NaviFormer uses a Transformer architecture inside deep reinforcement learning to jointly predict high-level routes and low-level collision-free trajectories for holistic navigation.
Leveraging single-goal predictions to improve the efficiency of multi-goal motion planning with dynamics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NaviFormer: A Deep Reinforcement Learning Transformer-like Model to Holistically Solve the Navigation Problem
NaviFormer uses a Transformer architecture inside deep reinforcement learning to jointly predict high-level routes and low-level collision-free trajectories for holistic navigation.