Reactive Multi-Robot Navigation in Outdoor Environments Through Uncertainty-Aware Active Learning of Human Preference Landscape
This work addresses the problem of flexible and safe multi-robot navigation in complex real-world settings for applications like disaster response, though it is incremental as it builds on existing preference learning and behavior adjustment methods.
The paper tackles the challenge of deploying multi-robot systems in uncertain outdoor environments by developing a framework that integrates real-time human guidance to adapt robot behaviors, achieving improved prediction accuracy and adaptation speed in a flood disaster search and rescue task with 20 users and 1764 feedback instances.
Compared with single robots, Multi-Robot Systems (MRS) can perform missions more efficiently due to the presence of multiple members with diverse capabilities. However, deploying an MRS in wide real-world environments is still challenging due to uncertain and various obstacles (e.g., building clusters and trees). With a limited understanding of environmental uncertainty on performance, an MRS cannot flexibly adjust its behaviors (e.g., teaming, load sharing, trajectory planning) to ensure both environment adaptation and task accomplishments. In this work, a novel joint preference landscape learning and behavior adjusting framework (PLBA) is designed. PLBA efficiently integrates real-time human guidance to MRS coordination and utilizes Sparse Variational Gaussian Processes with Varying Output Noise to quickly assess human preferences by leveraging spatial correlations between environment characteristics. An optimization-based behavior-adjusting method then safely adapts MRS behaviors to environments. To validate PLBA's effectiveness in MRS behavior adaption, a flood disaster search and rescue task was designed. 20 human users provided 1764 feedback based on human preferences obtained from MRS behaviors related to "task quality", "task progress", "robot safety". The prediction accuracy and adaptation speed results show the effectiveness of PLBA in preference learning and MRS behavior adaption.