Node and Edge Embedding Learning for Static Obstacle Segmentation

Jan 1, 2023·
Prathmesh Bele*
,
Apurva Kulkarni*
,
Hitul Desai
,
Amey Kavde
,
Dashrath Mali
,
Laxmikant Sahoo
,
et al.
· 1 min read
Type
Publication
Intellectual Property of India, Reference No. 202341087789
publications

Proposed a novel GNN architecture formulating free-space mapping as a scalable edge-prediction problem. Architected a dual-path Graph Attention Network to independently process node and edge features. Implemented class-aware edge retention via feature fusion, achieving parity with inflexible rule-based legacy systems.