IHGSL: Interpretable Heuristic Graph Structure Learning for Multi-Robot Autonomous Collaborative Systems

In multi-robot systems, capturing the complex and dynamic interaction relationships is essential for enhancing autonomous collaboration. However, existing learning-based approaches usually overlook the understanding of these relationships, leading to reliability issues and hindering their application to real-world scenarios. This paper proposes a novel approach called Interpretable Heuristic Graph Structure Learning (IHGSL) to better comprehend the complex collaborative relationships in multi-robot systems. We first construct a predicate space to define diverse predicates that express fundamental relationships. Then we employ the variational information bottleneck technique to acquire a latent representation of the current observation by aligning it with the historical trajectory. On this basis, the predicates that the robot should currently focus on the most are learned, and some interaction relationships are established accordingly. Thereby an interpretable relationship graph is generated heuristically to guide the achievement of multi-robot autonomous collaborative decision-making. Through experimental evaluation, we demonstrate the process of relationship inference, thus validating the interpretability of IHGSL. Compared with existing methods, IHGSL also achieves superior collaboration performance, which highlights the effectiveness of the learned heuristic graph structure.

Authors

• Yue Han
• Hanqi Li
• Cuiwei Liu
• Chen Liang
• Zhixiao Sun

Keywords

• Learning systems
• Navigation
• Robot kinematics
• Design methodology
• Decision making
• Collaboration
• Trajectory
• Multi-robot systems
• Reliability
• Intelligent robots
• Heuristic
• Graph Structure
• Multi-agent Systems
• Structure Learning
• Interactive Relationship
• Current Observations
• Latent Representation
• Historical Trajectory
• Decision-making Autonomy
• Relation Graph
• Inference Of Relationships
• Collaborative Decision-making
• Latent Variables
• Effective Learning
• Attention Mechanism
• Mutual Information
• Baseline Methods
• Relational Learning
• Observation Space
• Representative Trajectories
• Representative Observations
• Multi-agent Reinforcement Learning
• Aerial Robots
• Robot Trajectory
• Attention-based Methods
• Multilayer Perception
• Current Robot
• Compressed Representation
• High-level Policy