experiences during early interactions with new environments. To address this limitation, we propose the Flexible Instructional Scaffolding Reflection Framework (FISRF), an agent--mentor architecture that estimates the robot's Zone of Proximal Development (ZPD) in task planning and adaptively selects reflection strategies and mentor guidance, thereby facilitating the accumulation of effective error-correction experience. Experiments in ALFWorld and on real-world robotic platforms demonstrate that FISRF reduces the average number of error-correction rounds by 37% and redundant reasoning by 25.1%, while improving the overall task success rate by 8%. Project webpage : https://fisrfplanning.github.io/