.png){kind=icon}
Return
Hypergraph-based motion generation with multi-modal interaction relational reasoning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.trc.2025.105349.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Introduces the RHINO framework for hypergraph-based, multi-agent, multi-modal motion prediction with explicit relational reasoning. • Captures group-wise interactions via a multi-scale hypergraph that models joint influence. • Uses agent-behavior graph to disentangle the multi-modality of driving behaviors. • Performs intention-conditioned reasoning over hyperedges. • Learns higher-order interaction patterns and yields human-interpretable explanations. • Delivers accurate multi-future trajectory predictions with an efficient residual decoder.
Journal
T
IF:
0
Papers:
196
Citations:
0
Organization
Cited Papers
No cited papers available